Mistral AI · API pricing

Mistral API pricing

4 Mistral models on one OpenAI-compatible API, billed per token from a prepaid balance — no subscription. From €0.0252 per 100k input tokens and €0.0336 per 100k output tokens, margin and VAT included. All run on EU-sovereign infrastructure.

Models live
4
Input from
€0.0252
per 100k tokens
Output from
€0.0336
per 100k tokens
Largest context
512K
Mistral Large 4

Mistral API pricing per model

per 100k tokens · margin and VAT included · from our live catalog when this page is built

ModelInputOutputCached inContextMax outputJurisdiction
Mistral Small 3.2 24B
mistral-small-3.2-24btoolsvision
€0.0252€0.0588———EU sovereign
Mistral Small 4 119B
mistral-small-4-119btoolsvision
€0.0278€0.1109—256K—EU sovereign
Pixtral 12B
pixtral-12btoolsvision
€0.0336€0.0336—128K4KEU sovereign
Mistral Large 4
mistral-large-4toolsvision
€0.2514€0.7725€0.0259512K256KEU sovereign

Input, output and cached input are the prices debited from your prepaid balance per 100,000 tokens, margin and VAT included. Context is the window as served on Frontière AI; max output is the provider's cap on max_tokens (— when it sets none we know of). Tool calling is measured with a real call per model.

Where each Mistral model runs, and what Mistral's own API does with your data →

Mistral API cost calculator

Pick a model and a workload, or type your own token counts: the estimate uses the prices in the table above, margin and VAT included.

Example workload

Roughly 1,000 tokens ≈ 750 English words.

No discounted cache rate on this model: every input token is billed at the input rate.

Per request

€0.00058

Per day

€0.5838

Per month

€17.51

30 days

A €10 top-up covers about 17,129 requests · Mistral Small 3.2 24B

Where the money goes

  • Input€11.34 · 65%
  • Output€6.17 · 35%

Estimate, margin and VAT included, from the prices on this page. You are billed on the tokens the provider reports for each call, debited from a prepaid balance — no subscription.

Same workload on every model

ModelPer month
Mistral Small 3.2 24BEU sovereign€17.51Selected
Pixtral 12BEU sovereign€18.65
Mistral Small 4 119BEU sovereign€24.12
Mistral Large 4EU sovereign€194.21

Call Mistral models

The API is OpenAI-compatible: keep your SDK, change base_url and the key, and pass the model id. One key covers the whole catalog.

curl https://getfrontiereai.eu/api/v1/chat/completions \
  -H "Authorization: Bearer $FRONTIERE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-small-3.2-24b",
    "messages": [{"role": "user", "content": "Bonjour"}]
  }'
API reference →

Frequently asked

How much does the Mistral API cost?

On Frontière AI, Mistral models cost from €0.0252 to €0.2514 per 100,000 input tokens and from €0.0336 to €0.7725 per 100,000 output tokens, depending on the model — margin and VAT included, that is the amount debited from your prepaid balance. The table lists each model's price; the calculator turns it into a monthly cost for your workload.

Which Mistral model is the cheapest?

Mistral Small 3.2 24B is the cheapest on input (€0.0252 per 100k tokens), Pixtral 12B on output (€0.0336). Which costs less overall depends on your input/output ratio: the calculator compares them on your workload.

Which Mistral model has the largest context window?

Mistral Large 4, with 512K tokens of context as served on Frontière AI.

Is the Mistral API hosted in Europe on Frontière AI?

Yes: every live model is labeled EU sovereign — Scaleway (France) for Mistral Small 3.2 24B and Pixtral 12B and Mistral AI (France) for Mistral Small 4 119B and Mistral Large 4. Your prompts transit through our gateway, hosted by Vercel in Paris (a US company), without being stored.

Is there a subscription or a minimum spend?

No subscription. You top up a prepaid balance from €10 and each call is debited at the per-token price. Calls are refused once the balance reaches zero; a call already running can take it slightly below — deducted from your next top-up.

Do I need to change my code to call Mistral models?

No, if your code already uses an OpenAI SDK: point base_url at https://getfrontiereai.eu/api/v1, use a Frontière AI key and pass the model id, for example “mistral-small-3.2-24b”. Streaming and tool calling are relayed as-is.

How are cached input tokens billed?

Mistral Large 4 has a discounted rate for prompt tokens the provider serves from its cache (€0.0259 per 100k tokens on Mistral Large 4). The provider reports these tokens on each call and we bill them at that rate; on a model without a cache rate, every input token is billed at the input rate.

Other providers

Per-token prices for every publisher in our catalog

All model prices on one page →

Start calling Mistral in minutes

Create an account, top up €10, change two lines of code.

Create an account