Mistral AI

The French platform: open models and a free tier to experiment with.

Mistral is the French lab behind the current Small and Medium line. Mixtral 8x7B retired from the API on 30 Mar 2025. The console still gives you a key on an email; Free mode and Labs are the no-card slice.

Context goes to 256K. Labs ids (labs- prefix) are free of charge; mistral-medium-3-5 is paid. Limits live per org in the console, not as a published “one request a second”. Use Small or a Labs model to try, not to ship.

Free models: 12
Max context: 256K
Free tier: Free mode and Labs
Requirement: Email account, no card

Endpoint

Base URLhttps://api.mistral.ai/v1

Env varMISTRAL_API_KEY

Rate limitPer-org caps in the console; Labs models are free of charge

OpenAI-compatible
Native SDK: Mistral SDK
text
image
code

Code examples

npm install openai

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.mistral.ai/v1',
  apiKey: process.env.MISTRAL_API_KEY
})

const response = await client.chat.completions.create({
  model: 'mistral-small-latest',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

pip install openai

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mistral.ai/v1",
    api_key=os.environ["MISTRAL_API_KEY"],
)

response = client.chat.completions.create(
    model="mistral-small-latest",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

curl https://api.mistral.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MISTRAL_API_KEY" \
  -d '{
    "model": "mistral-small-latest",
    "messages": [{"role": "user", "content": "Explain closures in one paragraph."}]
  }'

npm install @mistralai/mistralai

import { Mistral } from '@mistralai/mistralai'

const client = new Mistral({ apiKey: process.env.MISTRAL_API_KEY })

const response = await client.chat.complete({
  model: 'mistral-small-latest',
  messages: [{ role: 'user', content: 'Explain closures in one paragraph.' }]
})

console.log(response.choices[0].message.content)

pip install mistralai

import os
from mistralai import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

response = client.chat.complete(
    model="mistral-small-latest",
    messages=[{"role": "user", "content": "Explain closures in one paragraph."}],
)

print(response.choices[0].message.content)

Worth knowing

open-mixtral-8x7b retired on 30 Mar 2025. Use mistral-small-latest or a labs- id.
mistral-medium-3-5 is a paid model (256K). Free mode and Labs are the no-card slice.

Models you get for free12

Mistral Smallmistral-small-latest
Mistral Small 2506mistral-small-2506
Mistral Nemoopen-mistral-nemo
Codestralcodestral-latest
Pixtral 12Bpixtral-12b-2409
Labs Mistral Smalllabs-mistral-small
Mistral Embedmistral-embed
Mistral Moderationmistral-moderation-latest
Mistral OCRocr-latest
Mistral Small 3.1mistral-small-3.1-24b-instruct
Devstral Smalldevstral-small-latest
Magistral Smallmagistral-small-latest