{"data":[{"context_length":1000000,"created":1794268800,"id":"gemini-4-carbon","model_spec":{"pricing":{"input":{"usd":2.5,"diem":2.5},"cache_input":{"usd":0.125,"diem":0.125},"output":{"usd":12.5,"diem":12.5}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 4 Carbon is Google's frontier model for long-horizon agentic work across software engineering, scientific reasoning, and cybersecurity defense, with a unified 1M token context window and deeper tunable thinking than Gemini 4 Argon.","name":"Gemini 4 Carbon","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1791849600,"id":"gemini-4-argon","model_spec":{"pricing":{"input":{"usd":2.5,"diem":2.5},"cache_input":{"usd":0.125,"diem":0.125},"output":{"usd":12.5,"diem":12.5}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 4 Argon is Google's frontier model for complex workflows across software engineering, enterprise knowledge work, and cybersecurity defense, with a unified 1M token context window and tunable thinking.","name":"Gemini 4 Argon","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1794614400,"id":"gemini-4-hydrogen","model_spec":{"pricing":{"input":{"usd":1.875,"diem":1.875},"cache_input":{"usd":0.09375,"diem":0.09375},"output":{"usd":9.375,"diem":9.375}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 4 Hydrogen is Google's fast, efficient model for coding and agentic work, with a unified 1M token context window and tunable thinking.","name":"Gemini 4 Hydrogen","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1791936000,"id":"pareto","model_spec":{"betaModel":true,"pricing":{"input":{"usd":1,"diem":1},"cache_input":{"usd":0.0375,"diem":0.0375},"output":{"usd":4,"diem":4}},"availableContextTokens":1000000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Pareto is a blended model that runs several frontier models in parallel on every request and returns one answer. It accepts text and image inputs.","name":"Pareto","modelSource":"https://unbiased.ai/model-card/","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1783555200,"id":"gemini-3-6-flash","model_spec":{"pricing":{"input":{"usd":0.9375,"diem":0.9375},"cache_input":{"usd":0.09375,"diem":0.09375},"output":{"usd":4.6875,"diem":4.6875}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 3.6 Flash, the successor to Gemini 3.5 Flash, is a high speed, high value thinking model with 1M context, designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.","name":"Gemini 3.6 Flash","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1786665600,"id":"gemini-3-7-flash","model_spec":{"pricing":{"input":{"usd":0.9375,"diem":0.9375},"cache_input":{"usd":0.09375,"diem":0.09375},"output":{"usd":4.6875,"diem":4.6875}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 3.7 Flash, the successor to Gemini 3.6 Flash, is built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.","name":"Gemini 3.7 Flash","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1788307200,"id":"gemini-3-8-flash","model_spec":{"pricing":{"input":{"usd":0.9375,"diem":0.9375},"cache_input":{"usd":0.09375,"diem":0.09375},"output":{"usd":4.6875,"diem":4.6875}},"model_sets":["venice_recommendations"],"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 3.8 Flash, the successor to Gemini 3.7 Flash, is built for complex coding, agentic workflows, and reliable multi-step execution, with 1M context and tunable thinking.","name":"Gemini 3.8 Flash","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1783555200,"id":"gemini-3-5-flash-lite","model_spec":{"pricing":{"input":{"usd":0.375,"diem":0.375},"cache_input":{"usd":0.0375,"diem":0.0375},"output":{"usd":3.125,"diem":3.125}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 3.5 Flash-Lite is the fastest, most cost-efficient Gemini 3.5 model with 1M context, ideal for everyday questions, summarization, and lightweight coding tasks.","name":"Gemini 3.5 Flash-Lite","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1787011200,"id":"z-ai-glm-5-3","model_spec":{"pricing":{"input":{"usd":1.75,"diem":1.75},"cache_input":{"usd":0.325,"diem":0.325},"output":{"usd":5.5,"diem":5.5}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window, and improves on GLM-5.2 in coding and in the balance between performance and token efficiency.","name":"GLM 5.3","modelSource":"https://huggingface.co/zai-org/GLM-5.3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1048576,"created":1787270400,"id":"z-ai-glm-5-3-flash","model_spec":{"pricing":{"input":{"usd":0.15,"diem":0.15},"cache_input":{"usd":0.03,"diem":0.03},"output":{"usd":0.5,"diem":0.5}},"model_sets":["venice_recommendations"],"availableContextTokens":1048576,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-5.3 Flash is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with visual context.","name":"GLM 5.3 Flash","modelSource":"https://huggingface.co/zai-org/GLM-5.3-Flash","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1781568000,"id":"zai-org-glm-5-2","model_spec":{"pricing":{"input":{"usd":1.4,"diem":1.4},"cache_input":{"usd":0.26,"diem":0.26},"output":{"usd":4.4,"diem":4.4}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","high","max"],"defaultReasoningEffort":"max","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-5.2, the successor to GLM-5.1, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports a longer context window than GLM-5.1 for processing extensive text and detailed analysis with fast inference speed.","name":"GLM 5.2","modelSource":"https://huggingface.co/zai-org/GLM-5.2","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":200000,"created":1775520000,"id":"zai-org-glm-5-1","model_spec":{"pricing":{"input":{"usd":1.54,"diem":1.54},"cache_input":{"usd":0.286,"diem":0.286},"output":{"usd":4.84,"diem":4.84}},"availableContextTokens":200000,"maxCompletionTokens":80000,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-5.1, the successor to GLM-5, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports large context windows for processing extensive text and detailed analysis with fast inference speed.","name":"GLM 5.1","modelSource":"https://huggingface.co/zai-org/GLM-5.1","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":198000,"created":1770768000,"id":"zai-org-glm-5","model_spec":{"pricing":{"input":{"usd":1,"diem":1},"cache_input":{"usd":0.2,"diem":0.2},"output":{"usd":3.2,"diem":3.2}},"availableContextTokens":198000,"maxCompletionTokens":32000,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-5, the successor to GLM-4.7, is a large language model developed by Z.ai, featuring significantly enhanced reasoning capabilities, improved instruction following, and support for multiple languages. Supports large context windows for processing extensive text and detailed analysis.","name":"GLM 5","modelSource":"https://huggingface.co/zai-org/GLM-5","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":200000,"created":1773532800,"id":"z-ai-glm-5-turbo","model_spec":{"pricing":{"input":{"usd":1.2,"diem":1.2},"cache_input":{"usd":0.24,"diem":0.24},"output":{"usd":4,"diem":4}},"availableContextTokens":200000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-5 Turbo is a fast inference model from Z.ai tuned for strong performance in agent-driven environments and production coding workflows.","name":"GLM 5 Turbo","modelSource":"https://huggingface.co/zai-org/GLM-5","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":200000,"created":1775001600,"id":"z-ai-glm-5v-turbo","model_spec":{"pricing":{"input":{"usd":1.5,"diem":1.5},"cache_input":{"usd":0.3,"diem":0.3},"output":{"usd":5,"diem":5}},"availableContextTokens":200000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-5V-Turbo is Z.ai's first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks with image and text inputs.","name":"GLM 5V Turbo","modelSource":"https://docs.z.ai/guides/vlm/glm-5v-turbo","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":200000,"created":1770163200,"id":"olafangensan-glm-4.7-flash-heretic","model_spec":{"pricing":{"input":{"usd":0.07,"diem":0.07},"cache_input":{"usd":0.035,"diem":0.035},"output":{"usd":0.4,"diem":0.4}},"availableContextTokens":200000,"maxCompletionTokens":24000,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-4.7-Flash-Heretic is an uncensored experimental variant of GLM-4.7-Flash, optimized for creative freedom and unfiltered dialogue with fast inference speed.","name":"GLM 4.7 Flash Heretic","modelSource":"https://huggingface.co/Olafangensan/GLM-4.7-Flash-heretic","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":198000,"created":1711929600,"id":"zai-org-glm-4.6","model_spec":{"pricing":{"input":{"usd":0.43,"diem":0.43},"cache_input":{"usd":0.08,"diem":0.08},"output":{"usd":1.75,"diem":1.75}},"availableContextTokens":198000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp4","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-4.6 is a large language model developed by Z.ai, featuring strong reasoning capabilities and support for multiple languages. Supports a large context window for processing extensive text and detailed analysis.","name":"GLM 4.6","modelSource":"https://huggingface.co/zai-org/GLM-4.6","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":198000,"created":1766534400,"id":"zai-org-glm-4.7","model_spec":{"pricing":{"input":{"usd":0.55,"diem":0.55},"cache_input":{"usd":0.11,"diem":0.11},"output":{"usd":2.65,"diem":2.65}},"availableContextTokens":198000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp4","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM-4.7, the successor to GLM-4.6, is a large language model developed by Z.ai, featuring strong reasoning capabilities and support for multiple languages. Supports a large context window for processing extensive text and detailed analysis.","name":"GLM 4.7","modelSource":"https://huggingface.co/zai-org/GLM-4.7","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1775001600,"id":"venice-uncensored-1-2","model_spec":{"pricing":{"input":{"usd":0.2,"diem":0.2},"output":{"usd":0.9,"diem":0.9}},"model_sets":["venice_recommendations"],"availableContextTokens":128000,"maxCompletionTokens":8192,"capabilities":{"optimizedForCode":false,"quantization":"fp16","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Venice Uncensored 1.2 is designed for maximum creative freedom and authentic interaction. Built for open-ended exploration, roleplay, and unfiltered dialogue with improved capabilities over 1.1.","name":"Venice Uncensored 1.2","modelSource":"https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition","offline":false,"privacy":"private","traits":["most_uncensored"],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1771545600,"id":"venice-uncensored-role-play","model_spec":{"pricing":{"input":{"usd":0.5,"diem":0.5},"output":{"usd":2,"diem":2}},"availableContextTokens":128000,"maxCompletionTokens":4096,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Optimized for creative roleplay scenarios with maximum freedom. Designed for immersive storytelling, character interactions, and open-ended creative writing.","name":"Venice Role Play Uncensored","modelSource":"https://huggingface.co/dphnAI/24B-3.2-RP-K2-final","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1794794400,"id":"qwen-4-max","model_spec":{"pricing":{"input":{"usd":1.5,"diem":1.5},"cache_input":{"usd":0.07500000000000001,"diem":0.07500000000000001},"cache_write":{"usd":1.875,"diem":1.875},"output":{"usd":4.5,"diem":4.5}},"availableContextTokens":1000000,"maxCompletionTokens":393216,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 4 Max is the flagship model of the Qwen 4 series. It accepts text, image, and video input, thinks by default with adjustable reasoning effort, and supports a 1M-token context window.","name":"Qwen 4 Max","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":262144,"created":1786492800,"id":"qwen-3-8-2-4t-a95b","model_spec":{"pricing":{"input":{"usd":2.5,"diem":2.5},"cache_input":{"usd":0.3125,"diem":0.3125},"output":{"usd":7.5,"diem":7.5}},"availableContextTokens":262144,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 3.8 2.4T is Alibaba's open-weight 2.4-trillion-parameter MoE model (95B active), with major gains in software engineering, research, and long-horizon agentic tasks. It is text-only, requires thinking mode, and supports a 262K-token context window.","name":"Qwen 3.8 2.4T","modelSource":"https://huggingface.co/Qwen/Qwen3.8-2.4T-A95B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1784678400,"id":"qwen-3-8-max","model_spec":{"pricing":{"input":{"usd":2.5,"diem":2.5},"cache_input":{"usd":0.3125,"diem":0.3125},"cache_write":{"usd":3.125,"diem":3.125},"output":{"usd":7.5,"diem":7.5}},"model_sets":["venice_recommendations"],"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 3.8 Max is Alibaba's flagship 2.4-trillion-parameter MoE model, with major gains over Qwen 3.7 Max in software engineering and office-productivity workflows and strong long-horizon, multi-agent performance. It accepts both text and vision-language input (images and video), operates in thinking mode only, and supports a 1M-token context window.","name":"Qwen 3.8 Max","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":262144,"created":1786924800,"id":"qwen-3-8-27b","model_spec":{"betaModel":true,"pricing":{"input":{"usd":0.45,"diem":0.45},"output":{"usd":3.2,"diem":3.2}},"availableContextTokens":262144,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","xhigh"],"defaultReasoningEffort":"xhigh","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 3.8 27B is a native vision-language dense model with 27B parameters. It improves coding, professional work, research, and long-horizon agentic tasks, with flexible thinking control and image and video understanding. It supports a native 262K-token context window.","name":"Qwen 3.8 27B","modelSource":"https://huggingface.co/Qwen/Qwen3.8-27B-FP8","offline":false,"privacy":"private","traits":["default_vision"],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1788998400,"id":"qwen-3-8-flash","model_spec":{"pricing":{"input":{"usd":0.14,"diem":0.14},"cache_input":{"usd":0.014,"diem":0.014},"output":{"usd":0.49,"diem":0.49}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 3.8 Flash is a multimodal model in the Qwen family, pairing strong reasoning and generation with remarkable speed. It natively supports a 1M-token context window, so it can process long documents, entire codebases, and complex conversations in a single pass. It excels at coding assistance, agentic workflows, and visual understanding, accepting text, image, and video input, and its thinking mode can be turned on or off per request.","name":"Qwen 3.8 Flash","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1779408000,"id":"qwen-3-7-max","model_spec":{"pricing":{"input":{"usd":2.7,"diem":2.7},"cache_input":{"usd":0.27,"diem":0.27},"cache_write":{"usd":3.35,"diem":3.35},"output":{"usd":8.05,"diem":8.05}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 3.7 Max is the largest model in the Qwen 3.7 series, with deep thinking, function calling, prompt caching, and multimodal input support for images and video. It excels at programming, office and productivity tasks, and long-running autonomous agent workflows.","name":"Qwen 3.7 Max","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1780358400,"id":"qwen-3-7-plus","model_spec":{"pricing":{"input":{"usd":0.5,"diem":0.5},"cache_input":{"usd":0.05,"diem":0.05},"cache_write":{"usd":0.625,"diem":0.625},"output":{"usd":2,"diem":2},"extended":{"context_token_threshold":256000,"input":{"usd":1.5,"diem":1.5},"output":{"usd":6,"diem":6},"cache_input":{"usd":0.15,"diem":0.15},"cache_write":{"usd":1.875,"diem":1.875}}},"model_sets":["venice_recommendations"],"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"constraints":{"temperature":{"default":0.7},"top_p":{"default":0.8}},"description":"Qwen 3.7 Plus, the successor to Qwen 3.6 Plus, is a reasoning model from Alibaba with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.","name":"Qwen 3.7 Plus","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1775433600,"id":"qwen-3-6-plus","model_spec":{"pricing":{"input":{"usd":0.625,"diem":0.625},"cache_input":{"usd":0.0625,"diem":0.0625},"cache_write":{"usd":0.78,"diem":0.78},"output":{"usd":3.75,"diem":3.75},"extended":{"context_token_threshold":256000,"input":{"usd":2.5,"diem":2.5},"output":{"usd":7.5,"diem":7.5},"cache_input":{"usd":0.0625,"diem":0.0625},"cache_write":{"usd":0.78,"diem":0.78}}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"constraints":{"temperature":{"default":0.7},"top_p":{"default":0.8}},"description":"Qwen 3.6 Plus Uncensored is an uncensored variant of Alibaba's Qwen 3.6 Plus, a reasoning model with exceptional performance across coding, reasoning, and general knowledge tasks. Features mixed reasoning, function calling, and multimodal input support.","name":"Qwen 3.6 Plus Uncensored","modelSource":"https://www.alibabacloud.com/blog/qwen3-6-plus-towards-real-world-agents_603005","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1776988800,"id":"qwen3-6-27b","model_spec":{"pricing":{"input":{"usd":0.325,"diem":0.325},"output":{"usd":3.25,"diem":3.25}},"availableContextTokens":256000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"constraints":{"temperature":{"default":1},"top_p":{"default":0.95}},"description":"The Qwen 3.6 27B native vision-language dense model builds upon the 3.5-27B version, with key improvements in agentic coding capabilities and enhanced STEM reasoning and inference skills. In the vision modality, it demonstrates significant advances in spatial intelligence, object localization, and detection, while video understanding, document OCR, and visual agent capabilities continue to improve steadily.","name":"Qwen 3.6 27B","modelSource":"https://huggingface.co/Qwen/Qwen3.6-27B-FP8","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1784505600,"id":"qwen3-6-35b-a3b","model_spec":{"betaModel":true,"pricing":{"input":{"usd":0.1,"diem":0.1},"output":{"usd":1,"diem":1}},"availableContextTokens":256000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":3,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"constraints":{"temperature":{"default":1},"top_p":{"default":0.95}},"description":"Qwen 3.6 35B A3B is a fast mixture-of-experts model with 35B total parameters and ~3B active per token. Strong at agentic coding, STEM reasoning, and tool use, with a native 256K context window.","name":"Qwen 3.6 35B A3B","modelSource":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1771200000,"id":"qwen3-5-397b-a17b","model_spec":{"pricing":{"input":{"usd":0.75,"diem":0.75},"output":{"usd":4.5,"diem":4.5}},"availableContextTokens":128000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":true,"supportsMultipleImages":true,"maxImages":5,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 3.5 is a reasoning model from Alibaba featuring a 397B parameter Mixture-of-Experts architecture with 17B active parameters. It excels at complex reasoning, coding, and general knowledge tasks.","name":"Qwen 3.5 397B","modelSource":"https://huggingface.co/Qwen/Qwen3.5-397B-A17B","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1771977600,"id":"qwen3-5-35b-a3b","model_spec":{"pricing":{"input":{"usd":0.15,"diem":0.15},"cache_input":{"usd":0.05,"diem":0.05},"output":{"usd":1,"diem":1}},"availableContextTokens":256000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":true,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"constraints":{"temperature":{"default":1},"top_p":{"default":0.95},"repetition_penalty":{"default":1}},"description":"Qwen 3.5 35B A3B is a highly efficient MoE model with 35B total parameters and only 3B active parameters. It surpasses the larger Qwen3-235B-A22B while being 6.7x smaller, excelling at reasoning, coding, and general knowledge tasks.","name":"Qwen 3.5 35B A3B","modelSource":"https://huggingface.co/Qwen/Qwen3.5-35B-A3B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1745903059,"id":"qwen3-235b-a22b-thinking-2507","model_spec":{"pricing":{"input":{"usd":0.45,"diem":0.45},"output":{"usd":3.5,"diem":3.5}},"availableContextTokens":128000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Reasons step by step before it answers. Built for in-depth research and handling long, complex documents. Ideal for technical work and high-precision tasks.","name":"Qwen 3 235B A22B Thinking 2507","modelSource":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1745903059,"id":"qwen3-235b-a22b-instruct-2507","model_spec":{"pricing":{"input":{"usd":0.15,"diem":0.15},"output":{"usd":0.75,"diem":0.75}},"availableContextTokens":128000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Answers directly, without a reasoning step. Built for in-depth research and handling long, complex documents. Ideal for technical work and high-precision tasks.","name":"Qwen 3 235B A22B Instruct 2507","modelSource":"https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1745903059,"id":"qwen3-next-80b","model_spec":{"pricing":{"input":{"usd":0.35,"diem":0.35},"output":{"usd":1.9,"diem":1.9}},"availableContextTokens":256000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp16","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Optimized for speed and efficiency.","name":"Qwen 3 Next 80b","modelSource":"https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1768521600,"id":"qwen3-vl-235b-a22b","model_spec":{"pricing":{"input":{"usd":0.21,"diem":0.21},"cache_input":{"usd":0.1,"diem":0.1},"output":{"usd":1.9,"diem":1.9}},"availableContextTokens":128000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen3-VL 235B vision-language model with MoE architecture. The largest model in the Qwen3-VL series, with superior visual perception, OCR, and multimodal reasoning.","name":"Qwen3 VL 235B","modelSource":"https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1769472000,"id":"qwen3-coder-480b-a35b-instruct-turbo","model_spec":{"pricing":{"input":{"usd":0.35,"diem":0.35},"cache_input":{"usd":0.04,"diem":0.04},"output":{"usd":1.5,"diem":1.5}},"availableContextTokens":256000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":true,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Turbo variant of Qwen3 Coder 480B, optimized for faster inference on code tasks.","name":"Qwen 3 Coder 480B Turbo","modelSource":"https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1775088000,"id":"google-gemma-4-26b-a4b-it","model_spec":{"pricing":{"input":{"usd":0.13,"diem":0.13},"cache_input":{"usd":0.05,"diem":0.05},"output":{"usd":0.4,"diem":0.4}},"availableContextTokens":256000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"bf16","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":true,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemma 4 26B A4B is a Mixture-of-Experts model from Google DeepMind with 26B total parameters and only 4B active per token, offering fast inference at high quality. It handles text, image, and video input, supports 256K context, function calling, and reasoning with configurable thinking modes.","name":"Google Gemma 4 26B A4B Instruct","modelSource":"https://huggingface.co/google/gemma-4-26B-A4B-it","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1775174400,"id":"google-gemma-4-31b-it","model_spec":{"pricing":{"input":{"usd":0.12,"diem":0.12},"cache_input":{"usd":0.09,"diem":0.09},"output":{"usd":0.36,"diem":0.36}},"model_sets":["venice_recommendations"],"availableContextTokens":256000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp4","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":true,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemma 4 31B is a dense model from Google DeepMind with 31B parameters, delivering frontier-level reasoning performance. It handles text, image, and video input, supports 256K context, function calling, and configurable thinking modes.","name":"Google Gemma 4 31B Instruct","modelSource":"https://huggingface.co/google/gemma-4-31B-it","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1776038400,"id":"gemma-4-uncensored","model_spec":{"pricing":{"input":{"usd":0.1625,"diem":0.1625},"output":{"usd":0.5,"diem":0.5}},"availableContextTokens":256000,"maxCompletionTokens":8192,"capabilities":{"optimizedForCode":false,"quantization":"int4","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":true,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemma 4 Uncensored is an uncensored variant of Google Gemma 4 26B, a Mixture-of-Experts model with 26B total parameters and only 4B active per token. Fine-tuned for uncensored chat without content filtering, it supports 256K context, coding, and general-purpose conversation.","name":"Gemma 4 Uncensored","modelSource":"https://huggingface.co/Jiunsong/supergemma4-26b-uncensored-gguf-v2","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":198000,"created":1762214400,"id":"google-gemma-3-27b-it","model_spec":{"pricing":{"input":{"usd":0.12,"diem":0.12},"output":{"usd":0.2,"diem":0.2}},"availableContextTokens":198000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's open source model, successor to Gemma 2.","name":"Google Gemma 3 27B Instruct","modelSource":"https://huggingface.co/google/gemma-3-27b-it","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1776470400,"id":"grok-4-3","model_spec":{"pricing":{"input":{"usd":1.42,"diem":1.42},"cache_input":{"usd":0.23,"diem":0.23},"output":{"usd":2.83,"diem":2.83},"extended":{"context_token_threshold":200000,"input":{"usd":2.83,"diem":2.83},"output":{"usd":5.67,"diem":5.67},"cache_input":{"usd":0.45,"diem":0.45}}},"availableContextTokens":1000000,"maxCompletionTokens":32000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":true},"description":"Grok 4.3 is a reasoning model from xAI with function calling, structured outputs, and a 1M-token context window. Suited for agentic workflows, instruction-following tasks, and applications requiring high factual accuracy.","name":"Grok 4.3","modelSource":"https://docs.x.ai/developers/models","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":500000,"created":1783382400,"id":"grok-4-5","model_spec":{"pricing":{"input":{"usd":2.27,"diem":2.27},"cache_input":{"usd":0.34,"diem":0.34},"output":{"usd":6.8,"diem":6.8},"extended":{"context_token_threshold":200000,"input":{"usd":4.53,"diem":4.53},"output":{"usd":13.6,"diem":13.6},"cache_input":{"usd":0.68,"diem":0.68}}},"availableContextTokens":500000,"maxCompletionTokens":32000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":true},"description":"Grok 4.5 is xAI's intelligent coding model for agentic software engineering and workflow tasks, with function calling, structured outputs, and a 500K-token context window.","name":"Grok 4.5","modelSource":"https://docs.x.ai/developers/models","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":500000,"created":1786320000,"id":"grok-4-6","model_spec":{"pricing":{"input":{"usd":2.27,"diem":2.27},"cache_input":{"usd":0.57,"diem":0.57},"output":{"usd":6.8,"diem":6.8},"extended":{"context_token_threshold":200000,"input":{"usd":4.53,"diem":4.53},"output":{"usd":13.6,"diem":13.6},"cache_input":{"usd":1.13,"diem":1.13}}},"availableContextTokens":500000,"maxCompletionTokens":200000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":true},"description":"Grok 4.6 is xAI's multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.","name":"Grok 4.6","modelSource":"https://docs.x.ai/developers/models","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":500000,"created":1789516800,"id":"grok-4-7","model_spec":{"pricing":{"input":{"usd":2.27,"diem":2.27},"cache_input":{"usd":0.57,"diem":0.57},"output":{"usd":6.8,"diem":6.8},"extended":{"context_token_threshold":200000,"input":{"usd":4.53,"diem":4.53},"output":{"usd":13.6,"diem":13.6},"cache_input":{"usd":1.13,"diem":1.13}}},"model_sets":["venice_recommendations"],"availableContextTokens":500000,"maxCompletionTokens":200000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":true},"description":"Grok 4.7, the successor to Grok 4.6, is xAI's multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.","name":"Grok 4.7","modelSource":"https://docs.x.ai/developers/models","offline":false,"privacy":"private","traits":["most_intelligent"]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":2000000,"created":1773273600,"id":"grok-4-20","model_spec":{"pricing":{"input":{"usd":1.42,"diem":1.42},"cache_input":{"usd":0.23,"diem":0.23},"output":{"usd":2.83,"diem":2.83},"extended":{"context_token_threshold":200000,"input":{"usd":2.83,"diem":2.83},"output":{"usd":5.67,"diem":5.67},"cache_input":{"usd":0.45,"diem":0.45}}},"availableContextTokens":2000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":true},"description":"Grok 4.20 is xAI's multimodal reasoning model with strong tool use, structured output support, and a 2M-token context window.","name":"Grok 4.20","modelSource":"https://docs.x.ai/developers/models","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":2000000,"created":1773273600,"id":"grok-4-20-multi-agent","model_spec":{"pricing":{"input":{"usd":1.42,"diem":1.42},"cache_input":{"usd":0.23,"diem":0.23},"output":{"usd":2.83,"diem":2.83},"extended":{"context_token_threshold":200000,"input":{"usd":2.83,"diem":2.83},"output":{"usd":5.67,"diem":5.67},"cache_input":{"usd":0.45,"diem":0.45}}},"availableContextTokens":2000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":false,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":true},"description":"Grok 4.20 Multi-Agent is a variant of xAI Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information across complex tasks.","name":"Grok 4.20 Multi-Agent","modelSource":"https://x.ai/api","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1779321600,"id":"grok-build-0-1","model_spec":{"pricing":{"input":{"usd":1,"diem":1},"cache_input":{"usd":0.2,"diem":0.2},"output":{"usd":2,"diem":2},"extended":{"context_token_threshold":200000,"input":{"usd":2,"diem":2},"output":{"usd":4,"diem":4},"cache_input":{"usd":0.4,"diem":0.4}}},"availableContextTokens":256000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"xAI's fast coding model trained specifically for agentic coding, currently in early access.","name":"Grok Build 0.1","modelSource":"https://docs.x.ai/developers/models/grok-build-0.1","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1768435200,"id":"mistral-small-3-2-24b-instruct","model_spec":{"pricing":{"input":{"usd":0.09375,"diem":0.09375},"output":{"usd":0.25,"diem":0.25}},"availableContextTokens":256000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Mistral Small 3.2 is a 24B parameter model optimized for efficiency and performance. Ideal for general-purpose tasks with balanced speed and capability.","name":"Mistral Small 3.2 24B Instruct","modelSource":"https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1771459200,"id":"gemini-3-1-pro-preview","model_spec":{"pricing":{"input":{"usd":2.5,"diem":2.5},"cache_input":{"usd":0.5,"diem":0.5},"cache_write":{"usd":0.5,"diem":0.5},"output":{"usd":15,"diem":15},"extended":{"context_token_threshold":200000,"input":{"usd":5,"diem":5},"output":{"usd":22.5,"diem":22.5},"cache_input":{"usd":0.5,"diem":0.5},"cache_write":{"usd":0.5,"diem":0.5}}},"availableContextTokens":1000000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":20,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 3.1 Pro is an evolution of Google's flagship frontier model with 1M context, advancing high-precision multimodal reasoning across text, image, and code.","name":"Gemini 3.1 Pro Preview","modelSource":"https://deepmind.google/models/gemini/pro/","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1779408000,"id":"gemini-3-5-flash","model_spec":{"pricing":{"input":{"usd":1.55,"diem":1.55},"cache_input":{"usd":0.155,"diem":0.155},"cache_write":{"usd":0.086,"diem":0.086},"output":{"usd":9.45,"diem":9.45}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":20,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 3.5 Flash is a high speed, high value thinking model with 1M context, designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.","name":"Gemini 3.5 Flash","modelSource":"https://deepmind.google/models/gemini/flash/","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1766102400,"id":"gemini-3-flash-preview","model_spec":{"pricing":{"input":{"usd":0.7,"diem":0.7},"cache_input":{"usd":0.07,"diem":0.07},"output":{"usd":3.75,"diem":3.75}},"availableContextTokens":256000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi-turn chat, and coding assistance. It delivers near Pro level reasoning with substantially lower latency.","name":"Gemini 3 Flash Preview","modelSource":"https://deepmind.google/models/gemini/flash/","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1781049600,"id":"claude-fable-5","model_spec":{"pricing":{"input":{"usd":10,"diem":10},"cache_input":{"usd":1,"diem":1},"cache_write":{"usd":12.5,"diem":12.5},"output":{"usd":50,"diem":50}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Fable 5 is a model from Anthropic designed for demanding reasoning and long-horizon agentic work. