# Free Codestral API Endpoints & Rate Limits

> 1 provider · 1 free model · Last updated: 29 Oct 2026

## Quick Answer

1 free Codestral API models across 1 provider including Mistral La Plateforme. Verified rate limits, context windows, and OpenAI-compatible endpoints. Last updated: 29 Oct 2026.

Mistral Codestral is available for free developer use on Mistral La Plateforme Experiment tier at 1 req/sec and 1 billion tokens per month.

## Quick Connect

Codestral endpoint with 1B free tokens/month on Experiment tier.

- **Base URL:** `https://api.mistral.ai/v1`
- **Model:** `Codestral`
- **Provider:** [Mistral La Plateforme](/providers/mistral-la-plateforme/)

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mistral.ai/v1",
    api_key="your-api-key",  # from Mistral La Plateforme
)

response = client.chat.completions.create(
    model="Codestral",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
```

## Rate Limits & Model Inventory

| Model | Provider | Cost | Context | RPM | TPM | RPD | Day tokens | Verified |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| Codestral | [Mistral La Plateforme](/providers/mistral-la-plateforme/) | $0 (Experiment) | Model-dependent | ~1 req/sec | Not published | Not published | ~1B tokens/month | 2026-10-29 |

Web page: https://freeinference.dev/free-codestral-api/
Machine-readable JSON: /data/providers.json
Agent summary: /llms.txt

Numbers cross-checked against official docs and live probes as of 2026-10-29. Limits change without notice — this is a map, not a contract.