Dolphin Mistral 24B Venice Edition is described as a collaborative project with Venice.ai aimed at creating the most uncensored version of Mistral 24B for use within the Venice ecosystem. It is also described as live on Venice as “Venice Uncensored,” the new default model for Venice users.
| Developer | Venice |
|---|---|
| Model ID | cognitivecomputations/dolphin-mistral-24b-venice-edition |
| Context Window | 128,000 tokens (~128K) |
| Modalities | Image, Text → Text |
| Capabilities | file input, parallel tool calls, reasoning, streaming, structured (JSON schema) output, tool/function calling, vision, web search |
Collaborative project
The model is presented as a collaboration with Venice.ai.
Uncensored positioning
It is described as the most uncensored version of Mistral 24B for use within the Venice ecosystem.
Venice product name
On Venice, it is shown as “Venice Uncensored.”
Default model on Venice
The model is described as the new default model for all Venice users.
Use within Venice ecosystem
The model is intended for use within the Venice ecosystem.
Default chat model on Venice
It is described as the default model for Venice users, indicating general conversational use on the platform.
Mistral 24B
The model is described as a version of Mistral 24B.
Sources: https://huggingface.co/dphn/Dolphin-Mistral-24B-Venice-Edition · https://venice.ai/blog/introducing-dolphin-mistral-24b-venice-edition-the-most-uncensored-ai-model-yet · https://developer.puter.com/ai/cognitivecomputations/dolphin-mistral-24b-venice-edition/
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Creative writing and screenwriting requiring unfiltered character dialogue, conflict, or mature themes.
Academic and historical research into sensitive, controversial, or taboo topics without system refusals.
Roleplay and interactive storytelling where the user defines the exact boundaries and character alignments.
Drafting complex arguments or exploring philosophical dilemmas from multiple, non-standard perspectives.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "cognitivecomputations/dolphin-mistral-24b-venice-edition", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "cognitivecomputations/dolphin-mistral-24b-venice-edition", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"cognitivecomputations/dolphin-mistral-24b-venice-edition","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
Free access is listed for `cognitivecomputations/dolphin-mistral-24b-venice-edition:free`, but the exact model itself is documented as paid at $0.20 per 1M input
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Venice Uncensored This page | Agentic workflows and structured output | |||
| Reasoning + agents |
Venice Uncensored has a 128,000 tokens context window.
Venice Uncensored takes image, text as input and returns text.
Use cognitivecomputations/dolphin-mistral-24b-venice-edition as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Venice Uncensored is priced at input $0.27508 / 1M tokens, output $1.23786 / 1M tokens.
Yes, Venice Uncensored can stream responses as they are generated.
Yes, Venice Uncensored accepts image input alongside text.
It is an uncensored, instruction-tuned chat model that follows system prompts closely and responds without built-in content refusals.
