Skip to content
OpenKey

Ministral 3 3B 2512

Mistral AIReleased Dec 2, 2025

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

Try in playground
Context window
131K tokens
Input
text, image
Output
text
Tokenizer
Mistral
Released
Dec 2, 2025

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.100$0.0030$0.103
Output$0.100$0.0030$0.103
Cache read$0.010$0.0003$0.010

Benchmarks

Artificial Analysis

Intelligence index
6.8
Coding index
4.8
Agentic index
1.6

Design Arena

CategoryEloWin rateRank
3Dmodels104035.9%#87
Codemodels106037.3%#88
Game devmodels101433%#96
Websitesmodels107038.2%#89

Head-to-head preference voting. How we filter and rank

Supported parameters

  • frequency_penalty
  • logprobs
  • max_tokens
  • presence_penalty
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model mistralai/ministral-3b-2512.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/ministral-3b-2512",
    "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="mistralai/ministral-3b-2512",
    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: "mistralai/ministral-3b-2512",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Ministral 3 3B 2512 cost via API?
Through OpenKey, Ministral 3 3B 2512 costs $0.103 per 1M input tokens and $0.103 per 1M output tokens. That is the provider price ($0.100 / $0.100) plus a flat 3% fee — nothing else.
What is Ministral 3 3B 2512's context window?
Ministral 3 3B 2512 accepts up to 131K tokens of context.
Is Ministral 3 3B 2512 OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "mistralai/ministral-3b-2512" using any OpenAI SDK — only the base URL and API key change.
What inputs does Ministral 3 3B 2512 support?
Ministral 3 3B 2512 accepts text, image input and produces text output.

More from Mistral AI

All Mistral AI models →