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities.","name":"Claude Fable 5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1787961600,"id":"claude-fable-5-1","model_spec":{"pricing":{"input":{"usd":10,"diem":10},"cache_input":{"usd":0.25,"diem":0.25},"cache_write":{"usd":12.5,"diem":12.5},"output":{"usd":50,"diem":50}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end development, and finance and analysis tasks. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities, and tends to be more concise in its plans and summaries.","name":"Claude Fable 5.1","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1794182400,"id":"claude-fable-5-2","model_spec":{"pricing":{"input":{"usd":8,"diem":8},"cache_input":{"usd":0.2,"diem":0.2},"cache_write":{"usd":10,"diem":10},"output":{"usd":40,"diem":40}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Fable 5.2 improves on Claude Fable 5.1 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work such as long code refactors, front-end development, and finance and analysis tasks. It features a 1M token context window, 128K max output tokens, always-on adaptive thinking, and strong multimodal capabilities, and tends to be more concise in its plans and summaries.","name":"Claude Fable 5.2","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1784764800,"id":"claude-opus-5","model_spec":{"pricing":{"input":{"usd":5,"diem":5},"cache_input":{"usd":0.5,"diem":0.5},"cache_write":{"usd":6.25,"diem":6.25},"output":{"usd":25,"diem":25}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Opus 5, the successor to Opus 4.8, delivers major gains in agentic coding, professional knowledge work, and long-horizon reasoning, with a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.","name":"Claude Opus 5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1784764800,"id":"claude-opus-5-fast","model_spec":{"pricing":{"input":{"usd":10,"diem":10},"cache_input":{"usd":1,"diem":1},"cache_write":{"usd":12.5,"diem":12.5},"output":{"usd":50,"diem":50}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Opus 5 (Fast) is a speed-optimized variant of Claude Opus 5, offering the same 1M token context window and strong performance across agentic coding, professional knowledge work, and long-horizon reasoning — with lower latency.","name":"Claude Opus 5 Fast","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1789689600,"id":"claude-opus-5-5","model_spec":{"pricing":{"input":{"usd":4,"diem":4},"cache_input":{"usd":0.2,"diem":0.2},"cache_write":{"usd":5,"diem":5},"output":{"usd":20,"diem":20}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Opus 5.5 is a step-change improvement over Opus 5, with the biggest gains in agentic coding, long-running agentic tasks, and knowledge work. It is also a much better collaborator on long-running work, with a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.","name":"Claude Opus 5.5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1790380800,"id":"claude-opus-5-5-fast","model_spec":{"pricing":{"input":{"usd":8,"diem":8},"cache_input":{"usd":0.4,"diem":0.4},"cache_write":{"usd":10,"diem":10},"output":{"usd":40,"diem":40}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Opus 5.5 Fast serves the same Opus 5.5 model with faster output generation, a 1M token context window, up to 128K output tokens, adaptive thinking, vision, and tool calling.","name":"Claude Opus 5.5 Fast","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1779926400,"id":"claude-opus-4-8","model_spec":{"pricing":{"input":{"usd":5,"diem":5},"cache_input":{"usd":0.5,"diem":0.5},"cache_write":{"usd":6.25,"diem":6.25},"output":{"usd":25,"diem":25}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Opus 4.8 is the successor to Opus 4.7 in Anthropic's Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.","name":"Claude Opus 4.8","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1776297600,"id":"claude-opus-4-7","model_spec":{"pricing":{"input":{"usd":5,"diem":5},"cache_input":{"usd":0.5,"diem":0.5},"cache_write":{"usd":6.25,"diem":6.25},"output":{"usd":25,"diem":25}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Opus 4.7 is a model from Anthropic for complex reasoning and agentic coding. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.","name":"Claude Opus 4.7","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1770249600,"id":"claude-opus-4-6","model_spec":{"pricing":{"input":{"usd":5,"diem":5},"cache_input":{"usd":0.5,"diem":0.5},"cache_write":{"usd":6.25,"diem":6.25},"output":{"usd":25,"diem":25}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Opus 4.6 is a reasoning model from Anthropic, building on Opus 4.5 with enhanced performance across complex software engineering, agentic workflows, and long-horizon tasks. It features a 1M token context window, improved multimodal capabilities, and stronger robustness to prompt injection.","name":"Claude Opus 4.6","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":198000,"created":1764979200,"id":"claude-opus-4-5","model_spec":{"pricing":{"input":{"usd":5,"diem":5},"cache_input":{"usd":0.5,"diem":0.5},"cache_write":{"usd":6.25,"diem":6.25},"output":{"usd":25,"diem":25}},"availableContextTokens":198000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Opus 4.5 is Anthropic's frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and reasoning benchmarks, and improved robustness to prompt injection.","name":"Claude Opus 4.5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1782691200,"id":"claude-sonnet-5","model_spec":{"pricing":{"input":{"usd":2,"diem":2},"cache_input":{"usd":0.2,"diem":0.2},"cache_write":{"usd":2.5,"diem":2.5},"output":{"usd":10,"diem":10}},"availableContextTokens":1000000,"maxCompletionTokens":64000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Sonnet 5 follows Sonnet 4.6, substantially improving on it in coding and agentic work and reaching near-Opus quality on many tasks. It features a 1M token context window, adaptive thinking, and strong document and vision understanding.","name":"Claude Sonnet 5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1790380800,"id":"claude-sonnet-5-5","model_spec":{"pricing":{"input":{"usd":2,"diem":2},"cache_input":{"usd":0.1,"diem":0.1},"cache_write":{"usd":2.5,"diem":2.5},"output":{"usd":10,"diem":10}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Sonnet 5.5 is a step-change improvement over Sonnet 5. It performs great with well-scoped everyday tasks like building features, fixing bugs, and creating polished documents, slides, and spreadsheets. Sonnet 5.5 also improves on communication and writes more clearly than Sonnet 5. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.","name":"Claude Sonnet 5.5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1791331200,"id":"claude-haiku-5-5","model_spec":{"pricing":{"input":{"usd":0.1,"diem":0.1},"cache_input":{"usd":0.01,"diem":0.01},"cache_write":{"usd":0.125,"diem":0.125},"output":{"usd":0.5,"diem":0.5},"extended":{"context_token_threshold":100000,"input":{"usd":0.5,"diem":0.5},"output":{"usd":2.5,"diem":2.5},"cache_input":{"usd":0.05,"diem":0.05},"cache_write":{"usd":0.625,"diem":0.625}}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Haiku 5.5 is built for high-volume, latency-sensitive work such as classification, routing, extraction, and subagent tasks. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong document and vision understanding.","name":"Claude Haiku 5.5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1771286400,"id":"claude-sonnet-4-6","model_spec":{"pricing":{"input":{"usd":3,"diem":3},"cache_input":{"usd":0.3,"diem":0.3},"cache_write":{"usd":3.75,"diem":3.75},"output":{"usd":15,"diem":15}},"availableContextTokens":1000000,"maxCompletionTokens":64000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Claude Sonnet 4.6 is Anthropic's best combination of speed and intelligence, offering strong performance on coding, reasoning, and general tasks with excellent speed and cost efficiency. It features a 1M token context window and 64K max output tokens.","name":"Claude Sonnet 4.6","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1762387200,"id":"openai-gpt-oss-120b","model_spec":{"pricing":{"input":{"usd":0.07,"diem":0.07},"output":{"usd":0.3,"diem":0.3}},"availableContextTokens":128000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation","name":"OpenAI GPT OSS 120B","modelSource":"https://huggingface.co/openai/gpt-oss-120b","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1792713600,"id":"kimi-k3-1-pro","model_spec":{"pricing":{"input":{"usd":2,"diem":2},"cache_input":{"usd":0.2,"diem":0.2},"output":{"usd":10,"diem":10}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"max","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Kimi K3.1 Pro is Moonshot AI's flagship multimodal reasoning model and the post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, agentic workflows, financial research, and 3D modeling through CAD code.","name":"Kimi K3.1 Pro","modelSource":"https://www.kimi.ai/blog/kimi-k3-1-pro","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1792713600,"id":"kimi-k3-1-pro-highspeed","model_spec":{"pricing":{"input":{"usd":5,"diem":5},"cache_input":{"usd":0.375,"diem":0.375},"output":{"usd":25,"diem":25}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"max","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Kimi K3.1 Pro Highspeed is the faster variant of Kimi K3.1 Pro, Moonshot AI's flagship multimodal reasoning model. It offers the same quality and 1M-token context window with substantially higher output speed for latency-sensitive coding and agentic workflows.","name":"Kimi K3.1 Pro Highspeed","modelSource":"https://www.kimi.ai/blog/kimi-k3-1-pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1784160000,"id":"kimi-k3","model_spec":{"pricing":{"input":{"usd":3.75,"diem":3.75},"cache_input":{"usd":0.375,"diem":0.375},"output":{"usd":18.75,"diem":18.75}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"max","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.","name":"Kimi K3","modelSource":"https://huggingface.co/moonshotai/Kimi-K3","offline":false,"privacy":"private","traits":["default_reasoning"]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1785715200,"id":"kimi-k3-fast-api","model_spec":{"pricing":{"input":{"usd":4.5,"diem":4.5},"cache_input":{"usd":0.45,"diem":0.45},"output":{"usd":22.5,"diem":22.5}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"max","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Kimi K3 is an ultra-large-scale, open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at navigating large repositories, using tools, debugging, and iterating against images, logs, tests, and runtime feedback.","name":"Kimi K3 Fast","modelSource":"https://huggingface.co/moonshotai/Kimi-K3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1781308800,"id":"kimi-k2-7-code","model_spec":{"pricing":{"input":{"usd":0.75,"diem":0.75},"cache_input":{"usd":0.16,"diem":0.16},"output":{"usd":3.5,"diem":3.5}},"availableContextTokens":256000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"int4","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built on Kimi K2.6, with 1T total parameters and 32B active parameters. It always operates in thinking mode, supports text and image input, and targets long-horizon software engineering, agentic task decomposition, and multi-turn coding workflows with 256K context.","name":"Kimi K2.7 Code","modelSource":"https://huggingface.co/moonshotai/Kimi-K2.7-Code","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1776643200,"id":"kimi-k2-6","model_spec":{"pricing":{"input":{"usd":0.75,"diem":0.75},"cache_input":{"usd":0.16,"diem":0.16},"output":{"usd":3.5,"diem":3.5}},"availableContextTokens":256000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"int4","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Kimi K2.6 is an open-source, native multimodal agentic model from Moonshot AI with 1T total parameters and 32B active parameters. It excels at long-horizon coding, coding-driven design, agent swarm orchestration, and proactive autonomous execution with a 256K-token context window.","name":"Kimi K2.6","modelSource":"https://huggingface.co/moonshotai/Kimi-K2.6","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1781136000,"id":"xiaomi-mimo-v2-5","model_spec":{"pricing":{"input":{"usd":0.4,"diem":0.4},"cache_input":{"usd":0.08,"diem":0.08},"output":{"usd":2,"diem":2}},"availableContextTokens":1000000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"MiMo-V2.5 is Xiaomi's native omnimodal model with strong agentic capabilities, supporting text, image, video, and audio understanding in a unified architecture. Built on a sparse Mixture-of-Experts backbone with 310B total and 15B active parameters, it delivers long-context reasoning up to 1M tokens, function calling, and multimodal perception.","name":"MiMo-V2.5","modelSource":"https://huggingface.co/XiaomiMiMo/MiMo-V2.5","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1790553600,"id":"xiaomi-mimo-v2-6-flash","model_spec":{"pricing":{"input":{"usd":0.175,"diem":0.175},"cache_input":{"usd":0.00375,"diem":0.00375},"output":{"usd":0.35,"diem":0.35}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"MiMo-V2.6-Flash is Xiaomi's efficiency-balanced omnimodal model: a sparse Mixture-of-Experts with 309B total and 15B activated parameters, natively understanding text, image, video, and audio with a 1M-token context window. Trained with mixed reinforcement learning across coding, general agents, visual, and cybersecurity tasks, it is built for long-horizon coding, tool use, and computer use.","name":"MiMo-V2.6-Flash","modelSource":"https://huggingface.co/XiaomiMiMo/MiMo-V2.6-Flash-RL","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1776988800,"id":"deepseek-v4-pro","model_spec":{"pricing":{"input":{"usd":1.65,"diem":1.65},"cache_input":{"usd":0.33,"diem":0.33},"output":{"usd":3.301,"diem":3.301}},"availableContextTokens":1000000,"maxCompletionTokens":262144,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.","name":"DeepSeek V4 Pro","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1776988800,"id":"deepseek-v4-flash","model_spec":{"pricing":{"input":{"usd":0.138,"diem":0.138},"cache_input":{"usd":0.028,"diem":0.028},"output":{"usd":0.275,"diem":0.275}},"availableContextTokens":1000000,"maxCompletionTokens":262144,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4 Flash is an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.","name":"DeepSeek V4 Flash 0423","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1785456000,"id":"deepseek-v4-flash-0731","model_spec":{"pricing":{"input":{"usd":0.13,"diem":0.13},"cache_input":{"usd":0.028,"diem":0.028},"output":{"usd":0.26,"diem":0.26}},"availableContextTokens":1000000,"maxCompletionTokens":262144,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4 Flash 0731 follows the 0423 release of DeepSeek V4 Flash, an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.","name":"DeepSeek V4 Flash 0731","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1788998400,"id":"deepseek-v4-1-flash","model_spec":{"pricing":{"input":{"usd":0.3,"diem":0.3},"cache_input":{"usd":0.0075,"diem":0.0075},"output":{"usd":1.2,"diem":1.2}},"availableContextTokens":1000000,"maxCompletionTokens":262144,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.","name":"DeepSeek V4.1 Flash","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1792195200,"id":"deepseek-v4-1-flash-1017","model_spec":{"pricing":{"input":{"usd":0.3,"diem":0.3},"cache_input":{"usd":0.0075,"diem":0.0075},"output":{"usd":1.2,"diem":1.2}},"availableContextTokens":1000000,"maxCompletionTokens":262144,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.","name":"DeepSeek v4.1 Flash (1017)","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1792713600,"id":"deepseek-v4-1-flash-uncensored","model_spec":{"pricing":{"input":{"usd":0.33,"diem":0.33},"cache_input":{"usd":0.00825,"diem":0.00825},"output":{"usd":1.32,"diem":1.32}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4.1 Flash Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.","name":"DeepSeek V4.1 Flash Uncensored","modelSource":"https://huggingface.co/dealignai/DeepSeek-V4.1-Flash-UNCENSORED-FP8","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1793059200,"id":"deepseek-v4-1-flash-1017-uncensored","model_spec":{"pricing":{"input":{"usd":0.33,"diem":0.33},"cache_input":{"usd":0.00825,"diem":0.00825},"output":{"usd":1.32,"diem":1.32}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4.1 Flash 1017 Uncensored is an abliterated, uncensored variant of DeepSeek V4.1 Flash 1017, a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.","name":"DeepSeek V4.1 Flash 1017 Uncensored","modelSource":"https://huggingface.co/dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8","offline":false,"privacy":"private","traits":["app_default","default","function_calling_default"],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1048576,"created":1794528000,"id":"glm-5-3-flash-uncensored","model_spec":{"pricing":{"input":{"usd":0.165,"diem":0.165},"cache_input":{"usd":0.033,"diem":0.033},"output":{"usd":0.55,"diem":0.55}},"availableContextTokens":1048576,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM 5.3 Flash Uncensored is an abliterated, uncensored variant of GLM-5.3 Flash, a reasoning model designed for coding, sustained agentic work, and production workloads, with a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.","name":"GLM 5.3 Flash Uncensored","modelSource":"https://huggingface.co/dealignai/GLM-5.3-Flash-UNCENSORED-FP8","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1792713600,"id":"deepseek-v4-1-flash-1017-ultrafast","model_spec":{"pricing":{"input":{"usd":3,"diem":3},"cache_input":{"usd":0.06,"diem":0.06},"output":{"usd":12,"diem":12}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4.1 Flash is a multimodal Mixture-of-Experts model with 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance.","name":"DeepSeek V4.1 Flash 1017 Ultrafast","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":160000,"created":1764806400,"id":"deepseek-v3.2","model_spec":{"pricing":{"input":{"usd":0.33,"diem":0.33},"cache_input":{"usd":0.16,"diem":0.16},"output":{"usd":0.48,"diem":0.48}},"availableContextTokens":160000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek-V3.2 is an efficient large language model with DeepSeek Sparse Attention (DSA) for long contexts. It features strong reasoning and tool-use skills, achieving top results on the 2025 IMO and IOI.","name":"DeepSeek V3.2","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V3.2","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1782604800,"id":"seed-2-1-turbo","model_spec":{"pricing":{"input":{"usd":0.625,"diem":0.625},"cache_input":{"usd":0.125,"diem":0.125},"output":{"usd":3.125,"diem":3.125}},"availableContextTokens":256000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"maxVideos":4,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Seed 2.1 Turbo (Dola-Seed-2.1) is ByteDance’s next-generation multimodal model for the coding and agent era, with engineering-grade code delivery, long-horizon agent execution, and upgraded GUI and video understanding. Supports text, image, and video inputs with a 256K context window.","name":"Seed 2.1 Turbo","modelSource":"https://console.byteplus.com/ark/region:ark+ap-southeast-1/model/detail?Id=dola-seed-2-1-turbo","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1786665600,"id":"deepseek-v4-pro-0813","model_spec":{"pricing":{"input":{"usd":1.65,"diem":1.65},"cache_input":{"usd":0.165,"diem":0.165},"output":{"usd":4.95,"diem":4.95}},"availableContextTokens":1000000,"maxCompletionTokens":262144,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4 Pro is a 1.6T-parameter Mixture-of-Experts model with 49B active parameters and a 1M-token context window. Built for advanced reasoning, coding, and long-horizon agentic workflows with a hybrid attention system for efficient long-context processing.","name":"DeepSeek V4 Pro 0813","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813","offline":false,"privacy":"private","traits":["default_code"]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1786233600,"id":"deepseek-v4-flash-0731-fast","model_spec":{"pricing":{"input":{"usd":0.35,"diem":0.35},"cache_input":{"usd":0.0875,"diem":0.0875},"output":{"usd":0.7,"diem":0.7}},"availableContextTokens":1000000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4 Flash 0731 follows the 0423 release of DeepSeek V4 Flash, an efficiency-optimized 284B-parameter Mixture-of-Experts model with 13B active parameters and a 1M-token context window. Tuned for fast inference and high-throughput workloads while maintaining strong reasoning and coding performance.","name":"DeepSeek V4 Flash 0731 Fast","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1783468800,"id":"aion-labs-aion-3-0","model_spec":{"pricing":{"input":{"usd":3.75,"diem":3.75},"cache_input":{"usd":0.9375,"diem":0.9375},"output":{"usd":7.5,"diem":7.5}},"availableContextTokens":128000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Aion 3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.","name":"Aion 3.0","modelSource":"https://www.aionlabs.ai/docs/models/","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1783468800,"id":"aion-labs-aion-3-0-mini","model_spec":{"pricing":{"input":{"usd":0.875,"diem":0.875},"cache_input":{"usd":0.225,"diem":0.225},"output":{"usd":1.75,"diem":1.75}},"availableContextTokens":128000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Aion 3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.","name":"Aion 3.0 Mini","modelSource":"https://www.aionlabs.ai/docs/models/","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":262144,"created":1790121600,"id":"aion-labs-aion-3-5","model_spec":{"pricing":{"input":{"usd":3.75,"diem":3.75},"cache_input":{"usd":0.9375,"diem":0.9375},"output":{"usd":7.5,"diem":7.5}},"availableContextTokens":262144,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Aion 3.5, the successor to Aion 3.0, is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models, with a longer context window. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.","name":"Aion 3.5","modelSource":"https://www.aionlabs.ai/docs/models/","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":262144,"created":1790121600,"id":"aion-labs-aion-3-5-mini","model_spec":{"pricing":{"input":{"usd":0.875,"diem":0.875},"cache_input":{"usd":0.225,"diem":0.225},"output":{"usd":1.75,"diem":1.75}},"availableContextTokens":262144,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. Multiple specialized models collaborate on each response to produce stronger narrative structure and more compelling tension and conflict at lower cost. It handles mature and darker themes with nuance and supports tool calling for richer interactive fiction.","name":"Aion 3.5 Mini","modelSource":"https://www.aionlabs.ai/docs/models/","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1790812800,"id":"abliteration-abliterated-model-large-v2","model_spec":{"pricing":{"input":{"usd":3,"diem":3},"cache_input":{"usd":0.3,"diem":0.3},"output":{"usd":5,"diem":5}},"availableContextTokens":1000000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Abliterated Large V2 is Abliteration AI's unrestricted reasoning model, based on GLM-5.3 and further abliterated and fine-tuned. Text-only with 1M context, for harder reasoning and evaluation workloads. Always reasons; depth can be set to low, high, or max.","name":"Abliterated Large V2","modelSource":"https://docs.abliteration.ai/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1792713600,"id":"abliteration-abliterated-model-large-flash","model_spec":{"pricing":{"input":{"usd":1.25,"diem":1.25},"cache_input":{"usd":0.125,"diem":0.125},"output":{"usd":2.5,"diem":2.5}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Abliterated Large Flash is Abliteration AI's unrestricted multimodal model, based on DeepSeek V4.1 Flash and further abliterated. It has 552B backbone parameters (8B active on input, 16B on output) and a 1M-token context window. It natively processes images and text, with strong reasoning, coding, and agentic performance and no content-filtering guardrails.","name":"Abliterated Large Flash","modelSource":"https://docs.abliteration.ai/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1727966436,"id":"llama-3.2-3b","model_spec":{"pricing":{"input":{"usd":0.15,"diem":0.15},"output":{"usd":0.6,"diem":0.6}},"availableContextTokens":128000,"maxCompletionTokens":4096,"capabilities":{"optimizedForCode":false,"quantization":"fp16","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Llama 3.2 3B is a lightweight model from Meta's Llama 3.2 family, sized for fast, low-cost tasks such as summarization, classification and rewriting. It supports text input and output with a 128K-token context window and handles several languages.","name":"Llama 3.2 3B","modelSource":"https://huggingface.co/meta-llama/Llama-3.2-3B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1743897600,"id":"llama-3.3-70b","model_spec":{"pricing":{"input":{"usd":0.7,"diem":0.7},"output":{"usd":2.8,"diem":2.8}},"availableContextTokens":128000,"maxCompletionTokens":4096,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Llama 3.3 70B is Meta's instruction-tuned 70-billion-parameter Llama model, which Meta reports performs close to its much larger Llama 3.1 405B on many tasks. It supports text input and output with a 128K-token context window, for chat, writing and code.","name":"Llama 3.3 70B","modelSource":"https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1048576,"created":1791763200,"id":"muse-wonder","model_spec":{"pricing":{"input":{"usd":5,"diem":5},"cache_input":{"usd":0.25,"diem":0.25},"output":{"usd":25,"diem":25}},"model_sets":["venice_recommendations"],"availableContextTokens":1048576,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":true,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"maxVideos":4,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Muse Wonder is a frontier reasoning model from Meta for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with a 1M-token context window. The model plans, delegates to sub-agents, calls tools in parallel, and recovers from errors so long-horizon work can run to completion without step-by-step direction.","name":"Muse Wonder","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1048576,"created":1792022400,"id":"muse-spark-open","model_spec":{"pricing":{"input":{"usd":1.5625,"diem":1.5625},"cache_input":{"usd":0.1875,"diem":0.1875},"output":{"usd":5.3125,"diem":5.3125}},"model_sets":["venice_recommendations"],"availableContextTokens":1048576,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh"],"defaultReasoningEffort":"xhigh","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Muse Spark Open is an open-weight reasoning model from Meta for coding and agentic workflows. It supports tool calling and native image understanding in a single checkpoint, using a sparse Mixture-of-Experts architecture with 816B total / 42B active parameters and a 1M-token context window.","name":"Muse Spark Open","modelSource":"https://huggingface.co/meta-models/Muse-Spark-Open-816B-A42B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1765584000,"id":"openai-gpt-52","model_spec":{"pricing":{"input":{"usd":1.75,"diem":1.75},"cache_input":{"usd":0.175,"diem":0.175},"output":{"usd":14,"diem":14}},"availableContextTokens":256000,"maxCompletionTokens":65536,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.2 is a frontier-grade model in the GPT-5 series, offering stronger agentic and long context performance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly to simple queries while spending more depth on complex tasks.","name":"GPT-5.2","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.2","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":400000,"created":1771891200,"id":"openai-gpt-53-codex","model_spec":{"pricing":{"input":{"usd":1.75,"diem":1.75},"cache_input":{"usd":0.175,"diem":0.175},"output":{"usd":14,"diem":14}},"availableContextTokens":400000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.3 Codex, the successor to GPT-5.2 Codex, is OpenAI's specialized coding model, optimized for advanced software development, code generation, and technical problem-solving. It supports a longer context window and longer outputs than GPT-5.2 Codex.","name":"GPT-5.3 