Model overview
What this model is for
Venice: Uncensored is a text-only, uncensored instruct model for developers who need conversational generation with fewer stated content restrictions. It is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. The source identifies uncensored behavior as its relevant capability, making it suitable for unrestricted or experimental text-generation use cases; no additional modalities, tool-calling support, agent features, or specialized capabilities are disclosed. OpenRouter lists a 128,000-token context window and a maximum output of 8,192 tokens. Pricing is listed at $0.20 per million input tokens and $0.90 per million output tokens. The model has 24 billion parameters, while no inference-speed benchmark or reported tokens-per-second figure is provided. Developers should verify whether the model’s behavior and output quality fit their application, since the supplied source does not provide benchmark results, safety documentation, or detailed operational guarantees. Licensing terms are not disclosed in the supplied source, so review the linked model documentation before deployment. The source page does not disclose a publication or update date, meaning its freshness cannot be independently established.