Mistral makes some of the best open-weight models available. Getting an API key takes about two minutes, and you don't need a credit card.
Prerequisites
You need:
- An email address
- A phone number that can receive SMS (for verification)
No credit card required for the free Experiment plan.
On the free Experiment plan, your API requests may be used to train Mistral's models. Upgrade to a paid plan if you're working with sensitive data.
How to generate your Mistral API key (step by step)
- Go to console.mistral.ai and create an account
- Verify your phone number when prompted. This is how Mistral gates the free tier
- Once inside the console, navigate to API Keys in the left sidebar
- Click Create new key, give it a name, and hit confirm
- Copy the key immediately and store it somewhere safe. Mistral won't show it again
Mistral API rate limits on the free plan
On the free Experiment plan, every model is capped at 500,000 tokens per minute and 1,000,000,000 tokens per month. The monthly cap is misleading - the per-minute limit is what you'll actually hit.
The per-minute limit is the one that matters. 500k tokens per minute = ~375,000 words per minute. That's fast, but concurrent requests will saturate it quickly. If a request gets rate limited, the API returns a 429 and you'll need to retry with backoff.
The monthly cap of 1B tokens is practical for individual use. At typical usage, most developers won't come close. If you're building something at scale or need guaranteed throughput, upgrading to the Scale plan removes these ceilings and adds data isolation.
Mistral API pricing: how much does it cost
Mistral charges per million tokens, counting both input (what you send) and output (what comes back). There's no subscription fee on the API side. You pay for what you use.
| Model | Input | Output |
|---|---|---|
| Mistral Small 3.2 | $0.10 / M tokens | $0.30 / M tokens |
| Mistral Large 3 | $0.50 / M tokens | $1.50 / M tokens |
A million input tokens ≈ 750,000 words or 1,500 pages. At Mistral Small's rates, that's $0.10. Most individuals and small teams won't notice the bill.
If you're running batch jobs that don't need an immediate response, Mistral offers a 50% discount. Use it if latency isn't a concern.
Choosing a Mistral model
Use mistral-small-latest by default.
It's fast, cheap, multimodal, multilingual, and Apache 2.0 licensed - no usage restrictions, no fees. This matters if you're building commercial software.
Use mistral-large-latest for complex multi-step tasks, nuanced analysis, or cases where output quality justifies the cost. It's five times the price of Small.
Adding your API key to your project
Set it as an environment variable so it never gets hardcoded into your source files:
export MISTRAL_API_KEY="your-key-here"
Test it with a curl call:
curl https://api.mistral.ai/v1/chat/completions \
-H "Authorization: Bearer $MISTRAL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistral-small-latest",
"messages": [{"role": "user", "content": "Hello"}]
}'
A JSON response with a choices array means the key is working. A 401 means the environment variable isn't set correctly.
For Python projects, use python-dotenv to load a .env file at runtime:
from dotenv import load_dotenv
import os
load_dotenv()
api_key = os.getenv("MISTRAL_API_KEY")
Use your Mistral API key in Char for AI meeting notes that stay on your device
Getting your own API key is a deliberate choice. It means you want control over what AI you're using and what happens to the data you send it. Char works on the same principles.
It's an open-source AI notepad for meetings that gives you complete control over your AI stack and your data.
The workflow is simple: record, transcribe locally, summarize with your own Mistral key. You choose which model runs. You can swap to Anthropic, OpenAI, or a local Ollama model any time without losing your files or your history.
Everything else stays local. The audio file, the transcript, the summary are all saved as plain markdown files on your device, not on Char's servers. Char doesn't have servers storing your conversations. There's nothing to breach, no vendor to trust with your data.
Plus, all core features, local transcription, and BYOK stay completely free. You're already paying for the API key, you shouldn't have to pay twice. But if you want cloud services and don't want to manage keys at all, there is a $8/month plan you can check out.
To connect Mistral, open Char's settings, go to API Keys, paste your key, and that's it. Try it out for free now - Download Char for macOS.