Codex","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.3-codex","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1772668800,"id":"openai-gpt-54","model_spec":{"pricing":{"input":{"usd":2.5,"diem":2.5},"cache_input":{"usd":0.25,"diem":0.25},"output":{"usd":15,"diem":15},"extended":{"context_token_threshold":272000,"input":{"usd":5,"diem":5},"output":{"usd":22.5,"diem":22.5},"cache_input":{"usd":0.5,"diem":0.5}}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.4, the successor to GPT-5.2, is a frontier model in the GPT-5 series with a 1M+ context window, offering improved agentic and long context performance. It uses adaptive reasoning to dynamically allocate computation across tasks.","name":"GPT-5.4","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.4","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1772668800,"id":"openai-gpt-54-pro","model_spec":{"pricing":{"input":{"usd":30,"diem":30},"output":{"usd":180,"diem":180},"extended":{"context_token_threshold":272000,"input":{"usd":60,"diem":60},"output":{"usd":270,"diem":270}}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","medium","high","xhigh"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.4 Pro builds on GPT-5.4's unified architecture with enhanced reasoning for complex, high-stakes tasks. It provides a 1M+ token context window (922K input, 128K output) and supports text and image inputs.","name":"GPT-5.4 Pro","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.4-pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":400000,"created":1774569600,"id":"openai-gpt-54-mini","model_spec":{"pricing":{"input":{"usd":0.75,"diem":0.75},"cache_input":{"usd":0.075,"diem":0.075},"output":{"usd":4.5,"diem":4.5}},"availableContextTokens":400000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.4 Mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong performance across reasoning, coding, and tool use.","name":"GPT-5.4 Mini","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.4-mini","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1776902400,"id":"openai-gpt-55","model_spec":{"pricing":{"input":{"usd":5,"diem":5},"cache_input":{"usd":0.5,"diem":0.5},"output":{"usd":30,"diem":30},"extended":{"context_token_threshold":272000,"input":{"usd":10,"diem":10},"output":{"usd":45,"diem":45},"cache_input":{"usd":1,"diem":1}}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.5, the successor to GPT-5.4, is a frontier model in the GPT-5 series with a 1M+ context window, offering improved agentic and long context performance. It uses adaptive reasoning to dynamically allocate computation across tasks.","name":"GPT-5.5","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.5","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1776988800,"id":"openai-gpt-55-pro","model_spec":{"pricing":{"input":{"usd":30,"diem":30},"output":{"usd":180,"diem":180},"extended":{"context_token_threshold":272000,"input":{"usd":60,"diem":60},"output":{"usd":270,"diem":270}}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["medium","high","xhigh"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.5 Pro, the successor to GPT-5.4 Pro, builds on GPT-5.5's unified architecture with enhanced reasoning for complex, high-stakes tasks. It provides a 1M+ token context window (922K input, 128K output) and supports text and image inputs.","name":"GPT-5.5 Pro","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.5-pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1783555200,"id":"openai-gpt-56-luna","model_spec":{"pricing":{"input":{"usd":0.2,"diem":0.2},"cache_input":{"usd":0.02,"diem":0.02},"cache_write":{"usd":0.25,"diem":0.25},"output":{"usd":1.2,"diem":1.2},"extended":{"context_token_threshold":272000,"input":{"usd":0.4,"diem":0.4},"output":{"usd":1.8,"diem":1.8},"cache_input":{"usd":0.04,"diem":0.04},"cache_write":{"usd":0.5,"diem":0.5}}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for its price tier.","name":"GPT-5.6 Luna","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.6-luna","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1783555200,"id":"openai-gpt-56-luna-pro","model_spec":{"pricing":{"input":{"usd":0.2,"diem":0.2},"cache_input":{"usd":0.02,"diem":0.02},"cache_write":{"usd":0.25,"diem":0.25},"output":{"usd":1.2,"diem":1.2},"extended":{"context_token_threshold":272000,"input":{"usd":0.4,"diem":0.4},"output":{"usd":1.8,"diem":1.8},"cache_input":{"usd":0.04,"diem":0.04},"cache_write":{"usd":0.5,"diem":0.5}}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks.","name":"GPT-5.6 Luna Pro","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.6-luna","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1783555200,"id":"openai-gpt-56-terra","model_spec":{"pricing":{"input":{"usd":2,"diem":2},"cache_input":{"usd":0.2,"diem":0.2},"cache_write":{"usd":2.5,"diem":2.5},"output":{"usd":12,"diem":12},"extended":{"context_token_threshold":272000,"input":{"usd":4,"diem":4},"output":{"usd":18,"diem":18},"cache_input":{"usd":0.4,"diem":0.4},"cache_write":{"usd":5,"diem":5}}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic tasks where capability and cost need to be balanced.","name":"GPT-5.6 Terra","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.6-terra","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1783555200,"id":"openai-gpt-56-terra-pro","model_spec":{"pricing":{"input":{"usd":2,"diem":2},"cache_input":{"usd":0.2,"diem":0.2},"cache_write":{"usd":2.5,"diem":2.5},"output":{"usd":12,"diem":12},"extended":{"context_token_threshold":272000,"input":{"usd":4,"diem":4},"output":{"usd":18,"diem":18},"cache_input":{"usd":0.4,"diem":0.4},"cache_write":{"usd":5,"diem":5}}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with reasoning.mode set to pro for higher-quality responses on complex tasks.","name":"GPT-5.6 Terra Pro","modelSource":"https://developers.openai.com/api/docs/models/gpt-5.6-terra","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1783555200,"id":"openai-gpt-56-sol","model_spec":{"pricing":{"input":{"usd":4,"diem":4},"cache_input":{"usd":0.4,"diem":0.4},"cache_write":{"usd":5,"diem":5},"output":{"usd":20,"diem":20},"extended":{"context_token_threshold":272000,"input":{"usd":8,"diem":8},"output":{"usd":30,"diem":30},"cache_input":{"usd":0.8,"diem":0.8},"cache_write":{"usd":10,"diem":10}}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tasks and long-horizon problem solving.","name":"GPT-5.6 Sol","modelSource":"https://openrouter.ai/openai/gpt-5.6-sol","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1783555200,"id":"openai-gpt-56-sol-pro","model_spec":{"pricing":{"input":{"usd":4,"diem":4},"cache_input":{"usd":0.4,"diem":0.4},"cache_write":{"usd":5,"diem":5},"output":{"usd":20,"diem":20},"extended":{"context_token_threshold":272000,"input":{"usd":8,"diem":8},"output":{"usd":30,"diem":30},"cache_input":{"usd":0.8,"diem":0.8},"cache_write":{"usd":10,"diem":10}}},"availableContextTokens":1000000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh","max"],"defaultReasoningEffort":"medium","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with reasoning.mode set to pro for higher-quality responses on complex tasks.","name":"GPT-5.6 Sol Pro","modelSource":"https://openrouter.ai/openai/gpt-5.6-sol-pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1788566400,"id":"openai-gpt-6-astra","model_spec":{"pricing":{"input":{"usd":10,"diem":10},"cache_input":{"usd":1,"diem":1},"cache_write":{"usd":12.5,"diem":12.5},"output":{"usd":50,"diem":50},"extended":{"context_token_threshold":272000,"input":{"usd":20,"diem":20},"output":{"usd":75,"diem":75},"cache_input":{"usd":2,"diem":2},"cache_write":{"usd":25,"diem":25}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6 Astra is OpenAI's most capable model, built for the hardest end-to-end work. It is suited for complex reasoning, coding, computer use, research, and document creation, with a 1.05M token context window (922K input, 128K output) and support for text and image inputs.","name":"GPT-6 Astra","modelSource":"https://developers.openai.com/api/docs/models/gpt-6-astra","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1788566400,"id":"openai-gpt-6-astra-pro","model_spec":{"pricing":{"input":{"usd":10,"diem":10},"cache_input":{"usd":1,"diem":1},"cache_write":{"usd":12.5,"diem":12.5},"output":{"usd":50,"diem":50},"extended":{"context_token_threshold":272000,"input":{"usd":20,"diem":20},"output":{"usd":75,"diem":75},"cache_input":{"usd":2,"diem":2},"cache_write":{"usd":25,"diem":25}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra.","name":"GPT-6 Astra Pro","modelSource":"https://developers.openai.com/api/docs/models/gpt-6-astra","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1790035200,"id":"openai-gpt-6-luna","model_spec":{"pricing":{"input":{"usd":0.1,"diem":0.1},"cache_input":{"usd":0.01,"diem":0.01},"cache_write":{"usd":0.125,"diem":0.125},"output":{"usd":0.5,"diem":0.5},"extended":{"context_token_threshold":272000,"input":{"usd":0.2,"diem":0.2},"output":{"usd":0.75,"diem":0.75},"cache_input":{"usd":0.02,"diem":0.02},"cache_write":{"usd":0.25,"diem":0.25}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6 Luna is OpenAI's most efficient GPT-6 model for focused, high-volume tasks. It is suited for chat, classification, and lightweight agentic workflows, with a 1.05M token context window (922K input, 128K output), text and image inputs, and capable reasoning for its price tier.","name":"GPT-6 Luna","modelSource":"https://developers.openai.com/api/docs/models/gpt-6-luna","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1790035200,"id":"openai-gpt-6-sol","model_spec":{"pricing":{"input":{"usd":2,"diem":2},"cache_input":{"usd":0.2,"diem":0.2},"cache_write":{"usd":2.5,"diem":2.5},"output":{"usd":10,"diem":10},"extended":{"context_token_threshold":272000,"input":{"usd":4,"diem":4},"output":{"usd":15,"diem":15},"cache_input":{"usd":0.4,"diem":0.4},"cache_write":{"usd":5,"diem":5}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6 Sol is built for complex coding and agentic workflows. It is OpenAI's GPT-6 coding and agent model, with a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max.","name":"GPT-6 Sol","modelSource":"https://developers.openai.com/api/docs/models/gpt-6-sol","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1790640000,"id":"openai-gpt-61-sol","model_spec":{"pricing":{"input":{"usd":2,"diem":2},"cache_input":{"usd":0.1,"diem":0.1},"cache_write":{"usd":2.5,"diem":2.5},"output":{"usd":10,"diem":10},"extended":{"context_token_threshold":272000,"input":{"usd":4,"diem":4},"output":{"usd":15,"diem":15},"cache_input":{"usd":0.2,"diem":0.2},"cache_write":{"usd":5,"diem":5}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6.1 Sol delivers near-Astra performance at a lower cost for complex coding, computer use, and professional work. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.","name":"GPT-6.1 Sol","modelSource":"https://developers.openai.com/api/docs/models/gpt-6.1-sol","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1791417600,"id":"openai-gpt-61-sol-ultrafast","model_spec":{"pricing":{"input":{"usd":12,"diem":12},"cache_input":{"usd":0.6,"diem":0.6},"cache_write":{"usd":15,"diem":15},"output":{"usd":60,"diem":60},"extended":{"context_token_threshold":272000,"input":{"usd":24,"diem":24},"output":{"usd":90,"diem":90},"cache_input":{"usd":1.2,"diem":1.2},"cache_write":{"usd":30,"diem":30}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6.1 Sol Ultrafast is the same model served in OpenAI's Ultrafast mode, up to 8x faster. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from low through max.","name":"GPT-6.1 Sol Ultrafast","modelSource":"https://developers.openai.com/api/docs/models/gpt-6.1-sol","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1792972800,"id":"openai-gpt-61-terra","model_spec":{"pricing":{"input":{"usd":1,"diem":1},"cache_input":{"usd":0.05,"diem":0.05},"cache_write":{"usd":1.25,"diem":1.25},"output":{"usd":5,"diem":5},"extended":{"context_token_threshold":272000,"input":{"usd":2,"diem":2},"output":{"usd":7.5,"diem":7.5},"cache_input":{"usd":0.1,"diem":0.1},"cache_write":{"usd":2.5,"diem":2.5}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6.1 Terra is a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. It has a 1.05M token context window (922K input, 128K output), support for text and image inputs, and reasoning effort from none through max.","name":"GPT-6.1 Terra","modelSource":"https://developers.openai.com/api/docs/models/gpt-6.1-terra","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1794873600,"id":"openai-gpt-62-astra","model_spec":{"pricing":{"input":{"usd":8,"diem":8},"cache_input":{"usd":0.4,"diem":0.4},"cache_write":{"usd":10,"diem":10},"output":{"usd":40,"diem":40},"extended":{"context_token_threshold":272000,"input":{"usd":16,"diem":16},"output":{"usd":60,"diem":60},"cache_input":{"usd":0.8,"diem":0.8},"cache_write":{"usd":20,"diem":20}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6.2 Astra is the flagship model in OpenAI's GPT-6.2 series, built for the hardest projects. It is suited for real-world engineering, professional work, and scientific research, with stronger visual reasoning for websites, slideshows, and 3D designs. It has a 1.05M token context window (922K input, 128K output) and support for text and image inputs.","name":"GPT-6.2 Astra","modelSource":"https://developers.openai.com/api/docs/models/gpt-6.2-astra","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1794873600,"id":"openai-gpt-62-astra-pro","model_spec":{"pricing":{"input":{"usd":8,"diem":8},"cache_input":{"usd":0.4,"diem":0.4},"cache_write":{"usd":10,"diem":10},"output":{"usd":40,"diem":40},"extended":{"context_token_threshold":272000,"input":{"usd":16,"diem":16},"output":{"usd":60,"diem":60},"cache_input":{"usd":0.8,"diem":0.8},"cache_write":{"usd":20,"diem":20}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6.2 Astra with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Astra.","name":"GPT-6.2 Astra Pro","modelSource":"https://developers.openai.com/api/docs/models/gpt-6.2-astra","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1794873600,"id":"openai-gpt-62-sol","model_spec":{"pricing":{"input":{"usd":2,"diem":2},"cache_input":{"usd":0.1,"diem":0.1},"cache_write":{"usd":2.5,"diem":2.5},"output":{"usd":10,"diem":10},"extended":{"context_token_threshold":272000,"input":{"usd":4,"diem":4},"output":{"usd":15,"diem":15},"cache_input":{"usd":0.2,"diem":0.2},"cache_write":{"usd":5,"diem":5}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6.2 Sol is an upgrade to GPT-6.1 Sol, positioned below GPT-6.2 Astra. It is an efficient, versatile model for everyday work, suited for multistep agentic workflows and clear, natural writing across technical and non-technical tasks. It has a 1.05M token context window (922K input, 128K output) and support for text and image inputs.","name":"GPT-6.2 Sol","modelSource":"https://developers.openai.com/api/docs/models/gpt-6.2-sol","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1050000,"created":1794873600,"id":"openai-gpt-62-sol-pro","model_spec":{"pricing":{"input":{"usd":2,"diem":2},"cache_input":{"usd":0.1,"diem":0.1},"cache_write":{"usd":2.5,"diem":2.5},"output":{"usd":10,"diem":10},"extended":{"context_token_threshold":272000,"input":{"usd":4,"diem":4},"output":{"usd":15,"diem":15},"cache_input":{"usd":0.2,"diem":0.2},"cache_write":{"usd":5,"diem":5}}},"availableContextTokens":1050000,"maxCompletionTokens":128000,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high","xhigh","max"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT-6.2 Sol with pro reasoning mode for difficult tasks that benefit from more model work. Supports text and image inputs with a 1.05M token context window. Pro mode can use more tokens and take longer than standard Sol.","name":"GPT-6.2 Sol Pro","modelSource":"https://developers.openai.com/api/docs/models/gpt-6.2-sol","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1772236800,"id":"openai-gpt-4o-2024-11-20","model_spec":{"pricing":{"input":{"usd":2.5,"diem":2.5},"cache_input":{"usd":1.25,"diem":1.25},"output":{"usd":10,"diem":10}},"availableContextTokens":128000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":true,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"OpenAI's multimodal model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.","name":"GPT-4o","modelSource":"https://developers.openai.com/api/docs/models/gpt-4o","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1772236800,"id":"openai-gpt-4o-mini-2024-07-18","model_spec":{"pricing":{"input":{"usd":0.15,"diem":0.15},"cache_input":{"usd":0.075,"diem":0.075},"output":{"usd":0.6,"diem":0.6}},"availableContextTokens":128000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":true,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"OpenAI's cost-efficient small model that delivers GPT-4 level intelligence at a fraction of the cost. Ideal for high-volume applications requiring strong reasoning. Version: 2024-07-18.","name":"GPT-4o Mini","modelSource":"https://developers.openai.com/api/docs/models/gpt-4o-mini","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":524288,"created":1781222400,"id":"minimax-m3-preview","model_spec":{"pricing":{"input":{"usd":0.3,"diem":0.3},"cache_input":{"usd":0.06,"diem":0.06},"output":{"usd":1.2,"diem":1.2}},"availableContextTokens":524288,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"MiniMax-M3 preview is a 1.4T-parameter frontier model from MiniMax for coding, agentic workflows, and complex reasoning, served at fp8 with a 512K context window.","name":"MiniMax M3 Preview","modelSource":"https://huggingface.co/MiniMaxAI/MiniMax-M3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1792281600,"id":"minimax-m3-1-flash","model_spec":{"pricing":{"input":{"usd":0.1875,"diem":0.1875},"cache_input":{"usd":0.01875,"diem":0.01875},"output":{"usd":0.75,"diem":0.75}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"MiniMax M3.1 Flash is a frontier model for coding, agentic workflows, and complex reasoning, with a 1M-token context window, text, image, and video input, and tunable thinking depth from low to max (max by default).","name":"MiniMax M3.1 Flash","modelSource":"https://www.minimax.io/models/text/m3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":198000,"created":1770854400,"id":"minimax-m25","model_spec":{"pricing":{"input":{"usd":0.27,"diem":0.27},"cache_input":{"usd":0.03,"diem":0.03},"output":{"usd":0.95,"diem":0.95}},"availableContextTokens":198000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"MiniMax-M2.5 is a large language model optimized for coding, agentic workflows, and modern application development with enhanced reasoning capabilities.","name":"MiniMax M2.5","modelSource":"https://huggingface.co/MiniMaxAI/MiniMax-M2.5","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":198000,"created":1773792000,"id":"minimax-m27","model_spec":{"pricing":{"input":{"usd":0.375,"diem":0.375},"cache_input":{"usd":0.06875,"diem":0.06875},"output":{"usd":1.5,"diem":1.5}},"availableContextTokens":198000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":false,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"MiniMax-M2.7 is a large language model designed for autonomous, real-world productivity with advanced agentic capabilities through multi-agent collaboration.","name":"MiniMax M2.7","modelSource":"https://huggingface.co/MiniMaxAI/MiniMax-M2.7","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1769472000,"id":"nvidia-nemotron-3-nano-30b-a3b","model_spec":{"pricing":{"input":{"usd":0.075,"diem":0.075},"output":{"usd":0.3,"diem":0.3}},"availableContextTokens":128000,"maxCompletionTokens":16384,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.","name":"NVIDIA Nemotron 3 Nano 30B","modelSource":"https://huggingface.co/nvidia/Nemotron-3-Nano-30B-A3B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1775692800,"id":"nvidia-nemotron-3-super-120b-a12b","model_spec":{"beta":true,"pricing":{"input":{"usd":0.125,"diem":0.125},"output":{"usd":0.625,"diem":0.625}},"availableContextTokens":256000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"bf16","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.","name":"NVIDIA Nemotron 3 Super 120B","modelSource":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":262144,"created":1792108800,"id":"nvidia-nemotron-3-5-super-vl-120b-a12b","model_spec":{"pricing":{"input":{"usd":0.2,"diem":0.2},"cache_input":{"usd":0.04,"diem":0.04},"output":{"usd":0.5,"diem":0.5}},"availableContextTokens":262144,"maxCompletionTokens":102400,"capabilities":{"optimizedForCode":true,"quantization":"fp4","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"maxVideos":1,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":true,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"NVIDIA Nemotron 3.5 Super VL is an open multimodal vision-language model for specialized agents. Its 120B-parameter Mixture-of-Experts design (12B active) understands text, images, documents, GUIs, and video, combining reasoning, instruction following, and tool use for long-running agentic workflows.","name":"NVIDIA Nemotron 3.5 Super VL 120B","modelSource":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-NVFP4","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":256000,"created":1780531200,"id":"nvidia-nemotron-3-ultra-550b-a55b","model_spec":{"pricing":{"input":{"usd":0.625,"diem":0.625},"cache_input":{"usd":0.1875,"diem":0.1875},"output":{"usd":3.125,"diem":3.125}},"availableContextTokens":256000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"NVIDIA Nemotron 3 Ultra is built for frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads.","name":"NVIDIA Nemotron 3 Ultra","modelSource":"https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":64000,"created":1779580800,"id":"e2ee-gemma-4-26b-a4b-uncensored-p","model_spec":{"pricing":{"input":{"usd":0.19,"diem":0.19},"output":{"usd":0.88,"diem":0.88}},"availableContextTokens":64000,"maxCompletionTokens":4096,"capabilities":{"optimizedForCode":false,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":false,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Gemma 4 26B A4B Uncensored running in a Trusted Execution Environment (TEE). An uncensored variant of Google's Gemma 4 MoE model with 25.2B total / 3.8B active parameters, with hardware attestation evidence available for independent verification.","name":"Gemma 4 26B A4B Uncensored","modelSource":"https://huggingface.co/coder3101/gemma-4-26B-A4B-it-heretic","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":524288,"created":1781568000,"id":"e2ee-glm-5-2-p","model_spec":{"pricing":{"input":{"usd":1.75,"diem":1.75},"cache_input":{"usd":0.3,"diem":0.3},"output":{"usd":5.75,"diem":5.75}},"availableContextTokens":524288,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM 5.2 running in a Trusted Execution Environment (TEE). A Z.AI model for long-horizon tasks with enhanced reasoning and project-level engineering context, with hardware attestation evidence available for independent verification.","name":"GLM 5.2","modelSource":"https://huggingface.co/zai-org/GLM-5.2","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1788652800,"id":"e2ee-glm-5-3-p","model_spec":{"pricing":{"input":{"usd":1.75,"diem":1.75},"cache_input":{"usd":0.325,"diem":0.325},"output":{"usd":5.5,"diem":5.5}},"availableContextTokens":1000000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM 5.3 running in a Trusted Execution Environment (TEE). Z.ai's flagship model with 1M context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","name":"GLM 5.3","modelSource":"https://huggingface.co/zai-org/GLM-5.3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1773792000,"id":"e2ee-gpt-oss-120b-p","model_spec":{"pricing":{"input":{"usd":0.13,"diem":0.13},"output":{"usd":0.65,"diem":0.65}},"availableContextTokens":128000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":false,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["low","medium","high"],"defaultReasoningEffort":"low","supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"GPT OSS 120B running in a Trusted Execution Environment (TEE). OpenAI's open-weight 117B-parameter MoE model with configurable reasoning depth and native tool use, with hardware attestation evidence available for independent verification.","name":"GPT OSS 120B","modelSource":"https://huggingface.co/openai/gpt-oss-120b","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1788825600,"id":"e2ee-kimi-k3-p","model_spec":{"pricing":{"input":{"usd":3.75,"diem":3.75},"cache_input":{"usd":0.375,"diem":0.375},"output":{"usd":18.75,"diem":18.75}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","max"],"defaultReasoningEffort":"max","supportsResponseSchema":true,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows.","name":"Kimi K3","modelSource":"https://huggingface.co/moonshotai/Kimi-K3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1794873600,"id":"e2ee-kimi-k3-1-pro-p","model_spec":{"pricing":{"input":{"usd":2.5,"diem":2.5},"cache_input":{"usd":0.25,"diem":0.25},"output":{"usd":12.5,"diem":12.5}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":true,"maxImages":10,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","max"],"defaultReasoningEffort":"max","supportsResponseSchema":true,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Kimi K3.1 Pro is Moonshot AI's flagship multimodal reasoning model and the post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, agentic workflows, financial research, and 3D modeling through CAD code.","name":"Kimi K3.1 Pro","modelSource":"https://huggingface.co/moonshotai/Kimi-K3.1-Pro","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":32000,"created":1773792000,"id":"e2ee-qwen-2-5-7b-p","model_spec":{"pricing":{"input":{"usd":0.05,"diem":0.05},"output":{"usd":0.13,"diem":0.13}},"availableContextTokens":32000,"maxCompletionTokens":4096,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":false,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 2.5 7B Instruct running in a Trusted Execution Environment (TEE). A compact model with strong coding, math, and multilingual capabilities supporting 29+ languages, with hardware attestation evidence available for independent verification.","name":"Qwen 2.5 7B","modelSource":"https://huggingface.co/Qwen/Qwen2.5-7B-Instruct","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":128000,"created":1773792000,"id":"e2ee-qwen3-vl-30b-a3b-p","model_spec":{"pricing":{"input":{"usd":0.25,"diem":0.25},"output":{"usd":0.9,"diem":0.9}},"availableContextTokens":128000,"maxCompletionTokens":4096,"capabilities":{"optimizedForCode":false,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":false,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen3 VL 30B A3B running in a Trusted Execution Environment (TEE). A multimodal model unifying text generation with visual understanding for images, with hardware attestation evidence available for independent verification.","name":"Qwen3 VL 30B A3B","modelSource":"https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":32000,"created":1779235200,"id":"e2ee-qwen3-6-35b-a3b","model_spec":{"pricing":{"input":{"usd":0.182,"diem":0.182},"cache_input":{"usd":0.06,"diem":0.06},"output":{"usd":1.18,"diem":1.18}},"availableContextTokens":32000,"maxCompletionTokens":4096,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 3.6 35B A3B FP8 running in a Trusted Execution Environment (TEE). A fast mixture-of-experts model with ~3B active parameters per token. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","name":"Qwen 3.6 35B A3B FP8","modelSource":"https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1783382400,"id":"e2ee-deepseek-v4-flash","model_spec":{"pricing":{"input":{"usd":0.182,"diem":0.182},"cache_input":{"usd":0.038,"diem":0.038},"output":{"usd":0.373,"diem":0.373}},"availableContextTokens":1000000,"maxCompletionTokens":8192,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4 Flash running in a Trusted Execution Environment (TEE). Hardware attestation evidence is available for independent verification of enclave identity and configuration.","name":"DeepSeek V4 Flash","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1793836800,"id":"e2ee-deepseek-v4-1-flash-1017-abliterated","model_spec":{"pricing":{"input":{"usd":0.375,"diem":0.375},"cache_input":{"usd":0.0075,"diem":0.0075},"output":{"usd":1.5,"diem":1.5}},"availableContextTokens":1000000,"maxCompletionTokens":131072,"capabilities":{"optimizedForCode":true,"quantization":"fp8","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"DeepSeek V4.1 Flash 1017 Abliterated running in a Trusted Execution Environment (TEE). A text-only reasoning and coding model with refusal behavior removed and a 1M-token context window. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","name":"DeepSeek V4.1 Flash 1017 Abliterated","modelSource":"https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1000000,"created":1788652800,"id":"e2ee-glm-5-3-flash","model_spec":{"pricing":{"input":{"usd":0.16,"diem":0.16},"cache_input":{"usd":0.038,"diem":0.038},"output":{"usd":0.54,"diem":0.54}},"availableContextTokens":1000000,"maxCompletionTokens":32768,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"GLM 5.3 Flash running in a Trusted Execution Environment (TEE). A fast, low-cost multimodal model with 1M context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","name":"GLM 5.3 Flash","modelSource":"https://huggingface.co/zai-org/GLM-5.3-Flash","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":262144,"created":1788652800,"id":"e2ee-qwen3-8-27b","model_spec":{"pricing":{"input":{"usd":0.47,"diem":0.47},"cache_input":{"usd":0.047,"diem":0.047},"output":{"usd":3.53,"diem":3.53}},"availableContextTokens":262144,"maxCompletionTokens":8192,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Qwen 3.8 27B running in a Trusted Execution Environment (TEE). A multimodal model with 262K context supporting text and image input. