# Uncensored

> Uncensored is an open-weight language model from Cognitivecomputations, released on 9 Jul 2025. It accepts text and generates text, with a 128K-token context window and up to 8K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $0.20 per million input tokens and $0.90 per million output tokens (OpenRouter), across 1 provider we track.

Source page: https://www.aimodel.directory/models/dolphin-mistral-24b-venice-edition
Last verified: 4 Oct 2026

## Specifications

- **Developer:** Cognitivecomputations
- **Release date:** 9 Jul 2025 (source: OpenRouter, https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition)
- **Status:** Generally available
- **Weights:** Open weights (source: Hugging Face, https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition)
- **License:** apache-2.0 (source: Hugging Face, https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition)
- **Parameters:** 24B (source: Hugging Face, https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition)
- **Context window:** 128K (128,000 tokens) (source: OpenRouter, https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition)
- **Max output:** 8K tokens (source: OpenRouter, https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition)
- **Knowledge cutoff:** 30 Apr 2024 (source: OpenRouter, https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition)
- **Input:** Text (source: OpenRouter, https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition)
- **Output:** Text (source: OpenRouter, https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition)
- **Reasoning mode:** No (source: OpenRouter, https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition)
- **Tool calling:** No (source: OpenRouter, https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition)
- **Structured output:** No (source: OpenRouter, https://openrouter.ai/cognitivecomputations/dolphin-mistral-24b-venice-edition)
- **Hugging Face:** cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition (source: Hugging Face, https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $0.20 | $0.90 | – | 128K |

## FAQ

### What is the context window of Uncensored?

Uncensored has a context window of 128,000 tokens (128K) and can generate up to 8,192 tokens in a single response, according to OpenRouter.

### How much does the Uncensored API cost?

Uncensored is listed from $0.20 per million input tokens and $0.90 per million output tokens (OpenRouter). Prices last verified 4 Oct 2026.

### Is Uncensored open source?

Uncensored is an open-weight model: its weights are published on Hugging Face as cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition under the apache-2.0 license. Check the license terms before commercial use.

### When was Uncensored released?

Cognitivecomputations released Uncensored on 9 Jul 2025, according to OpenRouter.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "Uncensored", https://www.aimodel.directory/models/dolphin-mistral-24b-venice-edition