Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is designed as an “uncensored” instruct-tuned LLM, preserving...
- Modalities
- text → text
- In / out per 1M
- Free / Free
- Context
- 33K tokens
- Added
- Jul 9, 2025
- Tokenizer
- Other
- Knowledge cutoff
- Apr 30, 2024
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | Free | — | Free |
| Output | Free | — | Free |
Providers
No provider breakdown is published for Uncensored (free) in the current catalog snapshot (Jul 28, 2026). Browse all providers
Supported parameters
- frequency_penalty
- max_tokens
- presence_penalty
- response_format
- stop
- structured_outputs
- temperature
- top_k
- top_p
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use
model cognitivecomputations/dolphin-mistral-24b-venice-edition:free.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"model": "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "cognitivecomputations/dolphin-mistral-24b-venice-edition:free",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);About Uncensored (free)
This is a fine-tuned Mistral-Small-24B-Instruct-2501 build, put together by dphn.ai with Venice.ai, aimed at instruct tasks without the usual refusal behavior baked into most chat models. It runs on Cognitive Computations' Dolphin approach — community fine-tunes across Llama, Mistral, and Qwen bases. Context window is 32,768 tokens, text-in/text-out only, no vision or reasoning mode. It supports structured outputs, response formatting, and standard sampling controls, so it slots into normal API workflows rather than needing special handling.
It's free — both provider price and OpenKey price are $0.00 per 1M tokens for input and output, one of 25 free models on OpenKey out of 329 total. Its 32,768-token context window sits above only 5% of catalog models, so most other models on the platform offer more room. Knowledge cutoff is April 30, 2024. No benchmark scores are published for it, and it has no sibling models listed under this lab on OpenKey.
Questions
- How much does Dolphin Mistral 24B Venice Edition (free) cost via API?
- It's free: $0.00 per 1M input tokens and $0.00 per 1M output tokens, both from the provider and through OpenKey. Since OpenKey's fee is 3% of provider list price, 3% of $0.00 is still $0.00 — there's no cost math to do here.
- Is Dolphin Mistral 24B Venice Edition free to use?
- Yes, it's fully free on OpenKey, with both prompt and completion pricing at $0.00 per 1M tokens. It's one of 25 free models currently available on the platform, out of 329 total models across 52 labs.
- What is Dolphin Mistral 24B Venice Edition's context window?
- The context window is 32,768 tokens. That's enough for a long document or a multi-turn conversation, though it ranks in just the bottom 5% of context sizes across the OpenKey catalog — most other models allow more.
- Does Dolphin Mistral 24B Venice Edition support structured outputs or tool calling?
- It supports structured outputs and response formatting, along with standard parameters like temperature, top_p, top_k, frequency_penalty, and presence_penalty. Tool/function calling is not listed among its supported parameters, so treat it as a plain text-completion model.
- What is Dolphin Mistral 24B Venice Edition's knowledge cutoff?
- Its knowledge cutoff is April 30, 2024. The model itself was released on July 9, 2025, as a fine-tune of Mistral-Small-24B-Instruct-2501, built by dphn.ai in collaboration with Venice.ai.