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","name":"Qwen 3.8 27B","modelSource":"https://huggingface.co/Qwen/Qwen3.8-27B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":262144,"created":1788652800,"id":"e2ee-kimi-k2-6","model_spec":{"pricing":{"input":{"usd":0.87,"diem":0.87},"cache_input":{"usd":0.44,"diem":0.44},"output":{"usd":4.12,"diem":4.12}},"availableContextTokens":262144,"maxCompletionTokens":8192,"capabilities":{"optimizedForCode":true,"quantization":"not-available","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":false,"supportsResponseSchema":false,"supportsTeeAttestation":true,"supportsE2EE":true,"supportsVideoInput":false,"supportsVision":true,"supportsWebSearch":true,"supportsXSearch":false},"description":"Kimi K2.6 running in a Trusted Execution Environment (TEE). MoonshotAI's multimodal model with 262K context. Hardware attestation evidence is available for independent verification of enclave identity and configuration.","name":"Kimi K2.6","modelSource":"https://huggingface.co/moonshotai/Kimi-K2.6","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"context_length":1048576,"created":1787875200,"id":"hy4-preview","model_spec":{"pricing":{"input":{"usd":1.0425,"diem":1.0425},"cache_input":{"usd":0.0525,"diem":0.0525},"output":{"usd":3.12625,"diem":3.12625}},"availableContextTokens":1048576,"maxCompletionTokens":64000,"capabilities":{"optimizedForCode":true,"quantization":"fp4","supportsAudioInput":false,"supportsFunctionCalling":true,"supportsLogProbs":false,"supportsMultipleImages":false,"supportsReasoning":true,"supportsReasoningEffort":true,"reasoningEffortOptions":["none","low","high"],"defaultReasoningEffort":"high","supportsResponseSchema":true,"supportsTeeAttestation":false,"supportsE2EE":false,"supportsVideoInput":false,"supportsVision":false,"supportsWebSearch":true,"supportsXSearch":false},"description":"Hy4 Preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy team, with 49B parameters active per token and a 1M-token context window. It is post-trained for software engineering, office and data analysis, game development, and scientific research, with strong long-horizon reasoning, tool use, and agentic performance.","name":"Hy4 Preview","modelSource":"https://huggingface.co/tencent/Hy4-preview","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"text"},{"created":1743099022,"id":"venice-sd35","model_spec":{"pricing":{"generation":{"usd":0.01,"diem":0.01},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":1500,"steps":{"default":25,"max":30},"widthHeightDivisor":16},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Venice SD35 is Venice's deployment of Stable Diffusion 3.5 Large, Stability AI's open-weight text-to-image model. It favors artistic and painterly styles over strict photorealism and accepts prompts of up to 1,500 characters.","name":"Venice SD35","modelSource":"https://huggingface.co/stabilityai/stable-diffusion-3.5-large","offline":false,"privacy":"private","traits":["eliza-default"]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1794268800,"id":"seedream-v5-5","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.0255,"diem":0.0255},"1.5K":{"usd":0.034,"diem":0.034},"2K":{"usd":0.051,"diem":0.051}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","1.5K","2K"],"supportsTransparentBackground":true,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:3"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Seedream V5.5 is ByteDance Seed's Seedream 5.5, generating high-quality images at 1K, 1.5K, or 2K with improved realism and text rendering. It pairs with Seedream V5.5 Edit.","name":"Seedream V5.5","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1786406400,"id":"grok-imagine-image-2-0","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.07,"diem":0.07},"2K":{"usd":0.1,"diem":0.1}},"quality":{"1K":{"low":{"usd":0.05,"diem":0.05},"medium":{"usd":0.07,"diem":0.07}},"2K":{"low":{"usd":0.07,"diem":0.07},"medium":{"usd":0.1,"diem":0.1}}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations","featured"],"constraints":{"promptCharacterLimit":7500,"defaultResolution":"1K","resolutions":["1K","2K"],"defaultQuality":"medium","qualities":["low","medium"],"aspectRatios":["1:1","4:3","3:2","16:9","2:1","19.5:9","20:9","21:9","5:2","3:4","2:3","9:16","1:2","9:19.5","9:20"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Grok Imagine 2.0 is the second generation of xAI's Grok Imagine image model, generating images at 1K or 2K from text, with low and medium quality settings. It pairs with Grok Imagine 2.0 Edit for changing existing images.","name":"Grok Imagine 2.0","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1793577600,"id":"krea-3","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.07,"diem":0.07},"2K":{"usd":0.1,"diem":0.1},"4K":{"usd":0.15,"diem":0.15}},"quality":{"1K":{"medium":{"usd":0.04,"diem":0.04},"high":{"usd":0.07,"diem":0.07}},"2K":{"medium":{"usd":0.08,"diem":0.08},"high":{"usd":0.1,"diem":0.1}},"4K":{"medium":{"usd":0.13,"diem":0.13},"high":{"usd":0.15,"diem":0.15}}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["medium","high"],"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Krea 3 is the third generation of Krea's image model, rendering at up to 4K with built-in prompt expansion that fills in detail from short prompts. It offers medium and high quality settings and pairs with Krea 3 Edit for changing and combining images.","name":"Krea 3","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1782777600,"id":"krea-2-turbo","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.04,"diem":0.04},"2K":{"usd":0.06,"diem":0.06}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":5000,"defaultResolution":"1K","resolutions":["1K","2K"],"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"defaultAspectRatio":"1:1","steps":{"default":8,"max":8},"widthHeightDivisor":8},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Krea 2 Turbo is the speed-optimized, open-weight version of Krea's Krea 2 image model, generating high-fidelity images at 1K or 2K in seconds. It suits rapid ideation and iteration.","name":"Krea 2 Turbo","modelSource":"https://huggingface.co/krea/Krea-2-Turbo","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1764086377,"id":"flux-2-pro","model_spec":{"pricing":{"generation":{"usd":0.03,"diem":0.03},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":3000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Flux 2 Pro is the Pro tier of Black Forest Labs' FLUX.2 image family, built for high-quality, prompt-faithful generation at speed. It handles detailed prompts of up to 3,000 characters.","name":"Flux 2 Pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1764086377,"id":"flux-2-max","model_spec":{"pricing":{"generation":{"usd":0.09,"diem":0.09},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":3000,"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"auto","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Flux 2 Max is the top tier of Black Forest Labs' FLUX.2 image family, aimed at realism, precision and consistency. It pairs with Flux 2 Max Edit for editing with up to 6 input images.","name":"Flux 2 Max","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1790812800,"id":"flux-3-image","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.12,"diem":0.12},"2K":{"usd":0.29,"diem":0.29},"4K":{"usd":0.98,"diem":0.98}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations","featured"],"constraints":{"promptCharacterLimit":32000,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Flux 3 is Black Forest Labs' flagship image model, with native 2K and 4K output, precise layout control and strong text rendering. It accepts prompts of up to 32,000 characters and pairs with Flux 3 Edit for local edits and multi-reference composition.","name":"Flux 3","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1788825600,"id":"gpt-image-2-5-flare","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.07,"diem":0.07},"2K":{"usd":0.15,"diem":0.15},"4K":{"usd":0.23,"diem":0.23}},"quality":{"1K":{"high":{"usd":0.07,"diem":0.07},"low":{"usd":0.03,"diem":0.03},"medium":{"usd":0.04,"diem":0.04}},"2K":{"high":{"usd":0.15,"diem":0.15},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.05,"diem":0.05}},"4K":{"high":{"usd":0.23,"diem":0.23},"low":{"usd":0.05,"diem":0.05},"medium":{"usd":0.07,"diem":0.07}}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations","featured"],"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"],"supportsTransparentBackground":true,"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"GPT Image 2.5 Flare is the faster tier of OpenAI's GPT Image 2.5, built for quick, high-quality generation in creator and high-volume work. It renders at up to 4K and pairs with GPT Image 2.5 Flare Edit for scoped edits.","name":"GPT Image 2.5 Flare","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1788825600,"id":"gpt-image-2-5-sunburst","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.07,"diem":0.07},"2K":{"usd":0.15,"diem":0.15},"4K":{"usd":0.23,"diem":0.23}},"quality":{"1K":{"high":{"usd":0.07,"diem":0.07},"low":{"usd":0.03,"diem":0.03},"medium":{"usd":0.04,"diem":0.04}},"2K":{"high":{"usd":0.15,"diem":0.15},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.05,"diem":0.05}},"4K":{"high":{"usd":0.23,"diem":0.23},"low":{"usd":0.05,"diem":0.05},"medium":{"usd":0.07,"diem":0.07}}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"],"supportsTransparentBackground":true,"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"GPT Image 2.5 Sunburst is the premium tier of OpenAI's GPT Image 2.5, built for precise, production-ready campaign and product imagery. It renders at up to 4K and pairs with GPT Image 2.5 Sunburst Edit for tightly controlled revisions.","name":"GPT Image 2.5 Sunburst","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1793836800,"id":"gpt-image-2-6-sunburst","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.09,"diem":0.09},"2K":{"usd":0.15,"diem":0.15},"4K":{"usd":0.24,"diem":0.24}},"quality":{"1K":{"high":{"usd":0.09,"diem":0.09},"low":{"usd":0.05,"diem":0.05},"medium":{"usd":0.07,"diem":0.07}},"2K":{"high":{"usd":0.15,"diem":0.15},"low":{"usd":0.08,"diem":0.08},"medium":{"usd":0.13,"diem":0.13}},"4K":{"high":{"usd":0.24,"diem":0.24},"low":{"usd":0.12,"diem":0.12},"medium":{"usd":0.2,"diem":0.2}}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"],"supportsTransparentBackground":true,"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"GPT Image 2.6 Sunburst is the high-fidelity tier of OpenAI's GPT Image 2.6, made for campaign and product work where detail matters. It renders at up to 4K and pairs with GPT Image 2.6 Sunburst Edit.","name":"GPT Image 2.6 Sunburst","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1793836800,"id":"gpt-image-2-6-flare","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.09,"diem":0.09},"2K":{"usd":0.15,"diem":0.15},"4K":{"usd":0.24,"diem":0.24}},"quality":{"1K":{"high":{"usd":0.09,"diem":0.09},"low":{"usd":0.05,"diem":0.05},"medium":{"usd":0.07,"diem":0.07}},"2K":{"high":{"usd":0.15,"diem":0.15},"low":{"usd":0.08,"diem":0.08},"medium":{"usd":0.13,"diem":0.13}},"4K":{"high":{"usd":0.24,"diem":0.24},"low":{"usd":0.12,"diem":0.12},"medium":{"usd":0.2,"diem":0.2}}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"],"supportsTransparentBackground":true,"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"GPT Image 2.6 Flare is the faster tier of OpenAI's GPT Image 2.6, giving high-fidelity results for campaign and product work at lower latency. It renders at up to 4K and pairs with GPT Image 2.6 Flare Edit.","name":"GPT Image 2.6 Flare","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1776729600,"id":"gpt-image-2","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.27,"diem":0.27},"2K":{"usd":0.51,"diem":0.51},"4K":{"usd":0.84,"diem":0.84}},"quality":{"1K":{"high":{"usd":0.26,"diem":0.26},"low":{"usd":0.02,"diem":0.02},"medium":{"usd":0.07,"diem":0.07}},"2K":{"high":{"usd":0.5,"diem":0.5},"low":{"usd":0.03,"diem":0.03},"medium":{"usd":0.13,"diem":0.13}},"4K":{"high":{"usd":0.83,"diem":0.83},"low":{"usd":0.05,"diem":0.05},"medium":{"usd":0.21,"diem":0.21}}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"],"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"GPT Image 2 is OpenAI's image generation model, known for fine typography and high detail. It renders at up to 4K, offers low, medium and high quality settings, and pairs with GPT Image 2 Edit for edits that preserve composition.","name":"GPT Image 2","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1765986864,"id":"gpt-image-1-5","model_spec":{"pricing":{"generation":{"usd":0.26,"diem":0.26},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":5000,"supportsTransparentBackground":true,"aspectRatios":["1:1","3:2","2:3"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"GPT Image 1.5 is an earlier generation of OpenAI's GPT Image model, producing high-quality images in three aspect ratios. It pairs with GPT Image 1.5 Edit, which preserves composition, lighting and detail.","name":"GPT Image 1.5","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1772323200,"id":"hunyuan-image-v3","model_spec":{"pricing":{"generation":{"usd":0.09,"diem":0.09},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":3000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Hunyuan Image 3.0 is Tencent's open-weight text-to-image model, served here as the Instruct version, which reasons about a prompt before generating. It suits detailed, instruction-heavy prompts of up to 3,000 characters.","name":"Hunyuan Image 3.0","modelSource":"https://huggingface.co/tencent/HunyuanImage-3.0-Instruct","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1780444800,"id":"ideogram-v4","model_spec":{"pricing":{"generation":{"usd":0.06,"diem":0.06},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Ideogram V4 is Ideogram's image model, known for legible, accurate text inside images. It suits posters, logos and marketing graphics.","name":"Ideogram V4","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1790726400,"id":"ideogram-v4-5","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.26,"diem":0.26},"2K":{"usd":0.26,"diem":0.26}},"quality":{"1K":{"high":{"usd":0.26,"diem":0.26},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.07,"diem":0.07}},"2K":{"high":{"usd":0.26,"diem":0.26},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.07,"diem":0.07}}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K"],"defaultQuality":"high","qualities":["low","medium","high"],"aspectRatios":["1:1","3:2","16:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Ideogram V4.5 is Ideogram's typography-focused image model, rendering accurate text for posters, logos and designs at 1K or 2K. It offers low, medium and high quality settings and pairs with Ideogram V4.5 Edit.","name":"Ideogram V4.5","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1779408000,"id":"krea-v2-large","model_spec":{"pricing":{"generation":{"usd":0.07,"diem":0.07},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":5000,"aspectRatios":["1:1","3:2","16:9","2:3","9:16"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1,"maxStyleReferences":3,"supportsStyleReferenceStrength":true},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":true,"description":"Krea v2 Large is Krea's high-fidelity text-to-image model, tuned for refined aesthetics and lifelike detail. It's the larger, higher-quality sibling of Krea v2 Medium.","name":"Krea v2 Large","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1779408000,"id":"krea-v2-medium","model_spec":{"pricing":{"generation":{"usd":0.04,"diem":0.04},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":5000,"aspectRatios":["1:1","3:2","16:9","2:3","9:16"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1,"maxStyleReferences":3,"supportsStyleReferenceStrength":true},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":true,"description":"Krea v2 Medium is Krea's cost-effective text-to-image model, balancing speed and quality. It's the lighter sibling of Krea v2 Large.","name":"Krea v2 Medium","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1781654400,"id":"luma-uni-1","model_spec":{"pricing":{"generation":{"usd":0.05,"diem":0.05},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":6000,"aspectRatios":["1:1","3:2","16:9","9:16","2:3"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1,"maxStyleReferences":3,"supportsStyleReferenceStrength":false},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":true,"description":"Luma Uni-1 is Luma AI's image model, which grounds prompts in web knowledge for faithful, high-fidelity results. It pairs with Luma Uni-1 Edit for text-guided edits that keep the source structure.","name":"Luma Uni-1","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1781654400,"id":"luma-uni-1-max","model_spec":{"pricing":{"generation":{"usd":0.12,"diem":0.12},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":6000,"aspectRatios":["1:1","3:2","16:9","9:16","2:3"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1,"maxStyleReferences":3,"supportsStyleReferenceStrength":false},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":true,"description":"Luma Uni-1 Max runs Luma AI's Uni-1 at maximum fidelity, for hero-quality stills with web-grounded prompt adherence. It pairs with Luma Uni-1 Max Edit.","name":"Luma Uni-1 Max","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1794268800,"id":"minimax-h3-image","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.04,"diem":0.04},"2K":{"usd":0.04,"diem":0.04},"4K":{"usd":0.1,"diem":0.1}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":true,"supportsStyleReferences":false,"description":"MiniMax H3 Image is MiniMax's image model for text-to-image generation, rendering at 1K, 2K and 4K in aspect ratios from 21:9 to 9:21. It pairs with MiniMax H3 Image Edit for changing and combining images.","name":"MiniMax H3 Image","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1788393600,"id":"muse-image","model_spec":{"pricing":{"generation":{"usd":0.02,"diem":0.02},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Muse Image is Meta's image model, known for faithful instruction following, accurate text and fine detail. It pairs with Muse Image Edit, which changes only what you ask and can compose from several reference images.","name":"Muse Image","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1772064000,"id":"nano-banana-2","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.1,"diem":0.1},"2K":{"usd":0.14,"diem":0.14},"4K":{"usd":0.19,"diem":0.19}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":32768,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:1","8:1","4:5","3:4","2:3","9:16","1:4","1:8"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":true,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Nano Banana 2 is Google's Gemini-based image model, generating at up to 4K from prompts of up to 32,768 characters. It pairs with Nano Banana 2 Edit for fast, high-quality edits.","name":"Nano Banana 2","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1791244800,"id":"nano-banana-2-1","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.1,"diem":0.1},"2K":{"usd":0.14,"diem":0.14},"4K":{"usd":0.19,"diem":0.19}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":32768,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:1","8:1","4:5","3:4","2:3","9:16","1:4","1:8"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":true,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Nano Banana 2.1 is an update to Google's Gemini-based Nano Banana 2 image model, generating at up to 4K from prompts of up to 32,768 characters. It pairs with Nano Banana 2.1 Edit.","name":"Nano Banana 2.1","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1763653951,"id":"nano-banana-pro","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.18,"diem":0.18},"2K":{"usd":0.23,"diem":0.23},"4K":{"usd":0.35,"diem":0.35}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["featured"],"constraints":{"promptCharacterLimit":32768,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:1","8:1","4:5","3:4","2:3","9:16","1:4","1:8"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":true,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Nano Banana Pro is the Pro tier of Google's Gemini-based Nano Banana image models, generating at up to 4K from prompts of up to 32,768 characters. It pairs with Nano Banana Pro Edit for high-quality edits.","name":"Nano Banana Pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1782777600,"id":"nano-banana-2-lite","model_spec":{"pricing":{"generation":{"usd":0.06,"diem":0.06},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":10000,"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:1","8:1","4:5","3:4","2:3","9:16","1:4","1:8"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Nano Banana 2 Lite is the efficiency-focused tier of Google's Nano Banana 2 image models, built for fast, cost-effective generation. It pairs with Nano Banana 2 Lite Edit for quick multi-turn edits.","name":"Nano Banana 2 Lite","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1770854400,"id":"recraft-v4","model_spec":{"pricing":{"generation":{"usd":0.05,"diem":0.05},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Recraft V4 is Recraft's image model, known for high-quality output and precise text rendering. It suits design, branding and marketing work.","name":"Recraft V4","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1770854400,"id":"recraft-v4-pro","model_spec":{"pricing":{"generation":{"usd":0.29,"diem":0.29},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Recraft V4 Pro is the premium tier of Recraft V4, adding finer detail to its precise text rendering. It suits design, branding and product imagery where detail matters.","name":"Recraft V4 Pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1762383600,"id":"seedream-v4","model_spec":{"pricing":{"generation":{"usd":0.05,"diem":0.05},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Seedream V4.5 is ByteDance Seed's image model, served uncensored, with strong composition and detail. It pairs with Seedream V4.5 Edit for natural-language editing.","name":"Seedream V4.5","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1771804800,"id":"seedream-v5-lite","model_spec":{"pricing":{"generation":{"usd":0.05,"diem":0.05},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5","4:3"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Seedream V5 Lite is the fast tier of ByteDance Seed's Seedream 5.0 image models, giving high-quality images at lower latency. It pairs with Seedream V5 Lite Edit.","name":"Seedream V5 Lite","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1783468800,"id":"seedream-v5-pro","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.06,"diem":0.06},"2K":{"usd":0.11,"diem":0.11}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K"],"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":true,"supportsStyleReferences":false,"description":"Seedream V5 Pro is the flagship tier of ByteDance Seed's Seedream 5.0, generating high-quality images at 1K or 2K. It pairs with Seedream V5 Pro Edit.","name":"Seedream V5 Pro","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1772582400,"id":"qwen-image-2","model_spec":{"pricing":{"generation":{"usd":0.05,"diem":0.05},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Qwen Image 2 is Alibaba's Qwen Image 2.0 text-to-image model, with native 2K output and accurate typography. It pairs with Qwen Image 2 Edit for natural-language editing without masks.","name":"Qwen Image 2","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1772582400,"id":"qwen-image-2-pro","model_spec":{"pricing":{"generation":{"usd":0.1,"diem":0.1},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":10000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Qwen Image 2 Pro is the highest-fidelity tier of Alibaba's Qwen Image 2.0, built for professional typography and detail. It pairs with Qwen Image 2 Pro Edit.","name":"Qwen Image 2 Pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1775001600,"id":"wan-2-7-text-to-image","model_spec":{"pricing":{"generation":{"usd":0.0375,"diem":0.0375},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":3000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Wan 2.7 is Alibaba's Wan 2.7 model in text-to-image mode, combining strong prompt understanding with high image quality. It handles prompts of up to 3,000 characters.","name":"Wan 2.7","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1775001600,"id":"wan-2-7-pro-text-to-image","model_spec":{"pricing":{"generation":{"usd":0.09375,"diem":0.09375},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":3000,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Wan 2.7 Pro is the enhanced tier of Alibaba's Wan 2.7 for text-to-image generation, adding finer detail. It pairs with Wan 2.7 Pro Edit for editing with up to 6 input images.","name":"Wan 2.7 Pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1775692800,"id":"grok-imagine-image","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.03,"diem":0.03},"2K":{"usd":0.04,"diem":0.04}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":7500,"defaultResolution":"1K","resolutions":["1K","2K"],"aspectRatios":["1:1","4:3","3:2","16:9","2:1","19.5:9","20:9","3:4","2:3","9:16","1:2","9:19.5","9:20"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Grok Imagine is xAI's image model, generating photorealistic images from text at 1K or 2K with reliable quality and low latency. It pairs with Grok Imagine Edit for changing elements and styles.","name":"Grok Imagine","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1738704152,"id":"lustify-sdxl","model_spec":{"pricing":{"generation":{"usd":0.01,"diem":0.01},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":1500,"steps":{"default":20,"max":50},"widthHeightDivisor":8},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Lustify SDXL is a community fine-tune of Stable Diffusion XL, built for uncensored, adult-oriented photorealistic images. It accepts prompts of up to 1,500 characters.","name":"Lustify SDXL","modelSource":"https://civitai.com/models/573152/lustify-sdxl-nsfw-checkpoint","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1736635129,"id":"lustify-v7","model_spec":{"pricing":{"generation":{"usd":0.01,"diem":0.01},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":1500,"steps":{"default":20,"max":50},"widthHeightDivisor":8},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Lustify v7 is version 7 of the Lustify community SDXL checkpoint, built for uncensored, adult-oriented photorealistic images. It accepts prompts of up to 1,500 characters.","name":"Lustify v7","modelSource":"https://civitai.com/models/573152/lustify-sdxl-nsfw-checkpoint","offline":false,"privacy":"private","traits":["most_uncensored"],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1774828800,"id":"lustify-v8","model_spec":{"pricing":{"generation":{"usd":0.01,"diem":0.01},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":1500,"steps":{"default":30,"max":50},"widthHeightDivisor":8},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Lustify v8 is version 8 of the Lustify community SDXL checkpoint, built for uncensored, adult-oriented photorealistic images. It accepts prompts of up to 1,500 characters.","name":"Lustify v8","modelSource":"https://civitai.com/models/573152/lustify-sdxl-nsfw-checkpoint","offline":false,"privacy":"private","traits":["most_uncensored"],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1736635129,"id":"qwen-image","model_spec":{"pricing":{"generation":{"usd":0.03,"diem":0.03},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":2048,"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Qwen Image is Alibaba's open-weight text-to-image model, known for close prompt adherence and accurate text rendering, including Chinese. It accepts prompts of up to 2,048 characters.","name":"Qwen Image","modelSource":"https://huggingface.co/Qwen/Qwen-Image","offline":false,"privacy":"anonymized","traits":["highest_quality"]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1736635129,"id":"wai-Illustrious","model_spec":{"pricing":{"generation":{"usd":0.01,"diem":0.01},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":1500,"steps":{"default":25,"max":30},"widthHeightDivisor":16},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Anime (WAI) is WAI-Illustrious, a community anime checkpoint built on Illustrious XL, for anime illustration, including uncensored adult content. It accepts prompts of up to 1,500 characters.","name":"Anime (WAI)","modelSource":"https://civitai.com/models/827184?modelVersionId=1761560","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1764758779,"id":"z-image-turbo","model_spec":{"pricing":{"generation":{"usd":0.01,"diem":0.01},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":7500,"steps":{"default":8,"max":8},"widthHeightDivisor":8},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Z-Image Turbo is the distilled, fast version of Z-Image, an open-weight text-to-image model from Alibaba's Tongyi Lab. It produces high-quality images in a few steps, which makes it a good default for quick generation.","name":"Z-Image Turbo","modelSource":"https://huggingface.co/Tongyi-MAI/Z-Image-Turbo","offline":false,"privacy":"private","traits":["default","fastest"]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1769731200,"id":"chroma","model_spec":{"pricing":{"generation":{"usd":0.01,"diem":0.01},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations","featured"],"constraints":{"promptCharacterLimit":7500,"steps":{"default":10,"max":10},"widthHeightDivisor":8},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Chroma is an open-weight community text-to-image model based on FLUX.1 schnell, trained for uncensored, photorealistic generation. It accepts prompts of up to 7,500 characters.","name":"Chroma","modelSource":"https://huggingface.co/lodestones/Chroma1-HD","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1785888000,"id":"qwen-image-3","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.04,"diem":0.04},"2K":{"usd":0.04,"diem":0.04}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K"],"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":true,"supportsStyleReferences":false,"description":"Qwen Image 3 is the standard tier of Alibaba's Qwen Image 3.0, offering cost-efficient text-to-image generation at 1K or 2K with strong text rendering. It pairs with Qwen Image 3 Edit.","name":"Qwen Image 3","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1784160000,"id":"qwen-image-3-pro","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.05,"diem":0.05},"2K":{"usd":0.09,"diem":0.09}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"model_sets":["venice_recommendations"],"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K"],"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":true,"supportsStyleReferences":false,"description":"Qwen Image 3 Pro is the Pro tier of Alibaba's Qwen Image 3.0, built for close prompt adherence and strong text rendering at 1K or 2K. It pairs with Qwen Image 3 Pro Edit.","name":"Qwen Image 3 Pro","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1791504000,"id":"qwen-image-2-1-turbo","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.02,"diem":0.02},"2K":{"usd":0.02,"diem":0.02}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K"],"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":true,"supportsStyleReferences":false,"description":"Qwen