Uncensored
Venice Uncensored Dolphin Mistral 24B is a text-based language model developed by dphn.ai in collaboration with Venice.ai. It is a fine-tuned version of Mistral-Small-24B-Instruct-2501 designed to operate without standard content restrictions. The model supports a large context window of 128,000 tokens for processing extensive text inputs.
Uncensored specs and pricing
- Provider: Venice
- Released: July 9, 2025
- Context window: 128K tokens
- Max output: 8K tokens
- Input: text
- Output: text
- Price: $0.20 input / $0.90 output per 1M tokens
What Uncensored is good at
- Generating text without content filtering
- Processing long-form documents or transcripts
- Creative writing and open-ended text generation
To-dos to try with Uncensored
- Analyze this 50,000-word manuscript and summarize the character arcs.
- Draft a story based on these specific plot points without applying content filters.
- Review this long technical report and extract all mentioned historical dates.
FAQ
- What does it mean that this model is uncensored? The model is an instruct-tuned LLM designed to operate without the standard content restrictions typically found in other AI models.
- Who developed this model? It was developed by dphn.ai in collaboration with Venice.ai as a fine-tuned variant of the Mistral-Small-24B-Instruct-2501 model.
- How much does Uncensored cost? Uncensored costs $0.20 per million input tokens and $0.90 per million output tokens through OpenRouter. In todo.is a typical agent step costs about 0.69 credits ($1 = 100 credits).
- What is the context window of Uncensored? Uncensored can read up to 128K tokens at once and write up to 8K tokens in one reply.
- Can I use Uncensored without coding? Yes. In todo.is you pick Uncensored as your agent's model and write to-dos in plain words, on the web, the Android app, WhatsApp or Telegram. No API key needed: credits are included, or you can bring your own key.
JavaScript is required to use the todo.is app.