HomeAPIs › Mistral

Mistral API — pricing, free tier & how to get a key

Mistral AI is the leading European LLM provider, with open-weight roots and a competitive hosted API. It runs Mistral Large (flagship), Mistral Small (cheap, fast) and Codestral (code), offers a real free tier, and is a popular choice for teams that want an EU-based alternative. Here's what it costs and how to get your key.

Mistral API pricing (reference, June 2026)

ModelInput $/1MOutput $/1MBest for
Mistral Large$2.00$6.00Flagship reasoning, quality
Mistral Small cheapest$0.20$0.60High volume, simple tasks
Codestral$0.30$0.90Code completion & generation
⚠️ Reference prices, June 2026 — Mistral updates pricing regularly. Confirm on mistral.ai/pricing before budgeting. Prices are per 1M tokens; output is billed separately and costs more.

→ Estimate your bill on the AI API cost calculator or model a whole app with the AI app cost estimator.

Is there a free tier?

Yes — Mistral's la Plateforme includes a free experiment tier with rate limits, good for testing and low-volume apps, with no upfront cost. For production volume you switch to pay-as-you-go. It's one of the few capable providers with both a genuine free tier and EU data hosting — see also Google Gemini for another real free quota.

How to get a Mistral API key (step by step)

1. Go to console.mistral.ai (la Plateforme) and create an account.
2. Open the API Keys page and click Create new key; copy it once.
3. Stay on the free experiment tier, or add billing under Workspace → Billing for higher limits.
4. The API is OpenAI-style; most OpenAI SDKs work with the Mistral base URL and key.

Test it with a simple request:

# quick test (replace $MISTRAL_API_KEY)
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":"hi"}]}'

Estimate your cost

Use the AI API Cost Calculator to plug in your token counts and request volume — it ranks Mistral against GPT-4o, Claude, Gemini and DeepSeek from cheapest to most expensive for your workload.

Cheaper alternatives

For the lowest cost on simple tasks, Mistral Small already competes with GPT-4o mini and Gemini Flash. If you want even cheaper, DeepSeek-V3 undercuts most providers. For frontier quality, compare Mistral Large with GPT-4o and Claude Sonnet.

FAQ

Does Mistral have a free tier?

Yes — the la Plateforme free experiment tier has rate limits and no upfront cost, suitable for testing and low-volume use.

How much does Mistral Large cost?

Around $2 input / $6 output per 1M tokens (reference, June 2026). Mistral Small is far cheaper at ~$0.20/$0.60.

How do I get a Mistral API key?

Sign up at console.mistral.ai, open API Keys, create a key, copy it once, and use the free tier or add billing.

Is Mistral good for code?

Yes — Codestral is purpose-built for code completion and generation, at ~$0.30/$0.90 per 1M tokens.

Not affiliated with Mistral AI. Prices are reference estimates — always verify on the official pricing page.