Image 2.1 Turbo is the fast, cost-effective tier of Alibaba's open-weight Qwen-Image 2.1 series, balancing quality and speed at 1K or 2K. It pairs with Qwen Image 2.1 Turbo Edit.","name":"Qwen Image 2.1 Turbo","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1789862400,"id":"qwen-image-2-1-pro","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.05,"diem":0.05},"2K":{"usd":0.05,"diem":0.05}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":10000,"defaultResolution":"1K","resolutions":["1K","2K"],"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":true,"supportsStyleReferences":false,"description":"Qwen Image 2.1 Pro is the full-capacity Qwen-Image 2.1 model from Alibaba, compact and efficient while generating at 1K or 2K. It pairs with Qwen Image 2.1 Pro Edit, which takes up to 10 reference images.","name":"Qwen Image 2.1 Pro","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1794873600,"id":"kling-v4-text-to-image","model_spec":{"pricing":{"resolutions":{"2K":{"usd":0.08,"diem":0.08},"4K":{"usd":0.12,"diem":0.12}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":32768,"defaultResolution":"2K","resolutions":["2K","4K"],"aspectRatios":["1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"Text-to-image at 2K and 4K, in aspect ratios from 21:9 to 9:16.","name":"Kling Image 4.0","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1794873600,"id":"mai-image-2-7","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.05,"diem":0.05},"2K":{"usd":0.17,"diem":0.17}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":32000,"defaultResolution":"1K","resolutions":["1K","2K"],"supportsTransparentBackground":true,"aspectRatios":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"MAI Image 2.7 is Microsoft's text-to-image model. It renders at 1K or 2K in seven aspect ratios and supports transparent backgrounds.","name":"MAI Image 2.7","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1794873600,"id":"mai-image-2-7-flash","model_spec":{"pricing":{"resolutions":{"1K":{"usd":0.02,"diem":0.02},"2K":{"usd":0.05,"diem":0.05}},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"constraints":{"promptCharacterLimit":32000,"defaultResolution":"1K","resolutions":["1K","2K"],"supportsTransparentBackground":true,"aspectRatios":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"],"defaultAspectRatio":"1:1","steps":{"default":20,"max":50},"widthHeightDivisor":1},"supportsWebSearch":false,"supportsOptimizePromptThinking":false,"supportsStyleReferences":false,"description":"MAI Image 2.7 Flash is the faster, lower-cost variant of Microsoft's MAI Image 2.7. It renders at 1K or 2K in seven aspect ratios and supports transparent backgrounds.","name":"MAI Image 2.7 Flash","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"image"},{"created":1787788800,"id":"gemini-omni-flash-1-1-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["360p","720p","1080p","4k"],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic","high_resolution","ultra_high_resolution"],"description":"Gemini Omni Flash 1.1 is Google's video model; this text-to-video variant turns prompts into 4- to 10-second clips at up to 4K. Sibling variants cover image-to-video, reference-to-video and video editing.","name":"Gemini Omni Flash 1.1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"gemini-omni-flash-1-1-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["360p","720p","1080p","4k"],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic","high_resolution","ultra_high_resolution"],"description":"Gemini Omni Flash 1.1's image-to-video variant animates a starting image into a 4- to 10-second clip at up to 4K, using Google's Gemini Omni Flash 1.1 video model.","name":"Gemini Omni Flash 1.1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"gemini-omni-flash-1-1-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["360p","720p","1080p","4k"],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic","high_resolution","ultra_high_resolution"],"description":"Gemini Omni Flash 1.1 R2V combines several reference images of characters, objects or styles into one 4- to 10-second clip at up to 4K, using Google's Gemini Omni Flash 1.1.","name":"Gemini Omni Flash 1.1 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"gemini-omni-flash-1-1-video-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["360p","720p","1080p","4k"],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["audio","long_duration","cinematic","photorealistic","high_resolution","ultra_high_resolution"],"description":"Gemini Omni Flash 1.1 Edit rewrites an existing clip from a text instruction, keeping its length, at up to 4K. It's the video editing variant of Google's Gemini Omni Flash 1.1.","name":"Gemini Omni Flash 1.1 Edit","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1774915200,"id":"seedance-2-0-text-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 is ByteDance Seed's cinematic video model, with native audio and lip-sync in more than eight languages. This text-to-video variant generates 4- to 15-second clips at up to 4K.","name":"Seedance 2.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1774915200,"id":"seedance-2-0-image-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0's image-to-video variant turns a starting image into a 4- to 15-second clip at up to 4K, with optional synchronized dialogue and sound.","name":"Seedance 2.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1774915200,"id":"seedance-2-0-reference-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 R2V builds 4- to 15-second clips at up to 4K from reference images, videos and audio, and can also edit or extend existing footage. It's the reference-driven variant of ByteDance Seed's Seedance 2.0.","name":"Seedance 2.0 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775001600,"id":"seedance-2-0-fast-text-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":3500},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Fast is a faster version of ByteDance Seed's Seedance 2.0, generating 4- to 15-second clips at up to 720p from text, with optional native audio and lip-sync.","name":"Seedance 2.0 Fast","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775001600,"id":"seedance-2-0-fast-image-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":3500,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Fast's image-to-video variant turns a starting image into a 4- to 15-second clip at up to 720p, with optional synchronized audio.","name":"Seedance 2.0 Fast","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775001600,"id":"seedance-2-0-fast-reference-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":3500,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Fast R2V is the reference-driven variant of Seedance 2.0 Fast, generating, editing or extending 4- to 15-second clips at up to 720p from reference images, videos and audio.","name":"Seedance 2.0 Fast R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782345600,"id":"seedance-2-0-mini-text-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Mini is ByteDance Seed's cost-effective Seedance 2.0 model for high-volume video creation. This text-to-video variant generates 4- to 15-second clips at up to 720p, with optional native audio.","name":"Seedance 2.0 Mini","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782345600,"id":"seedance-2-0-mini-image-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Mini's image-to-video variant turns a starting image into a 4- to 15-second clip at up to 720p, with optional native audio, for high-volume work.","name":"Seedance 2.0 Mini","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782345600,"id":"seedance-2-0-mini-reference-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.0 Mini R2V is the reference-driven variant of Seedance 2.0 Mini, building 4- to 15-second clips at up to 720p from reference images, videos and audio.","name":"Seedance 2.0 Mini R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786060800,"id":"seedance-2-5-text-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 is the next generation of ByteDance Seed's cinematic video model, with native audio and stories of up to 30 seconds. This text-to-video variant generates 4- to 30-second clips at up to 4K.","name":"Seedance 2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786060800,"id":"seedance-2-5-image-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5's image-to-video variant turns a starting image into a 4- to 30-second clip at up to 4K, with optional native audio.","name":"Seedance 2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786060800,"id":"seedance-2-5-reference-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["4k","1080p","720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 R2V builds 4- to 30-second clips at up to 4K from up to 30 reference images plus reference videos and audio, and can edit or extend footage. It's the reference-driven variant of ByteDance Seed's Seedance 2.5.","name":"Seedance 2.5 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786060800,"id":"seedance-2-5-edit-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["4k","1080p","720p","480p"],"durations":["Auto"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 Edit changes a 4- to 30-second source video by swapping subjects, objects or styles, while keeping its original motion, camera and length. Reference images are optional, and output is up to 4K.","name":"Seedance 2.5 Edit","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1794614400,"id":"seedance-2-5-flash-text-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 Flash is a faster version of ByteDance Seed's Seedance 2.5, with native audio. This text-to-video variant generates 4- to 30-second clips at up to 720p.","name":"Seedance 2.5 Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1794614400,"id":"seedance-2-5-flash-image-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 Flash's image-to-video variant turns a starting image into a 4- to 30-second clip at up to 720p, with optional native audio.","name":"Seedance 2.5 Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1794614400,"id":"seedance-2-5-flash-reference-to-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["21:9","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","480p"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 Flash R2V builds 4- to 30-second clips at up to 720p from up to 10 reference images plus reference videos and audio, and can edit or extend footage. It's the reference-driven variant of Seedance 2.5 Flash.","name":"Seedance 2.5 Flash R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1794614400,"id":"seedance-2-5-flash-edit-video-basic","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["720p","480p"],"durations":["Auto"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":15000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Seedance 2.5 Flash Edit changes a 4- to 30-second source video by swapping subjects, objects or styles, while keeping its original motion, camera and length. Reference images are optional, and output is up to 720p.","name":"Seedance 2.5 Flash Edit","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785542400,"id":"wan-3-0-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 is Alibaba's video model, generating 2- to 30-second clips at up to 1080p from text, with optional native audio.","name":"Wan 3.0","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785542400,"id":"wan-3-0-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0's image-to-video variant animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 1080p, with optional native audio.","name":"Wan 3.0","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785542400,"id":"wan-3-0-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Reference generates 2- to 30-second clips at up to 1080p from reference images, videos and audio, keeping subjects consistent at the pixel level.","name":"Wan 3.0 Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787529600,"id":"wan-3-0-prime-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime is a high-speed version of Alibaba's Wan 3.0, generating 2- to 30-second clips at up to 1080p from text much faster, with optional native audio.","name":"Wan 3.0 Prime","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787529600,"id":"wan-3-0-prime-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime's image-to-video variant quickly animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 1080p.","name":"Wan 3.0 Prime","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787529600,"id":"wan-3-0-prime-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p","480p"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime Reference is the high-speed reference variant of Wan 3.0, building 2- to 30-second clips at up to 1080p from reference images, videos and audio with consistent subjects.","name":"Wan 3.0 Prime Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Pro is the highest-resolution tier of Alibaba's Wan 3.0, generating 2- to 30-second clips at up to 4K from text, with optional native audio.","name":"Wan 3.0 Pro","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Pro's image-to-video variant animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 4K.","name":"Wan 3.0 Pro","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-pro-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Pro Reference builds 2- to 30-second clips at up to 4K from reference images, videos and audio, keeping subjects consistent at the pixel level.","name":"Wan 3.0 Pro Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-prime-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime Pro combines the speed of Wan 3.0 Prime with the 4K output of Wan 3.0 Pro, generating 2- to 30-second clips from text, with optional native audio.","name":"Wan 3.0 Prime Pro","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-prime-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime Pro's image-to-video variant quickly animates a strict first frame, or a first-and-last-frame pair, into a 2- to 30-second clip at up to 4K.","name":"Wan 3.0 Prime Pro","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788825600,"id":"wan-3-0-prime-pro-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","2k","4k"],"durations":["2s","5s","10s","15s","20s","25s","30s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":20000,"reference_image_min_short_side_pixels":240},"model_sets":["uncensored","high_resolution","audio","long_duration"],"description":"Wan 3.0 Prime Pro Reference is the fastest 4K reference variant of Wan 3.0, building 2- to 30-second clips from reference images, videos and audio with consistent subjects.","name":"Wan 3.0 Prime Pro Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775088000,"id":"wan-2-7-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":false,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source","venice_recommendations","featured"],"description":"Wan 2.7 is Alibaba's video model, served uncensored, for high-fidelity text-to-video in 5-, 10- or 15-second clips at up to 1080p. It can follow an audio track you provide.","name":"Wan 2.7","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775088000,"id":"wan-2-7-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":false,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source","venice_recommendations"],"description":"Wan 2.7's image-to-video variant animates a starting image, or a first-and-last-frame pair, into an uncensored 5-, 10- or 15-second clip at up to 1080p. It can follow an audio track you provide.","name":"Wan 2.7","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775088000,"id":"wan-2-7-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":true,"video_input":false},"model_sets":["uncensored","high_resolution","audio","open_source","venice_recommendations"],"description":"Wan 2.7 Reference generates uncensored 5- or 10-second clips at up to 1080p from reference images, keeping characters and subjects consistent, with native audio.","name":"Wan 2.7 Reference","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775088000,"id":"wan-2-7-video-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["uncensored","high_resolution","open_source","venice_recommendations"],"description":"Wan 2.7 Edit changes an existing video from text instructions, with an optional reference image, at up to 1080p. It's the uncensored editing variant of Alibaba's Wan 2.7.","name":"Wan 2.7 Edit","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1778284800,"id":"wan-2-7-enhanced-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source","venice_recommendations"],"description":"Wan 2.7 Enhanced is a version of Alibaba's Wan 2.7 for uncensored video with native audio. This image-to-video variant animates a starting image into a 5-, 10- or 15-second clip at up to 1080p.","name":"Wan 2.7 Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1780444800,"id":"wan-2-7-enhanced-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source","venice_recommendations"],"description":"Wan 2.7 Enhanced is a version of Alibaba's Wan 2.7 for uncensored video with native audio. This text-to-video variant generates 5-, 10- or 15-second clips at up to 1080p.","name":"Wan 2.7 Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786665600,"id":"wan-2-2-enhanced-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","480p"],"durations":["5s","8s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","open_source"],"description":"Wan 2.2 Enhanced is a version of Alibaba's Wan 2.2 for uncensored image-to-video, animating a starting image into a 5- or 8-second clip at up to 720p.","name":"Wan 2.2 Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782086400,"id":"happyhorse-1-1-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4","21:9","9:21","5:4","4:5"],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution"],"description":"HappyHorse 1.1 is Alibaba's video model, with synchronized native audio and multilingual lip-sync. This text-to-video variant generates 3- to 15-second clips at up to 1080p.","name":"HappyHorse 1.1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782086400,"id":"happyhorse-1-1-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"reference_image_min_short_side_pixels":300},"model_sets":["high_resolution"],"description":"HappyHorse 1.1's image-to-video variant animates a starting image into a 3- to 15-second clip at up to 1080p, with native audio and multilingual lip-sync.","name":"HappyHorse 1.1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782086400,"id":"happyhorse-1-1-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4","21:9","9:21","5:4","4:5"],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"reference_image_min_short_side_pixels":400},"model_sets":["high_resolution"],"description":"HappyHorse 1.1 Reference builds 3- to 15-second clips at up to 1080p from reference images, keeping characters consistent, with native audio and multilingual lip-sync.","name":"HappyHorse 1.1 Reference","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776988800,"id":"happyhorse-1-0-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","featured"],"description":"HappyHorse 1.0 is Alibaba's video model with native audio. This text-to-video variant generates high-fidelity 3- to 15-second clips at up to 1080p.","name":"HappyHorse 1.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1777075200,"id":"happyhorse-1-0-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"reference_image_min_short_side_pixels":300},"model_sets":["high_resolution"],"description":"HappyHorse 1.0's image-to-video variant animates a starting image into a 3- to 15-second clip at up to 1080p, with native audio.","name":"HappyHorse 1.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1777248000,"id":"happyhorse-1-0-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["1080p","720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"reference_image_min_short_side_pixels":400},"model_sets":["high_resolution"],"description":"HappyHorse 1.0 Reference generates 3- to 15-second clips at up to 1080p from reference images, keeping characters and subjects consistent, with native audio.","name":"HappyHorse 1.0 Reference","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1777248000,"id":"happyhorse-1-0-video-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["Auto"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true,"reference_image_min_short_side_pixels":300},"model_sets":["high_resolution"],"description":"HappyHorse 1.0 Edit changes an existing video from text instructions, with optional reference images, at up to 1080p with native audio.","name":"HappyHorse 1.0 Edit","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1765843200,"id":"wan-2.6-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source"],"description":"Wan 2.6 is Alibaba's video model with audio support. This image-to-video variant animates a starting image into a 5-, 10- or 15-second clip at up to 1080p, with optional audio, and can follow an audio track you provide.","name":"Wan 2.6","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1768824000,"id":"wan-2.6-flash-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source"],"description":"Wan 2.6 Flash is a fast version of Alibaba's Wan 2.6 for image-to-video, animating a starting image into a 5-, 10- or 15-second clip at up to 1080p with native audio.","name":"Wan 2.6 Flash","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1765843200,"id":"wan-2.6-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","long_duration","open_source"],"description":"Wan 2.6 is Alibaba's video model with audio support. This text-to-video variant generates 5-, 10- or 15-second clips at up to 1080p, with optional audio, and can follow an audio track you provide.","name":"Wan 2.6","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"wan-2.5-preview-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["1080p","720p","480p"],"durations":["5s","10s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","open_source"],"description":"Wan 2.5 Preview is a preview release of Alibaba's Wan 2.5, served uncensored. This image-to-video variant animates a starting image into a 5- or 10-second clip at up to 1080p with native audio.","name":"Wan 2.5 Preview","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"wan-2.5-preview-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["1080p","720p","480p"],"durations":["5s","10s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","high_resolution","audio","open_source"],"description":"Wan 2.5 Preview is a preview release of Alibaba's Wan 2.5, served uncensored. This text-to-video variant generates 5- or 10-second clips at up to 1080p with native audio.","name":"Wan 2.5 Preview","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776038400,"id":"grok-imagine-text-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic"],"description":"Grok Imagine is xAI's video model, generating 1- to 15-second clips at up to 720p from text, with native audio.","name":"Grok Imagine","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776211200,"id":"grok-imagine-image-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480p","720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic"],"description":"Grok Imagine's image-to-video variant turns a starting image into a 1- to 15-second clip at up to 720p, with native audio.","name":"Grok Imagine","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776211200,"id":"grok-imagine-reference-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["photorealistic"],"description":"Grok Imagine R2V generates 1- to 10-second clips at up to 720p from several reference images, which you cite in the prompt as @Image1, @Image2 and so on.","name":"Grok Imagine R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776211200,"id":"grok-imagine-video-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["480p","720p"],"durations":["5s","10s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","venice_recommendations"],"description":"Grok Imagine's video editing variant changes an existing clip from text instructions, in 5-, 10- or 15-second results at up to 720p, with native audio.","name":"Grok Imagine","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1780185600,"id":"grok-imagine-1-5-text-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p","1080p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","high_resolution","venice_recommendations","featured"],"description":"Grok Imagine 1.5 is xAI's updated video model, generating 1- to 15-second clips at up to 1080p from text, with native audio.","name":"Grok Imagine 1.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1780185600,"id":"grok-imagine-1-5-image-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480p","720p","1080p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","high_resolution","venice_recommendations"],"description":"Grok Imagine 1.5's image-to-video variant turns a starting image into a 1- to 15-second clip at up to 1080p, with native audio.","name":"Grok Imagine 1.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785283200,"id":"grok-imagine-1-5-reference-to-video-private","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","venice_recommendations"],"description":"Grok Imagine 1.5 R2V generates 1- to 15-second clips at up to 720p from up to 7 reference images, with native audio.","name":"Grok Imagine 1.5 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1790726400,"id":"grok-imagine-1-5-lite-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","4:3","3:2","1:1","2:3","3:4","9:16"],"resolutions":["480p","720p","1080p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","high_resolution"],"description":"Grok Imagine 1.5 Lite is a quicker, more affordable version of xAI's Grok Imagine 1.5, generating 1- to 15-second clips at up to 1080p from text, with native audio.","name":"Grok Imagine 1.5 Lite","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1790726400,"id":"grok-imagine-1-5-lite-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480p","720p","1080p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4096},"model_sets":["audio","long_duration","photorealistic","high_resolution"],"description":"Grok Imagine 1.5 Lite's image-to-video variant quickly turns a starting image into a 1- to 15-second clip at up to 1080p, with native audio.","name":"Grok Imagine 1.5 Lite","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1772668800,"id":"ltx-2-v2-3-fast-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["1080p","1440p","2160p"],"durations":["6s","8s","10s","12s","14s","16s","18s","20s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","open_source"],"description":"LTX Video 2.3 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.3 video model. This image-to-video variant animates a starting image into a 6- to 20-second clip at up to 4K, with optional audio.","name":"LTX Video 2.3 Fast","modelSource":"https://huggingface.co/Lightricks/LTX-2.3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1772668800,"id":"ltx-2-v2-3-fast-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["1080p","1440p","2160p"],"durations":["6s","8s","10s","12s","14s","16s","18s","20s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","open_source"],"description":"LTX Video 2.3 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.3 video model. This text-to-video variant generates 6- to 20-second clips at up to 4K, with optional audio.","name":"LTX Video 2.3 Fast","modelSource":"https://huggingface.co/Lightricks/LTX-2.3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1772668800,"id":"ltx-2-v2-3-full-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["1080p","1440p","2160p"],"durations":["6s","8s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","open_source"],"description":"LTX Video 2.3 Full Quality runs Lightricks' open-weight LTX-2.3 at full quality. This image-to-video variant animates a starting image into a 6-, 8- or 10-second clip at up to 4K, with optional audio.","name":"LTX Video 2.3 Full Quality","modelSource":"https://huggingface.co/Lightricks/LTX-2.3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1772668800,"id":"ltx-2-v2-3-full-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["1080p","1440p","2160p"],"durations":["6s","8s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","open_source"],"description":"LTX Video 2.3 Full Quality runs Lightricks' open-weight LTX-2.3 at full quality. This text-to-video variant generates 6-, 8- or 10-second clips at up to 4K, with optional audio.","name":"LTX Video 2.3 Full Quality","modelSource":"https://huggingface.co/Lightricks/LTX-2.3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786406400,"id":"ltx-2-5-fast-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","16:9","9:16"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["6s","8s","10s","12s","14s","16s","18s","20s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","open_source"],"description":"LTX Video 2.5 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.5 video model. This image-to-video variant animates a starting image into a 6- to 20-second clip at up to 4K, with optional audio.","name":"LTX Video 2.5 Fast","modelSource":"https://huggingface.co/Lightricks/LTX-2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786406400,"id":"ltx-2-5-fast-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["6s","8s","10s","12s","14s","16s","18s","20s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration","open_source"],"description":"LTX Video 2.5 Fast is the speed-focused tier of Lightricks' open-weight LTX-2.5 video model. This text-to-video variant generates 6- to 20-second clips at up to 4K, with optional audio.","name":"LTX Video 2.5 Fast","modelSource":"https://huggingface.co/Lightricks/LTX-2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786406400,"id":"ltx-2-5-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","16:9","9:16"],"resolutions":["720p","1080p"],"durations":["6s","8s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","open_source"],"description":"LTX Video 2.5 Pro is the quality-focused tier of Lightricks' open-weight LTX-2.5. This image-to-video variant animates a starting image into a 6-, 8- or 10-second clip at up to 1080p, with optional audio.","name":"LTX Video 2.5 Pro","modelSource":"https://huggingface.co/Lightricks/LTX-2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1786406400,"id":"ltx-2-5-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["720p","1080p"],"durations":["6s","8s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","open_source"],"description":"LTX Video 2.5 Pro is the quality-focused tier of Lightricks' open-weight LTX-2.5. This text-to-video variant generates 6-, 8- or 10-second clips at up to 1080p, with optional audio.","name":"LTX Video 2.5 Pro","modelSource":"https://huggingface.co/Lightricks/LTX-2.