Access 1 venice model through the OpenRouter unified API including Uncensored. Compare pricing, context windows, benchmarks, and capabilities between different venice models.
venice tokens processed on OpenRouter
OpenRouter serves 1 venice model behind one OpenAI-compatible API. Create an OpenRouter API key, point your client at https://openrouter.ai/api/v1, and set the model to an ID such as cognitivecomputations/dolphin-mistral-24b-venice-edition. The quickstart has request examples for every supported SDK.
Uncensored has the largest context window of any venice model on OpenRouter, accepting up to 128,000 tokens per request.
Uncensored is the most recently added venice model on OpenRouter, listed on July 9, 2025.