Free Mistral API
Mistral's free 'Experiment' tier: Large, Medium, Small, Codestral, Devstral and more.
FreeLLMAPI is a free, open-source LLM API that routes across every provider with a real free tier. The Mistral models below are on the free tier of Mistral — reachable through one OpenAI-compatible key, with automatic failover when a provider hits its rate limit.
Free Mistral models (7)
| Model | Context | Free limits | Capabilities |
|---|---|---|---|
| mistral-large-latest | 262K | 2 rpm | tools |
| mistral-medium-latest | 131K | 2 rpm | tools |
| mistral-small-latest | 262K | 2 rpm | tools |
| codestral-latest | 256K | 2 rpm | tools |
| devstral-latest | 262K | 2 rpm | tools |
| magistral-medium-latest | 131K | 2 rpm | tools |
| ministral-8b-latest | 262K | 2 rpm | tools |
How to use Mistral for free
- Install FreeLLMAPI — the open-source router (GitHub). It runs locally and keeps your keys on your machine.
- Add a free key for Mistral on the Keys page — no credit card required.
- Point your OpenAI client at the local endpoint and pick a model:
from openai import OpenAI
# FreeLLMAPI runs locally; grab your unified key + endpoint on the Keys page.
client = OpenAI(base_url="http://localhost:3001/v1", api_key="freellmapi-...")
resp = client.chat.completions.create(
model="mistral-large-latest",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
FAQ
Is the Mistral API really free?
Yes — these Mistral models run on genuine provider free tiers (on the free tier of Mistral). Inference costs nothing; you only add a free provider key.
Do I need a credit card?
No. The providers here offer free tiers that work without a card. You add the free key once and FreeLLMAPI routes to it.
How do I call Mistral through FreeLLMAPI?
Install the open-source router, add the provider's free key on the Keys page, then point any OpenAI SDK at your local endpoint — see the code sample above.