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"ovi-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["5s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","audio","open_source"],"description":"Ovi is Character.AI's open-weight audio-video model, based on Wan, that animates a starting image into a 5-second clip with native audio. It runs fast and is served uncensored.","name":"Ovi","modelSource":"https://huggingface.co/chetwinlow1/Ovi","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"minimax-h3-max-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","venice_recommendations","fast"],"description":"MiniMax H3 Max is a post-trained variant of MiniMax's H3 video model. This text-to-video variant generates 5- to 15-second clips at up to 1080p with native stereo audio.","name":"MiniMax H3 Max","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"minimax-h3-max-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","venice_recommendations","fast"],"description":"MiniMax H3 Max's image-to-video variant animates a first frame, with an optional end frame, into a 5- to 15-second clip at up to 1080p with native stereo audio.","name":"MiniMax H3 Max","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1789171200,"id":"minimax-h3-max-multi-angle","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","high_resolution","long_duration","cinematic","audio","fast"],"description":"MiniMax H3 Max Multi-Angle moves a virtual camera around a single image, with precise control of orbit, elevation and distance, producing 5- to 15-second clips at up to 1080p with native audio.","name":"MiniMax H3 Max Multi-Angle","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1787788800,"id":"minimax-h3-max-reference-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","venice_recommendations"],"description":"MiniMax H3 Max R2V generates 5- to 15-second clips at up to 1080p from reference images, videos and audio, cited in the prompt as @Image1, @Video1 and so on, with native audio.","name":"MiniMax H3 Max R2V","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1791331200,"id":"minimax-h3-max-recast","model_spec":{"privacy":"private","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["768P","1080P"],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true,"prompt_character_limit":2000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","high_resolution","long_duration","cinematic","photorealistic"],"description":"MiniMax H3 Max Recast replaces the people in a source video with people from reference photos, preserving the original motion, camera, cuts and soundtrack, at up to 1080p.","name":"MiniMax H3 Max Recast","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788307200,"id":"minimax-h3-max-turbo-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","fast"],"description":"MiniMax H3 Max Turbo is a faster version of MiniMax H3 Max, generating 5- to 15-second clips at up to 1080p from text with native stereo audio.","name":"MiniMax H3 Max Turbo","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1788307200,"id":"minimax-h3-max-turbo-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["480P","768P","1080P"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":10000},"model_sets":["uncensored","audio","high_resolution","long_duration","cinematic","photorealistic","fast"],"description":"MiniMax H3 Max Turbo's image-to-video variant animates a first frame, with an optional end frame, into a 5- to 15-second clip at up to 1080p with native stereo audio.","name":"MiniMax H3 Max Turbo","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1733186476,"id":"kling-2.6-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["5s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic"],"description":"Kling 2.6 Pro is Kling AI's full-quality video model with native audio generation. This text-to-video variant generates 5- or 10-second clips, with optional audio.","name":"Kling 2.6 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1733186476,"id":"kling-2.6-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["5s","10s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic"],"description":"Kling 2.6 Pro's image-to-video variant animates a starting image into a 5- or 10-second clip, with optional native audio.","name":"Kling 2.6 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"kling-2.5-turbo-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["5s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","photorealistic"],"description":"Kling 2.5 Turbo Pro is Kling AI's full-quality Kling 2.5 video model, generating 5- or 10-second clips from text.","name":"Kling 2.5 Turbo Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1758825748,"id":"kling-2.5-turbo-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["5s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","photorealistic"],"description":"Kling 2.5 Turbo Pro's image-to-video variant animates a starting image into a 5- or 10-second clip.","name":"Kling 2.5 Turbo Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-v3-4k-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration","ultra_high_resolution"],"description":"Kling V3 4K generates video at native 4K without upscaling, using Kling AI's V3 model. This text-to-video variant makes 3- to 15-second clips, with optional audio.","name":"Kling V3 4K","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-v3-4k-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration","ultra_high_resolution"],"description":"Kling V3 4K R2V animates a start frame into native 4K video, using reference elements to keep characters and objects consistent, in 3- to 15-second clips with optional audio.","name":"Kling V3 4K R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-o3-4k-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","long_duration","ultra_high_resolution"],"description":"Kling O3 4K generates native 4K video with Kling AI's O3 model, tuned for stylized and anime looks. This text-to-video variant makes 3- to 15-second clips, with optional audio.","name":"Kling O3 4K","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-o3-4k-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","long_duration","ultra_high_resolution"],"description":"Kling O3 4K's image-to-video variant animates a starting image, with an optional end image, into native 4K stylized or anime motion, in 3- to 15-second clips.","name":"Kling O3 4K","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1776816000,"id":"kling-o3-4k-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","long_duration","ultra_high_resolution"],"description":"Kling O3 4K R2V combines up to 7 character, object or style references into a single native 4K clip of 3 to 15 seconds, with optional audio.","name":"Kling O3 4K R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-o3-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration","venice_recommendations"],"description":"Kling O3 Pro is the premium tier of Kling AI's O3 video model. This text-to-video variant generates 3- to 15-second clips, with optional audio.","name":"Kling O3 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-o3-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration","venice_recommendations"],"description":"Kling O3 Pro's image-to-video variant animates a starting image, with an optional end image, into a 3- to 15-second clip, with optional audio.","name":"Kling O3 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1773014400,"id":"kling-o3-pro-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling O3 Pro R2V turns images and elements into 3- to 15-second clips with stable character identity, using a frontal image and reference images for each element.","name":"Kling O3 Pro R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-o3-standard-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling O3 Standard is the balanced tier of Kling AI's O3 video model, trading some quality for speed. This text-to-video variant generates 3- to 15-second clips, with optional audio.","name":"Kling O3 Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-o3-standard-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling O3 Standard's image-to-video variant animates a starting image, with an optional end image, into a 3- to 15-second clip, with optional audio.","name":"Kling O3 Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1773100800,"id":"kling-o3-standard-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling O3 Standard R2V turns images and elements into 3- to 15-second clips with stable character identity, at the Standard tier's balance of quality and speed.","name":"Kling O3 Standard R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1779667200,"id":"kling-v3-pro-motion-control","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":[],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["cinematic","photorealistic","long_duration"],"description":"Kling V3 Pro Motion Control transfers the movements in a reference video onto a character image, at Kling V3 Pro quality. The output follows the length of the source video.","name":"Kling V3 Pro Motion Control","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-v3-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Pro is the enhanced-quality tier of Kling AI's V3 video model. This text-to-video variant generates 3- to 15-second clips, with optional audio.","name":"Kling V3 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-v3-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Pro's image-to-video variant animates a start frame, with an optional end frame, into a 3- to 15-second clip, with optional audio.","name":"Kling V3 Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1779667200,"id":"kling-v3-standard-motion-control","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":[],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["cinematic","photorealistic","long_duration"],"description":"Kling V3 Standard Motion Control transfers the movements in a reference video onto a character image, a cost-effective option for portraits and simple animations. The output follows the length of the source video.","name":"Kling V3 Standard Motion Control","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-v3-standard-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Standard is the balanced tier of Kling AI's V3 video model. This text-to-video variant generates 3- to 15-second clips, with optional audio.","name":"Kling V3 Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1770076800,"id":"kling-v3-standard-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Standard's image-to-video variant animates a start frame, with an optional end frame, into a 3- to 15-second clip, with optional audio.","name":"Kling V3 Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1781654400,"id":"kling-v3-turbo-pro-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Turbo Pro is a faster version of Kling V3 Pro, generating 3- to 15-second clips at 1080p from text, with multi-shot storyboards.","name":"Kling V3 Turbo Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1781654400,"id":"kling-v3-turbo-pro-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Turbo Pro's image-to-video variant animates a start frame into a 3- to 15-second clip at 1080p, with multi-shot storyboards.","name":"Kling V3 Turbo Pro","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1781654400,"id":"kling-v3-turbo-standard-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Turbo Standard is a faster, cost-effective version of Kling V3, generating 3- to 15-second clips at 720p from text, with multi-shot storyboards.","name":"Kling V3 Turbo Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1781654400,"id":"kling-v3-turbo-standard-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":[],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["cinematic","audio","photorealistic","long_duration"],"description":"Kling V3 Turbo Standard's image-to-video variant animates a start frame into a 3- to 15-second clip at 720p, with multi-shot storyboards.","name":"Kling V3 Turbo Standard","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792800000,"id":"kling-v4-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","21:9"],"resolutions":["720p","1080p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 is Kling AI's fourth-generation video model. This text-to-video variant generates 3- to 30-second clips at 720p or 1080p with native audio, and supports multi-shot prompts.","name":"Kling 4.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792800000,"id":"kling-v4-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","1080p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Kling 4.0's image-to-video variant animates a starting image, with optional end-frame control, into a 3- to 30-second clip at 720p or 1080p with native audio and multi-shot prompts.","name":"Kling 4.0","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792800000,"id":"kling-v4-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","16:9","9:16","1:1","21:9"],"resolutions":["720p","1080p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s","21s","22s","23s","24s","25s","26s","27s","28s","29s","30s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 R2V generates 3- to 30-second clips at 720p or 1080p with native audio from up to 10 reference images and 5 reference videos, with an optional start frame and multi-shot prompts.","name":"Kling 4.0 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793836800,"id":"kling-v4-flash-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","21:9"],"resolutions":["720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 Flash is a faster version of Kling AI's Kling 4.0, generating 3- to 20-second clips at 720p from text with native audio.","name":"Kling 4.0 Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793836800,"id":"kling-v4-flash-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 Flash's image-to-video variant animates a start frame into a 3- to 20-second clip at 720p with native audio.","name":"Kling 4.0 Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793836800,"id":"kling-v4-flash-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","16:9","9:16","1:1","21:9"],"resolutions":["720p"],"durations":["3s","4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 Flash R2V generates 3- to 20-second clips at 720p with native audio from up to 10 reference images and 5 reference videos, with an optional start frame.","name":"Kling 4.0 Flash R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793836800,"id":"kling-v4-flash-video-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["720p"],"durations":["Auto"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true,"prompt_character_limit":26000,"reference_image_min_short_side_pixels":300},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Kling 4.0 Flash Edit changes a source video from a text instruction and up to 10 reference images, at 720p with native audio. The output follows the length of the source video.","name":"Kling 4.0 Flash Edit","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1764806400,"id":"longcat-distilled-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p"],"durations":["5s","10s","15s","20s","30s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","long_duration","open_source"],"description":"Longcat Distilled is the faster, distilled version of Meituan's open-weight LongCat-Video model. This image-to-video variant animates a starting image into a 5- to 30-second clip at 720p.","name":"Longcat Distilled","modelSource":"https://huggingface.co/meituan-longcat/LongCat-Video","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1764806400,"id":"longcat-distilled-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["720p"],"durations":["5s","10s","15s","20s","30s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","long_duration","open_source"],"description":"Longcat Distilled is the faster, distilled version of Meituan's open-weight LongCat-Video model. This text-to-video variant generates 5- to 30-second clips at 720p.","name":"Longcat Distilled","modelSource":"https://huggingface.co/meituan-longcat/LongCat-Video","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1764806400,"id":"longcat-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p"],"durations":["5s","10s","15s","20s","30s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","long_duration","open_source"],"description":"Longcat Full Quality runs Meituan's open-weight LongCat-Video model at full quality, built for longer clips. This image-to-video variant animates a starting image into a 5- to 30-second clip at 720p.","name":"Longcat Full Quality","modelSource":"https://huggingface.co/meituan-longcat/LongCat-Video","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1764806400,"id":"longcat-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1"],"resolutions":["720p"],"durations":["5s","10s","15s","20s","30s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["uncensored","long_duration","open_source"],"description":"Longcat Full Quality runs Meituan's open-weight LongCat-Video model at full quality, built for longer clips. This text-to-video variant generates 5- to 30-second clips at 720p.","name":"Longcat Full Quality","modelSource":"https://huggingface.co/meituan-longcat/LongCat-Video","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1729030447,"id":"veo3.1-fast-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["720p","1080p","4k"],"durations":["4s","6s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","cinematic","photorealistic"],"description":"Veo 3.1 Fast is a faster version of Google's Veo 3.1 video model. This text-to-video variant generates 4-, 6- or 8-second clips at up to 4K, with optional audio.","name":"Veo 3.1 Fast","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1729030447,"id":"veo3.1-fast-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","1080p","4k"],"durations":["4s","6s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","cinematic","photorealistic"],"description":"Veo 3.1 Fast's image-to-video variant animates a starting image into a 4-, 6- or 8-second clip at up to 4K, with optional audio.","name":"Veo 3.1 Fast","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1729030447,"id":"veo3.1-full-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":["720p","1080p","4k"],"durations":["4s","6s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","cinematic","photorealistic"],"description":"Veo 3.1 Full Quality runs Google's Veo 3.1 video model at full quality. This text-to-video variant generates 4-, 6- or 8-second clips at up to 4K, with optional audio.","name":"Veo 3.1 Full Quality","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1729030447,"id":"veo3.1-full-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["720p","1080p","4k"],"durations":["4s","6s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","cinematic","photorealistic"],"description":"Veo 3.1 Full Quality's image-to-video variant animates a starting image into a 4-, 6- or 8-second clip at up to 4K, with optional audio.","name":"Veo 3.1 Full Quality","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782777600,"id":"gemini-omni-flash-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":[],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Gemini Omni Flash is Google's video model for 4- to 10-second clips from text prompts. Gemini Omni Flash 1.1 is its newer successor.","name":"Gemini Omni Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782777600,"id":"gemini-omni-flash-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":[],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Gemini Omni Flash's image-to-video variant animates a starting image into a 4- to 10-second clip, using Google's Gemini Omni Flash video model.","name":"Gemini Omni Flash","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1782777600,"id":"gemini-omni-flash-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16"],"resolutions":[],"durations":["4s","6s","8s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","long_duration","cinematic","photorealistic"],"description":"Gemini Omni Flash R2V combines several reference images into one 4- to 10-second clip, using Google's Gemini Omni Flash video model.","name":"Gemini Omni Flash R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785801600,"id":"flux-3-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["auto","21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["5s","10s","15s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration"],"description":"Flux 3 is Black Forest Labs' video model with synchronized audio. This text-to-video variant generates 5- to 20-second clips at up to 4K.","name":"Flux 3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785801600,"id":"flux-3-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["5s","10s","15s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration"],"description":"Flux 3's image-to-video variant animates a single still image into a 5- to 20-second clip at up to 4K, with synchronized audio.","name":"Flux 3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785801600,"id":"flux-3-first-last-frame-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["5s","10s","15s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration"],"description":"Flux 3 First Last Frame generates the transition between a start frame and an end frame, as a 5- to 20-second clip at up to 4K with synchronized audio.","name":"Flux 3 First Last Frame","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785801600,"id":"flux-3-extend-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":["auto","21:9","16:9","4:3","1:1","3:4","9:16","9:21"],"resolutions":["720p","1080p","1440p","2160p"],"durations":["5s","10s","15s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["high_resolution","ultra_high_resolution","audio","long_duration"],"description":"Flux 3 Extend continues an existing clip beyond its final frame, adding 5 to 20 seconds at up to 4K with synchronized audio.","name":"Flux 3 Extend","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792108800,"id":"flux-3-max-text-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"text-to-video","aspect_ratios":["auto","21:9","2:1","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","1080p"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Flux 3 Max is Black Forest Labs' post-trained Flux 3 video model, built for high visual quality at high speed. This text-to-video variant generates 5- to 20-second clips at up to 1080p with synchronized audio.","name":"Flux 3 Max","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1792108800,"id":"flux-3-max-image-to-video","model_spec":{"privacy":"private","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","21:9","2:1","16:9","4:3","1:1","3:4","9:16"],"resolutions":["720p","1080p"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s","16s","17s","18s","19s","20s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["audio","high_resolution","long_duration","cinematic","photorealistic"],"description":"Flux 3 Max's image-to-video variant animates a still image, with an optional end frame, into a 5- to 20-second clip at up to 1080p with synchronized audio.","name":"Flux 3 Max","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769472000,"id":"pixverse-v5.6-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["360p","540p","720p","1080p"],"durations":["5s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic"],"description":"PixVerse v5.6 is PixVerse's video model. This text-to-video variant generates 5- or 8-second clips at up to 1080p, with optional audio.","name":"PixVerse v5.6","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769472000,"id":"pixverse-v5.6-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["360p","540p","720p","1080p"],"durations":["5s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic"],"description":"PixVerse v5.6's image-to-video variant animates a starting image into a 5- or 8-second clip at up to 1080p, with optional audio.","name":"PixVerse v5.6","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769472000,"id":"pixverse-v5.6-transition","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4"],"resolutions":["360p","540p","720p","1080p"],"durations":["5s","8s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic"],"description":"PixVerse v5.6 Transition creates a smooth transition between a start image and an end image, as a 5- or 8-second clip at up to 1080p, with optional audio.","name":"PixVerse v5.6 Transition","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775865600,"id":"pixverse-c1-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic","long_duration"],"description":"PixVerse C1 is PixVerse's film-grade video model, generating 3- to 15-second clips at up to 1080p from text, with optional native audio.","name":"PixVerse C1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775865600,"id":"pixverse-c1-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic","long_duration"],"description":"PixVerse C1's image-to-video variant animates a starting image into a cinematic 3- to 15-second clip at up to 1080p, with optional native audio.","name":"PixVerse C1","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775865600,"id":"pixverse-c1-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic","long_duration"],"description":"PixVerse C1 R2V generates character-consistent 3- to 15-second clips at up to 1080p from reference images of subjects and backgrounds, with optional native audio.","name":"PixVerse C1 R2V","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775865600,"id":"pixverse-c1-transition","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","4:3","1:1","3:4","9:16","2:3","3:2","21:9"],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","15s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","cinematic","long_duration"],"description":"PixVerse C1 Transition creates a seamless cinematic transition between a start image and an end image, as a 3- to 15-second clip at up to 1080p, with optional native audio.","name":"PixVerse C1 Transition","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769817600,"id":"vidu-q3-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","4:3","3:4","1:1"],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","12s","14s","16s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","long_duration","cinematic","venice_recommendations"],"description":"Vidu Q3 is Vidu's video model. This text-to-video variant generates 3- to 16-second clips at up to 1080p, with optional audio.","name":"Vidu Q3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769817600,"id":"vidu-q3-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["360p","540p","720p","1080p"],"durations":["3s","5s","8s","10s","12s","14s","16s"],"audio":true,"audio_configurable":true,"audio_input":false,"per_reference_audio":false,"video_input":false},"model_sets":["high_resolution","audio","long_duration","cinematic","venice_recommendations"],"description":"Vidu Q3's image-to-video variant animates a starting image into a 3- to 16-second clip at up to 1080p, with optional audio.","name":"Vidu Q3","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775952000,"id":"runway-gen4-5","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4","21:9"],"resolutions":[],"durations":["2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":1000},"model_sets":["cinematic","photorealistic"],"description":"Runway Gen-4.5 is Runway's video model. This image-to-video variant animates a starting image into a 2- to 10-second clip.","name":"Runway Gen-4.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775952000,"id":"runway-gen4-5-text","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16"],"resolutions":[],"durations":["2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":1000},"model_sets":["cinematic","photorealistic"],"description":"Runway Gen-4.5's text-to-video variant generates 2- to 10-second clips from prompts of up to 1,000 characters, using Runway's Gen-4.5 video model.","name":"Runway Gen-4.5","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1769040000,"id":"runway-gen4-turbo","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4","21:9"],"resolutions":[],"durations":["2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":1000},"model_sets":["fast","cinematic","photorealistic","fast"],"description":"Runway Gen-4 Turbo is a faster version of Runway's Gen-4 video model, animating a starting image into a 2- to 10-second clip.","name":"Runway Gen-4 Turbo","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1775174400,"id":"topaz-video-upscale","model_spec":{"privacy":"anonymized","constraints":{"model_type":"video","aspect_ratios":[],"resolutions":["2x","4x"],"durations":["Auto"],"audio":false,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":true},"model_sets":["high_resolution","ultra_high_resolution"],"description":"Topaz Video Upscale uses Topaz Labs' upscaling to enlarge an existing video 2x or 4x while restoring detail. The output keeps the source video's length.","name":"Topaz Video Upscale","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785888000,"id":"minimax-h3-enhanced-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3 Enhanced is a version of MiniMax's H3 (Hailuo 3) tuned for uncensored output. This text-to-video variant generates 5- to 15-second clips at up to 2K with native audio.","name":"MiniMax H3 Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785888000,"id":"minimax-h3-enhanced-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3 R2V Enhanced generates uncensored 5- to 15-second clips at up to 2K from reference images and audio, with native audio.","name":"MiniMax H3 R2V Enhanced","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785369600,"id":"minimax-h3-text-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3, also called Hailuo 3, is MiniMax's video model. This text-to-video variant generates 5- to 15-second clips at up to 2K with native audio.","name":"MiniMax H3","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785369600,"id":"minimax-h3-image-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3's image-to-video variant animates a first frame, with an optional end frame, into a 5- to 15-second clip at up to 2K with native audio.","name":"MiniMax H3","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1785369600,"id":"minimax-h3-reference-to-video","model_spec":{"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["768P","2K"],"durations":["5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","high_resolution","photorealistic"],"description":"MiniMax H3 R2V generates 5- to 15-second clips at up to 2K from reference images, videos and audio, cited in the prompt as @Image1, @Video1 and so on, with native audio.","name":"MiniMax H3 R2V","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793750400,"id":"minimax-h3-chili-text-to-video","model_spec":{"beta":true,"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","21:9","4:3","1:1","3:4","9:16"],"resolutions":["768P"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000},"model_sets":["uncensored","audio","long_duration"],"description":"MiniMax H3 Chili is an uncensored version of MiniMax's H3 video model. This text-to-video variant generates 4- to 15-second clips at 768p with native audio.","name":"MiniMax H3 Chili (Prodia)","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793750400,"id":"minimax-h3-chili-image-to-video","model_spec":{"beta":true,"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":[],"resolutions":["768P"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","long_duration"],"description":"MiniMax H3 Chili's image-to-video variant animates a first frame, with an optional end frame, into a 4- to 15-second clip at 768p with native audio.","name":"MiniMax H3 Chili (Prodia)","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1793750400,"id":"minimax-h3-chili-reference-to-video","model_spec":{"beta":true,"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["adaptive","16:9","4:3","1:1","3:4","9:16","21:9"],"resolutions":["768P"],"durations":["4s","5s","6s","7s","8s","9s","10s","11s","12s","13s","14s","15s"],"audio":true,"audio_configurable":false,"audio_input":true,"per_reference_audio":false,"video_input":false,"prompt_character_limit":7000,"reference_image_min_short_side_pixels":256,"reference_image_min_aspect_ratio":0.4,"reference_image_max_aspect_ratio":2.5},"model_sets":["uncensored","audio","long_duration"],"description":"MiniMax H3 Chili R2V generates 4- to 15-second clips at 768p with native audio from reference images, videos and audio, cited in the prompt as @Image1, @Video1 and @Audio1.","name":"MiniMax H3 Chili R2V (Prodia)","offline":false,"traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1791417600,"id":"ltx-2-5-bonbon-text-to-video","model_spec":{"beta":true,"privacy":"anonymized","constraints":{"model_type":"text-to-video","aspect_ratios":["16:9","9:16","1:1","4:3","3:4","3:2","2:3"],"resolutions":["720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4000},"model_sets":["audio","long_duration","open_source"],"description":"LTX Video 2.5 Bonbon is a less filtered version of Lightricks' open-weight LTX-2.5 video model. This text-to-video variant generates 1- to 10-second clips at 720p with native audio.","name":"LTX Video 2.5 Bonbon","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1791417600,"id":"ltx-2-5-bonbon-image-to-video","model_spec":{"beta":true,"privacy":"anonymized","constraints":{"model_type":"image-to-video","aspect_ratios":["auto","16:9","9:16","1:1","4:3","3:4","3:2","2:3"],"resolutions":["720p"],"durations":["1s","2s","3s","4s","5s","6s","7s","8s","9s","10s"],"audio":true,"audio_configurable":false,"audio_input":false,"per_reference_audio":false,"video_input":false,"prompt_character_limit":4000},"model_sets":["audio","long_duration","open_source"],"description":"LTX Video 2.5 Bonbon is a less filtered version of Lightricks' open-weight LTX-2.5 video model. This image-to-video variant animates a starting image, with an optional end frame, into a 1- to 10-second clip at 720p with native audio.","name":"LTX Video 2.5 Bonbon","offline":false,"traits":[]},"object":"model","owned_by":"venice.ai","type":"video"},{"created":1771804800,"id":"ace-step-15","model_spec":{"pricing":{"durations":{"60":{"usd":0.03,"diem":0.03,"min_seconds":60,"max_seconds":60},"90":{"usd":0.04,"diem":0.04,"min_seconds":61,"max_seconds":90},"120":{"usd":0.05,"diem":0.05,"min_seconds":91,"max_seconds":120},"150":{"usd":0.06,"diem":0.06,"min_seconds":121,"max_seconds":150},"180":{"usd":0.07,"diem":0.07,"min_seconds":151,"max_seconds":180},"210":{"usd":0.08,"diem":0.08,"min_seconds":181,"max_seconds":210}}},"supports_lyrics":true,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"duration_options":[60,90,120,150,180,210],"min_duration":60,"max_duration":210,"default_duration":60,"supported_formats":["flac"],"default_format":"flac","prompt_character_limit":512,"lyrics_character_limit":4096,"min_prompt_length":10,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Feature-rich song generation with optional lyrics and detailed musical controls.","name":"ACE-Step 1.5","modelSource":"https://huggingface.co/ACE-Step/Ace-Step1.5","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1771718400,"id":"elevenlabs-music","model_spec":{"pricing":{"durations":{"60":{"usd":0.69,"diem":0.69,"min_seconds":3,"max_seconds":60},"120":{"usd":1.38,"diem":1.38,"min_seconds":61,"max_seconds":120},"180":{"usd":2.08,"diem":2.08,"min_seconds":121,"max_seconds":180},"240":{"usd":2.76,"diem":2.76,"min_seconds":181,"max_seconds":240},"300":{"usd":3.45,"diem":3.45,"min_seconds":241,"max_seconds":300},"360":{"usd":4.15,"diem":4.15,"min_seconds":301,"max_seconds":360},"420":{"usd":4.84,"diem":4.84,"min_seconds":361,"max_seconds":420},"480":{"usd":5.52,"diem":5.52,"min_seconds":421,"max_seconds":480},"540":{"usd":6.22,"diem":6.22,"min_seconds":481,"max_seconds":540},"600":{"usd":6.9,"diem":6.9,"min_seconds":541,"max_seconds":600}}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":true,"supports_lyrics_optimizer":false,"supports_loop":false,"min_duration":3,"max_duration":600,"default_duration":60,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":4096,"min_prompt_length":10,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"High-quality instrumental music generation with configurable duration. Best for polished, production-ready tracks across a wide range of genres.","name":"ElevenLabs Music","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1789430400,"id":"elevenlabs-music-v2","model_spec":{"pricing":{"durations":{"60":{"usd":0.69,"diem":0.69,"min_seconds":3,"max_seconds":60},"120":{"usd":1.38,"diem":1.38,"min_seconds":61,"max_seconds":120},"180":{"usd":2.08,"diem":2.08,"min_seconds":121,"max_seconds":180},"240":{"usd":2.76,"diem":2.76,"min_seconds":181,"max_seconds":240},"300":{"usd":3.45,"diem":3.45,"min_seconds":241,"max_seconds":300},"360":{"usd":4.15,"diem":4.15,"min_seconds":301,"max_seconds":360},"420":{"usd":4.84,"diem":4.84,"min_seconds":361,"max_seconds":420},"480":{"usd":5.52,"diem":5.52,"min_seconds":421,"max_seconds":480},"540":{"usd":6.22,"diem":6.22,"min_seconds":481,"max_seconds":540},"600":{"usd":6.9,"diem":6.9,"min_seconds":541,"max_seconds":600}}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":true,"supports_lyrics_optimizer":false,"supports_loop":false,"min_duration":3,"max_duration":600,"default_duration":60,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":4096,"min_prompt_length":10,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"High-quality realistic music generation with optional vocals and configurable duration. Best for polished, production-ready tracks across a wide range of genres.","name":"ElevenLabs Music v2","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1789430400,"id":"elevenlabs-music-v2-5","model_spec":{"pricing":{"durations":{"60":{"usd":0.69,"diem":0.69,"min_seconds":3,"max_seconds":60},"120":{"usd":1.38,"diem":1.38,"min_seconds":61,"max_seconds":120},"180":{"usd":2.08,"diem":2.08,"min_seconds":121,"max_seconds":180},"240":{"usd":2.76,"diem":2.76,"min_seconds":181,"max_seconds":240},"300":{"usd":3.45,"diem":3.45,"min_seconds":241,"max_seconds":300},"360":{"usd":4.15,"diem":4.15,"min_seconds":301,"max_seconds":360},"420":{"usd":4.84,"diem":4.84,"min_seconds":361,"max_seconds":420},"480":{"usd":5.52,"diem":5.52,"min_seconds":421,"max_seconds":480},"540":{"usd":6.22,"diem":6.22,"min_seconds":481,"max_seconds":540},"600":{"usd":6.9,"diem":6.9,"min_seconds":541,"max_seconds":600}}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":true,"supports_lyrics_optimizer":false,"supports_loop":false,"min_duration":3,"max_duration":600,"default_duration":60,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":4096,"min_prompt_length":10,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Latest ElevenLabs music generation with higher-quality realistic tracks, optional vocals, and configurable duration. Best for polished, production-ready songs across a wide range of genres.","name":"ElevenLabs Music v2.5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1771718400,"id":"minimax-music-v2","model_spec":{"pricing":{"generation":{"usd":0.04,"diem":0.04}},"supports_lyrics":true,"lyrics_required":true,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":300,"lyrics_character_limit":3000,"min_prompt_length":10,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Full song generation with vocals and lyrics. Provide your own lyrics with verse/chorus structure for complete songs with singing.","name":"MiniMax Music 2.0","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1775952000,"id":"minimax-music-v25","model_spec":{"pricing":{"generation":{"usd":0.18,"diem":0.18}},"supports_lyrics":true,"lyrics_required":false,"supports_force_instrumental":true,"supports_lyrics_optimizer":true,"supports_loop":false,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":2000,"lyrics_character_limit":3500,"min_prompt_length":10,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Advanced song generation with vocals, lyrics optimizer, and instrumental mode. Supports structure tags and up to 3500 character lyrics.","name":"MiniMax Music 2.5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1775952000,"id":"minimax-music-v26","model_spec":{"pricing":{"generation":{"usd":0.18,"diem":0.18}},"supports_lyrics":true,"lyrics_required":false,"supports_force_instrumental":true,"supports_lyrics_optimizer":false,"supports_loop":false,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":300,"lyrics_character_limit":1000,"min_prompt_length":10,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Latest MiniMax song generation with vocals, instrumental mode, and support for rich structure tags in lyrics.","name":"MiniMax Music 2.6","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1779408000,"id":"lyria-3-pro","model_spec":{"pricing":{"generation":{"usd":0.1,"diem":0.1}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":5000,"min_prompt_length":1,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Google's Lyria 3 Pro generates full-length, structured songs up to 3 minutes long from a single text prompt. Supports vocals, lyrics, and multi-language generation across genres.","name":"Lyria 3 Pro","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1771718400,"id":"stable-audio-25","model_spec":{"pricing":{"generation":{"usd":0.19,"diem":0.19}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"min_duration":5,"max_duration":190,"default_duration":30,"supported_formats":["wav"],"default_format":"wav","prompt_character_limit":500,"min_prompt_length":10,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Fast, lightweight audio generation for sound effects, ambient textures, and short musical clips. Flexible duration from 5 seconds to over 3 minutes.","name":"Stable Audio 2.5","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1784592000,"id":"sonilo-v1-1-music","model_spec":{"pricing":{"per_second":{"usd":0.0028750000000000004,"diem":0.0028750000000000004}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"min_duration":1,"max_duration":600,"default_duration":90,"supported_formats":["m4a"],"default_format":"m4a","prompt_character_limit":4096,"min_prompt_length":1,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Generate licensed, commercial-use-safe music with precise control over style, mood, instrumentation, and duration.","name":"Sonilo V1.1 Music","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1784592000,"id":"sonilo-v1-1-sound-effects","model_spec":{"pricing":{"per_second":{"usd":0.0020700000000000002,"diem":0.0020700000000000002}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"min_duration":1,"max_duration":180,"default_duration":8,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":4096,"min_prompt_length":1,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Generate licensed, commercial-use-safe sound effects with precise control over type, texture, intensity, and duration.","name":"Sonilo V1.1 Sound Effects","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1772236800,"id":"elevenlabs-sound-effects-v2","model_spec":{"pricing":{"per_second":{"usd":0.0023000000000000004,"diem":0.0023000000000000004}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":true,"min_duration":1,"max_duration":22,"default_duration":7,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":450,"min_prompt_length":1,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Generate high-quality sound effects from text descriptions using ElevenLabs. Ideal for films, games, and digital content with configurable duration.","name":"ElevenLabs Sound Effects","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1772236800,"id":"mmaudio-v2-text-to-audio","model_spec":{"pricing":{"per_second":{"usd":0.0009200000000000001,"diem":0.0009200000000000001}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"min_duration":1,"max_duration":30,"default_duration":5,"supported_formats":["wav"],"default_format":"wav","prompt_character_limit":500,"min_prompt_length":1,"supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Generate synchronized audio and sound effects from text prompts with MMAudio V2.","name":"MMAudio V2","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1772236800,"id":"elevenlabs-tts-v3","model_spec":{"pricing":{"per_thousand_characters":{"usd":0.11500000000000002,"diem":0.11500000000000002}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":5000,"min_prompt_length":1,"voices":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"default_voice":"Aria","supports_custom_voice_id":true,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Generate natural text-to-speech audio using ElevenLabs Eleven-v3. High-quality voices with stability control and automatic text normalization.","name":"ElevenLabs TTS v3","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1790640000,"id":"elevenlabs-tts-v4","model_spec":{"pricing":{"per_thousand_characters":{"usd":0.09200000000000001,"diem":0.09200000000000001}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":5000,"min_prompt_length":1,"voices":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"default_voice":"Aria","supports_custom_voice_id":true,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Generate expressive text-to-speech audio using ElevenLabs Eleven-v4. High-quality voices with audio tag support and automatic text normalization.","name":"ElevenLabs TTS v4","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1790640000,"id":"elevenlabs-tts-v4-turbo","model_spec":{"pricing":{"per_thousand_characters":{"usd":0.046000000000000006,"diem":0.046000000000000006}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":5000,"min_prompt_length":1,"voices":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"default_voice":"Aria","supports_custom_voice_id":true,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"description":"Generate fast text-to-speech audio using ElevenLabs Eleven-v4 Turbo. High-quality low-latency voices with audio tag support and automatic text normalization.","name":"ElevenLabs TTS v4 Turbo","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1772236800,"id":"elevenlabs-tts-multilingual-v2","model_spec":{"pricing":{"per_thousand_characters":{"usd":0.11500000000000002,"diem":0.11500000000000002}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":5000,"min_prompt_length":1,"voices":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"default_voice":"Aria","supports_custom_voice_id":true,"supports_language_code":false,"supports_speed":true,"supports_reference_audios":false,"default_speed":1,"min_speed":0.7,"max_speed":1.2,"description":"Multilingual text-to-speech using ElevenLabs. Supports 29 languages with high-quality natural-sounding voices, configurable speed, and accent accuracy.","name":"ElevenLabs Multilingual v2","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1785110400,"id":"elevenlabs-voice-changer","model_spec":{"pricing":{"durations":{"60":{"usd":0.35,"diem":0.35,"min_seconds":1,"max_seconds":60},"120":{"usd":0.69,"diem":0.69,"min_seconds":61,"max_seconds":120},"180":{"usd":1.04,"diem":1.04,"min_seconds":121,"max_seconds":180},"240":{"usd":1.38,"diem":1.38,"min_seconds":181,"max_seconds":240},"300":{"usd":1.73,"diem":1.73,"min_seconds":241,"max_seconds":300}}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"supported_formats":["mp3"],"default_format":"mp3","prompt_character_limit":0,"min_prompt_length":0,"voices":["Aria","Roger","Sarah","Laura","Charlie","George","Callum","River","Liam","Charlotte","Alice","Matilda","Will","Jessica","Eric","Chris","Brian","Daniel","Lily","Bill"],"default_voice":"Aria","supports_custom_voice_id":true,"supports_language_code":false,"supports_speed":false,"supports_reference_audios":false,"voice_changer":true,"supports_background_noise_removal":true,"supports_seed":true,"accepted_audio_formats":["mp3","wav","ogg","mp4","aac"],"max_source_audio_duration_seconds":300,"description":"Re-record any speech in a different voice with ElevenLabs Voice Changer. Keeps the original delivery, pacing and emotion.","name":"ElevenLabs Voice Changer","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1782691200,"id":"seed-audio-1-0","model_spec":{"pricing":{"per_second":{"usd":0.0028750000000000004,"diem":0.0028750000000000004}},"supports_lyrics":false,"lyrics_required":false,"supports_force_instrumental":false,"supports_lyrics_optimizer":false,"supports_loop":false,"supported_formats":["mp3","wav"],"default_format":"mp3","prompt_character_limit":3000,"min_prompt_length":1,"voices":["Describe in prompt","Tim","Stokie","Dacey","Vivi","Mindy","Kian","Jess","Vienna","Cedric","Magnus","Quentin","Wukong","Gigi","Celeste","Esther","Tracy","Sven","Felipe","Usseau","Enzo","Minimi","Jihoon","Martins","Han"],"default_voice":"Describe in prompt","supports_custom_voice_id":false,"supports_language_code":false,"supports_speed":true,"supports_reference_audios":true,"max_reference_audios":3,"default_speed":1,"min_speed":0.5,"max_speed":2,"description":"Generate expressive multilingual speech and audio from a text prompt with BytePlus Seed Audio 1.0 (20 languages, timestamp length control).","name":"Seed Audio 1.0","modelSource":"","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"music"},{"created":1741924661,"id":"text-embedding-bge-m3","model_spec":{"pricing":{"input":{"usd":0.15,"diem":0.15},"output":{"usd":0.6,"diem":0.6}},"embeddingDimensions":1024,"maxInputTokens":8192,"description":"BGE-M3 is BAAI's open-weight multilingual embedding model, covering more than 100 languages. It turns inputs of up to 8,192 tokens into 1,024-dimensional vectors for semantic search, retrieval and clustering across languages.","name":"BGE-M3","modelSource":"https://huggingface.co/BAAI/bge-m3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"embedding"},{"created":1776384000,"id":"text-embedding-bge-en-icl","model_spec":{"pricing":{"input":{"usd":0.0125,"diem":0.0125},"output":{"usd":0.0125,"diem":0.0125}},"embeddingDimensions":4096,"maxInputTokens":8192,"description":"BGE-EN-ICL is BAAI's English embedding model, which can take a few examples in the query to adapt to a task, an approach BAAI calls in-context learning. It returns 4,096-dimensional vectors for inputs of up to 8,192 tokens, for English retrieval and classification.","name":"BGE-EN-ICL","modelSource":"https://huggingface.co/BAAI/bge-en-icl","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"embedding"},{"created":1776384000,"id":"text-embedding-qwen3-8b","model_spec":{"pricing":{"input":{"usd":0.0125,"diem":0.0125},"output":{"usd":0.0125,"diem":0.0125}},"embeddingDimensions":4096,"maxInputTokens":32768,"supportsCustomDimensions":true,"description":"Qwen3 Embedding 8B is the largest model in Alibaba's open-weight Qwen3 Embedding series, built on Qwen3 and trained for more than 100 languages, including programming languages. It returns 4,096-dimensional vectors for multilingual and code retrieval.","name":"Qwen3 Embedding 8B","modelSource":"https://huggingface.co/Qwen/Qwen3-Embedding-8B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"embedding"},{"created":1776384000,"id":"text-embedding-qwen3-0-6b","model_spec":{"pricing":{"input":{"usd":0.0125,"diem":0.0125},"output":{"usd":0.0125,"diem":0.0125}},"embeddingDimensions":1024,"maxInputTokens":32768,"supportsCustomDimensions":true,"description":"Qwen3 Embedding 0.6B is the smallest model in Alibaba's open-weight Qwen3 Embedding series, a fast, low-cost choice for multilingual and code retrieval. It returns 1,024-dimensional vectors.","name":"Qwen3 Embedding 0.6B","modelSource":"https://huggingface.co/Qwen/Qwen3-Embedding-0.6B","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"embedding"},{"created":1776384000,"id":"text-embedding-multilingual-e5-large-instruct","model_spec":{"pricing":{"input":{"usd":0.0125,"diem":0.0125},"output":{"usd":0.0125,"diem":0.0125}},"embeddingDimensions":1024,"maxInputTokens":512,"description":"Multilingual E5 Large Instruct is an open-weight embedding model from Microsoft's E5 family, covering about 100 languages. Queries start with a one-line task instruction, and inputs of up to 512 tokens become 1,024-dimensional vectors, which suits short passages and queries.","name":"Multilingual E5 Large Instruct","modelSource":"https://huggingface.co/intfloat/multilingual-e5-large-instruct","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"embedding"},{"created":1776384000,"id":"text-embedding-3-small","model_spec":{"pricing":{"input":{"usd":0.025,"diem":0.025},"output":{"usd":0.025,"diem":0.025}},"embeddingDimensions":1536,"maxInputTokens":8191,"supportsCustomDimensions":true,"description":"Text Embedding 3 Small is OpenAI's efficient embedding model, returning 1,536-dimensional vectors for inputs of up to 8,191 tokens. It's a low-cost default for semantic search, clustering and classification, and its vectors can be shortened with the dimensions parameter.","name":"Text Embedding 3 Small","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"embedding"},{"created":1776384000,"id":"text-embedding-3-large","model_spec":{"pricing":{"input":{"usd":0.1625,"diem":0.1625},"output":{"usd":0.1625,"diem":0.1625}},"embeddingDimensions":3072,"maxInputTokens":8191,"supportsCustomDimensions":true,"description":"Text Embedding 3 Large is OpenAI's larger embedding model, returning 3,072-dimensional vectors for inputs of up to 8,191 tokens. It suits retrieval where accuracy matters more than cost, and its vectors can be shortened with the dimensions parameter.","name":"Text Embedding 3 Large","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"embedding"},{"created":1776384000,"id":"gemini-embedding-2-preview","model_spec":{"pricing":{"input":{"usd":0.25,"diem":0.25},"output":{"usd":0.25,"diem":0.25}},"embeddingDimensions":3072,"maxInputTokens":2048,"supportsCustomDimensions":true,"description":"Gemini Embedding 2 Preview is a preview of Google's Gemini-based embedding model, returning 3,072-dimensional vectors for inputs of up to 2,048 tokens. It's built for semantic search, retrieval and classification.","name":"Gemini Embedding 2 Preview","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"embedding"},{"created":1776384000,"id":"text-embedding-nemotron-embed-vl-1b-v2","model_spec":{"pricing":{"input":{"usd":0.0125,"diem":0.0125},"output":{"usd":0.0125,"diem":0.0125}},"embeddingDimensions":2048,"maxInputTokens":32768,"description":"Nemotron Embed VL 1B v2 is NVIDIA's open-weight embedding model from its Llama Nemotron family, trained for retrieval over visually rich documents such as reports, slides and scanned pages. Through the API it embeds text into 2,048-dimensional vectors.","name":"Nemotron Embed VL 1B v2","modelSource":"https://huggingface.co/nvidia/llama-nemotron-embed-vl-1b-v2","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"embedding"},{"created":1742418046,"id":"tts-kokoro","model_spec":{"pricing":{"input":{"usd":3.5,"diem":3.5}},"default_format":"mp3","supported_formats":["mp3","opus","aac","flac","wav","pcm"],"supports_custom_voice_id":false,"voices":["af_alloy","af_aoede","af_bella","af_heart","af_jadzia","af_jessica","af_kore","af_nicole","af_nova","af_river","af_sarah","af_sky","am_adam","am_echo","am_eric","am_fenrir","am_liam","am_michael","am_onyx","am_puck","am_santa","bf_alice","bf_emma","bf_lily","bm_daniel","bm_fable","bm_george","bm_lewis","ef_dora","em_alex","em_santa","ff_siwis","hf_alpha","hf_beta","hm_omega","hm_psi","if_sara","im_nicola","jf_alpha","jf_gongitsune","jf_nezumi","jf_tebukuro","jm_kumo","pf_dora","pm_alex","pm_santa","zf_xiaobei","zf_xiaoni","zf_xiaoxiao","zf_xiaoyi","zm_yunjian","zm_yunxi","zm_yunxia","zm_yunyang"],"description":"Kokoro is hexgrad's open-weight 82M-parameter text-to-speech model. It speaks in 54 voices across several languages and returns MP3, Opus, AAC, FLAC, WAV or PCM audio.","name":"Kokoro Text to Speech","modelSource":"https://huggingface.co/hexgrad/Kokoro-82M","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1773100800,"id":"tts-qwen3-0-6b","model_spec":{"pricing":{"input":{"usd":87.5,"diem":87.5}},"default_format":"mp3","supported_formats":["mp3"],"supports_custom_voice_id":false,"voices":["Aiden","Dylan","Eric","Ono_Anna","Ryan","Serena","Sohee","Uncle_Fu","Vivian"],"description":"Qwen 3 TTS 0.6B is the smaller of Alibaba's two open-weight Qwen3-TTS models, built for fast, low-cost speech. It offers 9 voices and returns MP3 audio.","name":"Qwen 3 TTS 0.6B","modelSource":"https://huggingface.co/Qwen/Qwen3-TTS","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1773100800,"id":"tts-qwen3-1-7b","model_spec":{"pricing":{"input":{"usd":112.5,"diem":112.5}},"default_format":"mp3","supported_formats":["mp3"],"supports_custom_voice_id":false,"voices":["Aiden","Dylan","Eric","Ono_Anna","Ryan","Serena","Sohee","Uncle_Fu","Vivian"],"description":"Qwen 3 TTS 1.7B is the larger of Alibaba's two open-weight Qwen3-TTS models, trading some speed for higher-quality speech. It offers 9 voices and returns MP3 audio.","name":"Qwen 3 TTS 1.7B","modelSource":"https://huggingface.co/Qwen/Qwen3-TTS","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1776384000,"id":"tts-xai-v1","model_spec":{"pricing":{"input":{"usd":18.75,"diem":18.75}},"default_format":"mp3","supported_formats":["mp3","wav","pcm"],"supports_custom_voice_id":false,"voices":["altair","ara","atlas","carina","castor","celeste","cosmo","eve","helios","helix","iris","kepler","leo","lumen","luna","lux","naksh","orion","perseus","rex","rigel","sal","sirius","ursa","zagan","zenith"],"description":"xAI TTS v1 is xAI's text-to-speech model, made for narration, assistants and voice apps. It offers 26 voices and returns MP3, WAV or PCM audio.","name":"xAI TTS v1","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1776384000,"id":"tts-inworld-1-5-max","model_spec":{"pricing":{"input":{"usd":12.5,"diem":12.5}},"default_format":"wav","supported_formats":["wav"],"supports_custom_voice_id":false,"voices":["Alex","Ashley","Craig","Edward","Elizabeth","Hades","Luna","Mark","Olivia","Pixie","Priya","Ronald","Sarah","Theodore"],"description":"Inworld TTS-1.5 Max is the higher-quality tier of Inworld's TTS-1.5 speech model, made for expressive delivery in games, companions and voice agents. It offers 14 voices and returns WAV audio.","name":"Inworld TTS-1.5 Max","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1776384000,"id":"tts-chatterbox-hd","model_spec":{"pricing":{"input":{"usd":50,"diem":50}},"default_format":"wav","supported_formats":["wav"],"supports_custom_voice_id":false,"voices":["Aurora","Blade","Britney","Carl","Cliff","Richard","Rico","Siobhan","Vicky"],"voice_cloning":{"mode":"zero_shot","accepted_formats":["mp3","wav","flac","mp4"],"min_sample_seconds":5,"retention_days":7},"description":"Chatterbox HD is Resemble AI's open-weight text-to-speech model, known for expressive, natural delivery. It offers 9 voices and returns WAV audio.","name":"Chatterbox HD (Resemble AI)","modelSource":"https://huggingface.co/ResembleAI/chatterbox","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1776384000,"id":"tts-orpheus","model_spec":{"pricing":{"input":{"usd":62.5,"diem":62.5}},"default_format":"wav","supported_formats":["wav"],"supports_custom_voice_id":false,"voices":["dan","jess","leah","leo","mia","tara","zac","zoe"],"description":"Orpheus TTS is Canopy Labs' open-weight speech model, built on Llama 3B for natural, emotive delivery. It offers 8 voices and returns WAV audio.","name":"Orpheus TTS","modelSource":"https://huggingface.co/canopylabs/orpheus-3b-0.1-ft","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1776384000,"id":"tts-elevenlabs-turbo-v2-5","model_spec":{"pricing":{"input":{"usd":62.5,"diem":62.5}},"default_format":"mp3","supported_formats":["mp3"],"supports_custom_voice_id":true,"voices":["Alice","Aria","Bill","Brian","Callum","Charlie","Charlotte","Chris","Daniel","Eric","George","Jessica","Laura","Liam","Lily","Matilda","Rachel","River","Roger","Sarah","Will"],"description":"ElevenLabs Turbo v2.5 is ElevenLabs' low-latency multilingual speech model, balancing quality and speed for real-time use. It offers 21 voices and returns MP3 audio.","name":"ElevenLabs Turbo v2.5","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1776384000,"id":"tts-minimax-speech-02-hd","model_spec":{"pricing":{"input":{"usd":125,"diem":125}},"default_format":"mp3","supported_formats":["mp3","pcm","flac"],"supports_custom_voice_id":false,"voices":["CalmWoman","CasualGuy","DeepVoiceMan","DeterminedMan","ElegantMan","ExuberantGirl","FriendlyPerson","ImposingManner","InspirationalGirl","LivelyGirl","LovelyGirl","PatientMan","SweetGirl","WiseWoman","YoungKnight"],"description":"Clone your voice from a short recording and generate natural speech in it across 30+ languages.","name":"MiniMax Speech-02 HD","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1776643200,"id":"tts-gemini-3-1-flash","model_spec":{"pricing":{"input":{"usd":187.5,"diem":187.5}},"default_format":"mp3","supported_formats":["mp3","opus","wav"],"supports_custom_voice_id":false,"voices":["Achernar","Achird","Algenib","Algieba","Alnilam","Aoede","Autonoe","Callirrhoe","Charon","Despina","Enceladus","Erinome","Fenrir","Gacrux","Iapetus","Kore","Laomedeia","Leda","Orus","Puck","Pulcherrima","Rasalgethi","Sadachbia","Sadaltager","Schedar","Sulafat","Umbriel","Vindemiatrix","Zephyr","Zubenelgenubi"],"description":"Gemini 3.1 Flash TTS is Google's Gemini-based speech model, which follows natural-language instructions for tone and pacing. It offers 30 voices and returns MP3, Opus or WAV audio.","name":"Gemini 3.1 Flash TTS","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1780617600,"id":"tts-gradium-v1","model_spec":{"pricing":{"input":{"usd":47.5,"diem":47.5}},"default_format":"wav","supported_formats":["wav","pcm","opus"],"supports_custom_voice_id":false,"voices":["Alice","Davi","Elise","Emma","Eva","Jack","Kent","Leo","Maximilian","Mia","Sergio","Valentina"],"description":"Gradium TTS is Gradium's text-to-speech model for natural, low-latency voice generation. It offers 12 voices and returns WAV, PCM or Opus audio.","name":"Gradium TTS","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"tts"},{"created":1744453050,"id":"upscaler","model_spec":{"pricing":{"generation":{"usd":0.01,"diem":0.01},"upscale":{"2x":{"usd":0.02,"diem":0.02},"4x":{"usd":0.08,"diem":0.08}}},"description":"Upscaler is Venice's image upscaling model, enlarging an image 2x to 4x, up to 4096×4096 pixels. An optional creativity setting lets it add fine detail and texture as it scales.","name":"Upscaler","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"upscale"},{"created":1774396800,"id":"firered-image-edit","model_spec":{"pricing":{"inpaint":{"usd":0.04,"diem":0.04}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"promptCharacterLimit":1500,"combineImages":true,"singleImageAspectRatio":true},"supportsOptimizePromptThinking":false,"description":"FireRed is an instruction-following image editor that changes a source image from a natural-language request, with support for several reference images. It accepts prompts of up to 1,500 characters.","name":"FireRed","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1794268800,"id":"seedream-v5-5-edit","model_spec":{"pricing":{"inpaint":{"usd":0.0255,"diem":0.0255},"resolutions":{"1K":{"usd":0.0255,"diem":0.0255},"1.5K":{"usd":0.034,"diem":0.034},"2K":{"usd":0.051,"diem":0.051}},"inputImages":{"included":0,"additional":{"usd":0.010199235000000001,"diem":0.010199235000000001}}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:3"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":10,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","1.5K","2K"],"supportsTransparentBackground":true},"supportsOptimizePromptThinking":false,"description":"Seedream V5.5 Edit is ByteDance Seed's Seedream 5.5 for natural-language editing, at 1K, 1.5K, or 2K with up to 10 input images.","name":"Seedream V5.5","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1780531200,"id":"qwen-edit-uncensored","model_spec":{"pricing":{"inpaint":{"usd":0.04,"diem":0.04}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"promptCharacterLimit":1500,"combineImages":true,"singleImageAspectRatio":true},"supportsOptimizePromptThinking":false,"description":"Qwen Edit Uncensored is an uncensored image editor based on Alibaba's Qwen image editing model, with improved quality and precision. It changes a source image from a natural-language instruction, without masks.","name":"Qwen Edit Uncensored","offline":false,"privacy":"private","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1769644800,"id":"grok-imagine-edit","model_spec":{"pricing":{"inpaint":{"usd":0.03,"diem":0.03},"resolutions":{"1K":{"usd":0.03,"diem":0.03},"2K":{"usd":0.04,"diem":0.04}},"inputImages":{"included":0,"additional":{"usd":0.0023000000000000004,"diem":0.0023000000000000004}}},"constraints":{"aspectRatios":["auto","1:1","4:3","3:2","16:9","2:1","19.5:9","20:9","3:4","2:3","9:16","1:2","9:19.5","9:20"],"promptCharacterLimit":7500,"combineImages":true,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"]},"supportsOptimizePromptThinking":false,"description":"Grok Imagine Edit uses xAI's Grok Imagine to change an existing image from a text instruction: swap elements, restyle a scene or adjust details, at 1K or 2K.","name":"Grok Imagine","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1786406400,"id":"grok-imagine-image-2-0-edit","model_spec":{"pricing":{"inpaint":{"usd":0.07,"diem":0.07},"resolutions":{"1K":{"usd":0.07,"diem":0.07},"2K":{"usd":0.1,"diem":0.1}},"inputImages":{"included":0,"additional":{"usd":0.011500000000000002,"diem":0.011500000000000002}},"quality":{"1K":{"low":{"usd":0.05,"diem":0.05},"medium":{"usd":0.07,"diem":0.07}},"2K":{"low":{"usd":0.07,"diem":0.07},"medium":{"usd":0.1,"diem":0.1}}}},"constraints":{"aspectRatios":["auto","1:1","4:3","3:2","16:9","2:1","19.5:9","20:9","21:9","5:2","3:4","2:3","9:16","1:2","9:19.5","9:20"],"promptCharacterLimit":7500,"combineImages":true,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"],"defaultQuality":"medium","qualities":["low","medium"]},"supportsOptimizePromptThinking":false,"description":"Grok Imagine 2.0 Edit uses xAI's Grok Imagine 2.0 to change elements, styles and details of an existing image from a text instruction, at 1K or 2K with low and medium quality settings.","name":"Grok Imagine 2.0","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1793577600,"id":"krea-3-edit","model_spec":{"pricing":{"inpaint":{"usd":0.07,"diem":0.07},"resolutions":{"1K":{"usd":0.07,"diem":0.07},"2K":{"usd":0.1,"diem":0.1},"4K":{"usd":0.15,"diem":0.15}},"inputImages":{"included":0,"additional":{"usd":0.024999850000000004,"diem":0.024999850000000004}},"quality":{"1K":{"medium":{"usd":0.04,"diem":0.04},"high":{"usd":0.07,"diem":0.07}},"2K":{"medium":{"usd":0.08,"diem":0.08},"high":{"usd":0.1,"diem":0.1}},"4K":{"medium":{"usd":0.13,"diem":0.13},"high":{"usd":0.15,"diem":0.15}}}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":8,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["medium","high"]},"supportsOptimizePromptThinking":false,"description":"Krea 3 Edit changes an image from a text instruction and can combine up to 8 input images, rendering at up to 4K. It offers medium and high quality settings.","name":"Krea 3","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1772582400,"id":"qwen-image-2-edit","model_spec":{"pricing":{"inpaint":{"usd":0.05,"diem":0.05}},"constraints":{"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":10000,"combineImages":true,"singleImageAspectRatio":true},"supportsOptimizePromptThinking":false,"description":"Qwen Image 2 Edit is Alibaba's Qwen Image 2.0 in editing mode, changing an image from a natural-language instruction without masks.","name":"Qwen Image 2","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1772582400,"id":"qwen-image-2-pro-edit","model_spec":{"pricing":{"inpaint":{"usd":0.1,"diem":0.1}},"constraints":{"aspectRatios":["1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":10000,"combineImages":true,"singleImageAspectRatio":true},"supportsOptimizePromptThinking":false,"description":"Qwen Image 2 Pro Edit is the highest-fidelity tier of Alibaba's Qwen Image 2.0 for natural-language editing, built for precise, professional results.","name":"Qwen Image 2 Pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1776902400,"id":"wan-2-7-pro-edit","model_spec":{"pricing":{"inpaint":{"usd":0.094,"diem":0.094}},"constraints":{"aspectRatios":["auto"],"promptCharacterLimit":5000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"]},"supportsOptimizePromptThinking":false,"description":"Wan 2.7 Pro Edit is the premium tier of Alibaba's Wan 2.7 for natural-language image editing, combining up to 6 input images at 1K or 2K.","name":"Wan 2.7 Pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1767571200,"id":"flux-2-max-edit","model_spec":{"pricing":{"inpaint":{"usd":0.12,"diem":0.12},"inputImages":{"included":1,"additional":{"usd":0.0345,"diem":0.0345}}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":3000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true},"supportsOptimizePromptThinking":false,"description":"Flux 2 Max Edit is the top FLUX.2 tier from Black Forest Labs for editing, built for realism, precision and consistency across up to 6 input images.","name":"Flux 2 Max","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1790812800,"id":"flux-3-image-edit","model_spec":{"pricing":{"inpaint":{"usd":0.12,"diem":0.12},"resolutions":{"1K":{"usd":0.12,"diem":0.12},"2K":{"usd":0.29,"diem":0.29},"4K":{"usd":0.98,"diem":0.98}}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":32000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"]},"supportsOptimizePromptThinking":false,"description":"Flux 3 Edit is Black Forest Labs' flagship image editor, made for precise local edits and multi-reference composition across up to 6 input images, with output up to 4K.","name":"Flux 3","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1788825600,"id":"gpt-image-2-5-flare-edit","model_spec":{"pricing":{"inpaint":{"usd":0.08,"diem":0.08},"resolutions":{"1K":{"usd":0.08,"diem":0.08},"2K":{"usd":0.15,"diem":0.15},"4K":{"usd":0.24,"diem":0.24}},"inputImages":{"included":1,"additional":{"usd":0.00966,"diem":0.00966}},"quality":{"1K":{"high":{"usd":0.08,"diem":0.08},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.04,"diem":0.04}},"2K":{"high":{"usd":0.15,"diem":0.15},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.06,"diem":0.06}},"4K":{"high":{"usd":0.24,"diem":0.24},"low":{"usd":0.05,"diem":0.05},"medium":{"usd":0.08,"diem":0.08}}}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"],"supportsTransparentBackground":true},"supportsOptimizePromptThinking":false,"description":"GPT Image 2.5 Flare Edit makes fast, scoped edits with OpenAI's GPT Image 2.5 while keeping the subject and composition intact. It takes up to 6 input images and renders at up to 4K.","name":"GPT Image 2.5 Flare","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1788825600,"id":"gpt-image-2-5-sunburst-edit","model_spec":{"pricing":{"inpaint":{"usd":0.08,"diem":0.08},"resolutions":{"1K":{"usd":0.08,"diem":0.08},"2K":{"usd":0.15,"diem":0.15},"4K":{"usd":0.24,"diem":0.24}},"inputImages":{"included":1,"additional":{"usd":0.00966,"diem":0.00966}},"quality":{"1K":{"high":{"usd":0.08,"diem":0.08},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.04,"diem":0.04}},"2K":{"high":{"usd":0.15,"diem":0.15},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.06,"diem":0.06}},"4K":{"high":{"usd":0.24,"diem":0.24},"low":{"usd":0.05,"diem":0.05},"medium":{"usd":0.08,"diem":0.08}}}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"],"supportsTransparentBackground":true},"supportsOptimizePromptThinking":false,"description":"GPT Image 2.5 Sunburst Edit gives tight control over edits with OpenAI's premium GPT Image 2.5 tier, holding the subject and composition steady across revisions. It takes up to 6 input images and renders at up to 4K.","name":"GPT Image 2.5 Sunburst","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1793836800,"id":"gpt-image-2-6-sunburst-edit","model_spec":{"pricing":{"inpaint":{"usd":0.1,"diem":0.1},"resolutions":{"1K":{"usd":0.1,"diem":0.1},"2K":{"usd":0.16,"diem":0.16},"4K":{"usd":0.25,"diem":0.25}},"inputImages":{"included":1,"additional":{"usd":0.010500000000000002,"diem":0.010500000000000002}},"quality":{"1K":{"high":{"usd":0.1,"diem":0.1},"low":{"usd":0.06,"diem":0.06},"medium":{"usd":0.09,"diem":0.09}},"2K":{"high":{"usd":0.16,"diem":0.16},"low":{"usd":0.09,"diem":0.09},"medium":{"usd":0.14,"diem":0.14}},"4K":{"high":{"usd":0.25,"diem":0.25},"low":{"usd":0.13,"diem":0.13},"medium":{"usd":0.21,"diem":0.21}}}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"],"supportsTransparentBackground":true},"supportsOptimizePromptThinking":false,"description":"GPT Image 2.6 Sunburst Edit makes high-fidelity edits with OpenAI's GPT Image 2.6 Sunburst, keeping the subject and composition intact. It takes up to 6 input images and renders at up to 4K.","name":"GPT Image 2.6 Sunburst Edit","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1793836800,"id":"gpt-image-2-6-flare-edit","model_spec":{"pricing":{"inpaint":{"usd":0.1,"diem":0.1},"resolutions":{"1K":{"usd":0.1,"diem":0.1},"2K":{"usd":0.16,"diem":0.16},"4K":{"usd":0.25,"diem":0.25}},"inputImages":{"included":1,"additional":{"usd":0.010500000000000002,"diem":0.010500000000000002}},"quality":{"1K":{"high":{"usd":0.1,"diem":0.1},"low":{"usd":0.06,"diem":0.06},"medium":{"usd":0.09,"diem":0.09}},"2K":{"high":{"usd":0.16,"diem":0.16},"low":{"usd":0.09,"diem":0.09},"medium":{"usd":0.14,"diem":0.14}},"4K":{"high":{"usd":0.25,"diem":0.25},"low":{"usd":0.13,"diem":0.13},"medium":{"usd":0.21,"diem":0.21}}}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"],"supportsTransparentBackground":true},"supportsOptimizePromptThinking":false,"description":"GPT Image 2.6 Flare Edit makes fast, high-fidelity edits with OpenAI's GPT Image 2.6 Flare, keeping the subject and composition intact. It takes up to 6 input images and renders at up to 4K.","name":"GPT Image 2.6 Flare Edit","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1776729600,"id":"gpt-image-2-edit","model_spec":{"pricing":{"inpaint":{"usd":0.34,"diem":0.34},"resolutions":{"1K":{"usd":0.34,"diem":0.34},"2K":{"usd":0.52,"diem":0.52},"4K":{"usd":0.84,"diem":0.84}},"inputImages":{"included":1,"additional":{"usd":0.009200000000000002,"diem":0.009200000000000002}},"quality":{"1K":{"high":{"usd":0.34,"diem":0.34},"low":{"usd":0.03,"diem":0.03},"medium":{"usd":0.08,"diem":0.08}},"2K":{"high":{"usd":0.52,"diem":0.52},"low":{"usd":0.03,"diem":0.03},"medium":{"usd":0.14,"diem":0.14}},"4K":{"high":{"usd":0.84,"diem":0.84},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.22,"diem":0.22}}}},"constraints":{"aspectRatios":["1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"],"defaultQuality":"high","qualities":["low","medium","high"]},"supportsOptimizePromptThinking":false,"description":"GPT Image 2 Edit makes high-fidelity edits with OpenAI's GPT Image 2 that preserve the original composition. It takes up to 6 input images and renders at up to 4K.","name":"GPT Image 2","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1767555000,"id":"gpt-image-1-5-edit","model_spec":{"pricing":{"inpaint":{"usd":0.31,"diem":0.31},"inputImages":{"included":1,"additional":{"usd":0.028060000000000005,"diem":0.028060000000000005}}},"constraints":{"aspectRatios":["auto","1:1","3:2","2:3"],"promptCharacterLimit":5000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"supportsTransparentBackground":true},"supportsOptimizePromptThinking":false,"description":"GPT Image 1.5 Edit makes high-fidelity edits with OpenAI's GPT Image 1.5, preserving composition, lighting and detail. It takes up to 6 input images.","name":"GPT Image 1.5","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1790726400,"id":"ideogram-v4-5-edit","model_spec":{"pricing":{"inpaint":{"usd":0.26,"diem":0.26},"resolutions":{"1K":{"usd":0.26,"diem":0.26},"2K":{"usd":0.26,"diem":0.26}},"quality":{"1K":{"high":{"usd":0.26,"diem":0.26},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.07,"diem":0.07}},"2K":{"high":{"usd":0.26,"diem":0.26},"low":{"usd":0.04,"diem":0.04},"medium":{"usd":0.07,"diem":0.07}}}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":5,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"],"defaultQuality":"high","qualities":["low","medium","high"]},"supportsOptimizePromptThinking":false,"description":"Ideogram V4.5 Edit is Ideogram's typography-aware image editor, changing images and the text within them. It takes up to 5 input images, the source plus up to 4 references, at 1K or 2K.","name":"Ideogram V4.5","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1772064000,"id":"nano-banana-2-edit","model_spec":{"pricing":{"inpaint":{"usd":0.1,"diem":0.1},"resolutions":{"1K":{"usd":0.1,"diem":0.1},"2K":{"usd":0.14,"diem":0.14},"4K":{"usd":0.19,"diem":0.19}}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:1","8:1","4:5","3:4","2:3","9:16","1:4","1:8"],"promptCharacterLimit":32768,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"]},"supportsOptimizePromptThinking":false,"description":"Nano Banana 2 Edit uses Google's Gemini-based Nano Banana 2 to edit images from a text instruction, combining up to 6 input images at up to 4K with fast turnaround.","name":"Nano Banana 2","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1791244800,"id":"nano-banana-2-1-edit","model_spec":{"pricing":{"inpaint":{"usd":0.1,"diem":0.1},"resolutions":{"1K":{"usd":0.1,"diem":0.1},"2K":{"usd":0.14,"diem":0.14},"4K":{"usd":0.19,"diem":0.19}}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:1","8:1","4:5","3:4","2:3","9:16","1:4","1:8"],"promptCharacterLimit":32768,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"]},"supportsOptimizePromptThinking":false,"description":"Nano Banana 2.1 Edit uses Google's Gemini-based Nano Banana 2.1 to edit images from a text instruction, combining up to 6 input images at up to 4K with fast turnaround.","name":"Nano Banana 2.1","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1765584000,"id":"nano-banana-pro-edit","model_spec":{"pricing":{"inpaint":{"usd":0.18,"diem":0.18},"resolutions":{"1K":{"usd":0.18,"diem":0.18},"2K":{"usd":0.23,"diem":0.23},"4K":{"usd":0.35,"diem":0.35}}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:1","8:1","4:5","3:4","2:3","9:16","1:4","1:8"],"promptCharacterLimit":32768,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"]},"supportsOptimizePromptThinking":false,"description":"Nano Banana Pro Edit uses Google's Nano Banana Pro for high-quality edits from a text instruction, combining up to 6 input images at up to 4K.","name":"Nano Banana Pro","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1782777600,"id":"nano-banana-2-lite-edit","model_spec":{"pricing":{"inpaint":{"usd":0.06,"diem":0.06}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:1","8:1","4:5","3:4","2:3","9:16","1:4","1:8"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true},"supportsOptimizePromptThinking":false,"description":"Nano Banana 2 Lite Edit is Google's efficiency-focused image editor, built for fast multi-turn local edits with up to 6 input images.","name":"Nano Banana 2 Lite","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1781654400,"id":"luma-uni-1-edit","model_spec":{"pricing":{"inpaint":{"usd":0.06,"diem":0.06}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:3","4:5"],"promptCharacterLimit":6000,"combineImages":false,"singleImageAspectRatio":false},"supportsOptimizePromptThinking":false,"description":"Luma Uni-1 Edit makes text-guided edits with Luma AI's Uni-1 while preserving the structure of the source image.","name":"Luma Uni-1","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1781654400,"id":"luma-uni-1-max-edit","model_spec":{"pricing":{"inpaint":{"usd":0.13,"diem":0.13}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:3","4:5"],"promptCharacterLimit":6000,"combineImages":false,"singleImageAspectRatio":false},"supportsOptimizePromptThinking":false,"description":"Luma Uni-1 Max Edit makes text-guided edits at maximum fidelity with Luma AI's Uni-1, preserving the structure of the source image.","name":"Luma Uni-1 Max","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1794268800,"id":"minimax-h3-image-edit","model_spec":{"pricing":{"inpaint":{"usd":0.06,"diem":0.06},"resolutions":{"1K":{"usd":0.06,"diem":0.06},"2K":{"usd":0.06,"diem":0.06},"4K":{"usd":0.12,"diem":0.12}},"inputImages":{"included":1,"additional":{"usd":0.019374050000000004,"diem":0.019374050000000004}}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":16,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K","4K"]},"supportsOptimizePromptThinking":false,"description":"MiniMax H3 Image Edit changes an image from a text instruction and can combine up to 16 input images, rendering at up to 4K.","name":"MiniMax H3 Image","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1788393600,"id":"muse-image-edit","model_spec":{"pricing":{"inpaint":{"usd":0.02,"diem":0.02}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true},"supportsOptimizePromptThinking":false,"description":"Muse Image Edit is Meta's Muse Image in editing mode. It changes only what you ask and can compose from up to 6 reference images.","name":"Muse Image","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1771804800,"id":"seedream-v5-lite-edit","model_spec":{"pricing":{"inpaint":{"usd":0.05,"diem":0.05}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","9:16","2:3","3:4","4:5","4:3"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true},"supportsOptimizePromptThinking":false,"description":"Seedream V5 Lite Edit is the fast tier of ByteDance Seed's Seedream 5.0 for natural-language editing, with up to 6 input images.","name":"Seedream V5 Lite","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1783468800,"id":"seedream-v5-pro-edit","model_spec":{"pricing":{"inpaint":{"usd":0.06,"diem":0.06},"resolutions":{"1K":{"usd":0.06,"diem":0.06},"2K":{"usd":0.11,"diem":0.11}},"inputImages":{"included":1,"additional":{"usd":0.0034500000000000004,"diem":0.0034500000000000004}}},"constraints":{"aspectRatios":["auto","1:1","5:4","4:3","3:2","16:9","21:9","4:5","3:4","2:3","9:16","9:21"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"]},"supportsOptimizePromptThinking":true,"description":"Seedream V5 Pro Edit is the flagship tier of ByteDance Seed's Seedream 5.0 for natural-language editing, at 1K or 2K with up to 6 input images.","name":"Seedream V5 Pro","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1767484800,"id":"seedream-v4-edit","model_spec":{"pricing":{"inpaint":{"usd":0.05,"diem":0.05}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true},"supportsOptimizePromptThinking":false,"description":"Seedream V4.5 Edit is ByteDance Seed's Seedream 4.5 in editing mode, known for well-composed results from natural-language instructions, with up to 6 input images.","name":"Seedream V4.5","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1785888000,"id":"qwen-image-3-edit","model_spec":{"pricing":{"inpaint":{"usd":0.04,"diem":0.04},"resolutions":{"1K":{"usd":0.04,"diem":0.04},"2K":{"usd":0.04,"diem":0.04}},"inputImages":{"included":0,"additional":{"usd":0.0034500000000000004,"diem":0.0034500000000000004}}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":10000,"combineImages":true,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"]},"supportsOptimizePromptThinking":true,"description":"Qwen Image 3 Edit is the standard tier of Alibaba's Qwen Image 3.0 for natural-language editing, cost-efficient and able to use multiple reference images at 1K or 2K.","name":"Qwen Image 3","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1784160000,"id":"qwen-image-3-pro-edit","model_spec":{"pricing":{"inpaint":{"usd":0.05,"diem":0.05},"resolutions":{"1K":{"usd":0.05,"diem":0.05},"2K":{"usd":0.09,"diem":0.09}},"inputImages":{"included":0,"additional":{"usd":0.0034500000000000004,"diem":0.0034500000000000004}}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":10000,"combineImages":true,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"]},"supportsOptimizePromptThinking":true,"description":"Qwen Image 3 Pro Edit is the Pro tier of Alibaba's Qwen Image 3.0 for natural-language editing with multiple reference images, at 1K or 2K.","name":"Qwen Image 3 Pro","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1791504000,"id":"qwen-image-2-1-turbo-edit","model_spec":{"pricing":{"inpaint":{"usd":0.02,"diem":0.02},"resolutions":{"1K":{"usd":0.02,"diem":0.02},"2K":{"usd":0.02,"diem":0.02}}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":6,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"]},"supportsOptimizePromptThinking":true,"description":"Qwen Image 2.1 Turbo Edit is the fast tier of Alibaba's Qwen-Image 2.1 for editing: local edits, restyles and compositions from up to 6 input images at 1K or 2K.","name":"Qwen Image 2.1 Turbo","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1789862400,"id":"qwen-image-2-1-pro-edit","model_spec":{"pricing":{"inpaint":{"usd":0.05,"diem":0.05},"resolutions":{"1K":{"usd":0.05,"diem":0.05},"2K":{"usd":0.05,"diem":0.05}}},"constraints":{"aspectRatios":["auto","1:1","3:2","16:9","21:9","9:16","2:3","3:4","4:5"],"promptCharacterLimit":10000,"combineImages":true,"maxInputImages":10,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"]},"supportsOptimizePromptThinking":true,"description":"Qwen Image 2.1 Pro Edit is the full-capacity Qwen-Image 2.1 editor, handling local edits and compositions of people and products from up to 10 reference images at 1K or 2K.","name":"Qwen Image 2.1 Pro","modelSource":"https://www.alibabacloud.com/help/en/model-studio/models","offline":false,"privacy":"anonymized","traits":[],"uncensored":true},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1794873600,"id":"kling-v4-image-edit","model_spec":{"pricing":{"inpaint":{"usd":0.08,"diem":0.08},"resolutions":{"2K":{"usd":0.08,"diem":0.08},"4K":{"usd":0.12,"diem":0.12}},"inputImages":{"included":0,"additional":{"usd":0.0036800000000000005,"diem":0.0036800000000000005}}},"constraints":{"aspectRatios":["auto","1:1","16:9","9:16","4:3","3:4","3:2","2:3","21:9"],"promptCharacterLimit":32768,"combineImages":true,"maxInputImages":10,"singleImageAspectRatio":true,"defaultResolution":"2K","resolutions":["2K","4K"]},"supportsOptimizePromptThinking":false,"description":"Edits images from a text instruction. Refer to inputs as @Image1, @Image2, and so on. Accepts up to 10 images, at 2K and 4K.","name":"Kling Image 4.0","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1794873600,"id":"mai-image-2-7-edit","model_spec":{"pricing":{"inpaint":{"usd":0.06,"diem":0.06},"resolutions":{"1K":{"usd":0.06,"diem":0.06},"2K":{"usd":0.18,"diem":0.18}},"inputImages":{"included":1,"additional":{"usd":0.009430000000000003,"diem":0.009430000000000003}}},"constraints":{"aspectRatios":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"],"promptCharacterLimit":32000,"combineImages":true,"maxInputImages":5,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"],"supportsTransparentBackground":true},"supportsOptimizePromptThinking":false,"description":"Edits images from a text instruction with Microsoft's MAI Image 2.7. Accepts up to 5 images, at 1K and 2K.","name":"MAI Image 2.7","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1794873600,"id":"mai-image-2-7-flash-edit","model_spec":{"pricing":{"inpaint":{"usd":0.02,"diem":0.02},"resolutions":{"1K":{"usd":0.02,"diem":0.02},"2K":{"usd":0.06,"diem":0.06}},"inputImages":{"included":1,"additional":{"usd":0.00299,"diem":0.00299}}},"constraints":{"aspectRatios":["1:1","16:9","9:16","4:3","3:4","3:2","2:3"],"promptCharacterLimit":32000,"combineImages":true,"maxInputImages":5,"singleImageAspectRatio":true,"defaultResolution":"1K","resolutions":["1K","2K"],"supportsTransparentBackground":true},"supportsOptimizePromptThinking":false,"description":"Edits images from a text instruction with MAI Image 2.7 Flash, the faster, lower-cost variant of Microsoft's MAI Image 2.7. Accepts up to 5 images, at 1K and 2K.","name":"MAI Image 2.7 Flash","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"inpaint"},{"created":1760136444,"id":"nvidia/parakeet-tdt-0.6b-v3","model_spec":{"pricing":{"per_audio_second":{"usd":0.0001,"diem":0.0001}},"description":"Parakeet TDT 0.6B v3 is NVIDIA's open-weight speech recognition model, with 600 million parameters and support for 25 European languages, which it detects on its own. It transcribes quickly, with punctuation and capitalization.","name":"Parakeet ASR","modelSource":"https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"asr"},{"created":1736899200,"id":"openai/whisper-large-v3","model_spec":{"pricing":{"per_audio_second":{"usd":0.0001,"diem":0.0001}},"description":"Whisper Large V3 is OpenAI's open-weight speech recognition model, trained on about 5 million hours of audio and able to transcribe around 100 languages. It's a robust general-purpose choice for multilingual transcription.","name":"Whisper Large V3","modelSource":"https://huggingface.co/openai/whisper-large-v3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"asr"},{"created":1776384000,"id":"fal-ai/wizper","model_spec":{"pricing":{"per_audio_second":{"usd":0.0001,"diem":0.0001}},"description":"Wizper is an optimized deployment of OpenAI's Whisper Large V3, transcribing the same languages with faster turnaround. It accepts a language hint and returns segment timestamps.","name":"Wizper (Whisper v3)","modelSource":"https://huggingface.co/openai/whisper-large-v3","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"asr"},{"created":1776384000,"id":"elevenlabs/scribe-v2","model_spec":{"pricing":{"per_audio_second":{"usd":0.000167,"diem":0.000167}},"description":"ElevenLabs Scribe V2 is ElevenLabs' speech-to-text model, built for accurate transcription across many languages. It accepts a language hint and returns word-level timestamps with speaker labels.","name":"ElevenLabs Scribe V2","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"asr"},{"created":1776470400,"id":"stt-xai-v1","model_spec":{"pricing":{"per_audio_second":{"usd":0.000031480000000000004,"diem":0.000031480000000000004}},"description":"xAI Speech to Text v1 is xAI's speech recognition model, which transcribes recorded audio into text. It accepts a language hint and returns word-level timestamps.","name":"xAI Speech to Text v1","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"asr"},{"created":1789689600,"id":"jev-latest","model_spec":{"betaModel":true,"pricing":{"input":{"usd":0.042,"diem":0.042},"output":{"usd":0,"diem":0}},"maxStateTokens":32000,"maxTotalTokens":64000,"description":"Jev (System One) is TypeSafe AI's decision model. Instead of writing text, it answers typed questions about a passage with structured judgments: yes-or-no probabilities, choices with confidence, or scores on a rubric. It reads up to 32,000 tokens of context, with up to 64,000 tokens across context and questions.","name":"Jev (System One)","offline":false,"privacy":"anonymized","traits":[]},"object":"model","owned_by":"venice.ai","type":"decision"},{"created":1791244800,"id":"clef-api","model_spec":{"betaModel":true,"pricing":{"input":{"usd":0.05,"diem":0.05},"output":{"usd":0.05,"diem":0.05}},"maxStateTokens":32768,"maxTotalTokens":32768,"description":"Clef (System One) is Cloudflare's decision model. Like Jev, it answers typed questions about a passage with structured judgments rather than prose: probabilities, choices or rubric scores. It reads up to 32,768 tokens of context.","name":"Clef (System One)","offline":false,"privacy":"private","traits":[]},"object":"model","owned_by":"venice.ai","type":"decision"}],"object":"list","type":"all"}