Official Provider HubParis, France

Mistral AI API Pricing & Token Economics

Mistral AI offers high-performance frontier models including Mistral Large 3, Mistral Small 4, and Codestral. Leveraging their custom Tekken byte-pair tokenizer with a 131k vocabulary, Mistral models demonstrate exceptional token compression efficiency for code and European languages.

Official Mistral AI Pricing Docs API Reference

Prompt Caching Policy

Prompt caching supported on Large 3 ($0.15/1M cached) and Small 4 ($0.015/1M cached).

Batch / Asynchronous Rules

Standard API execution rules. Refer to individual endpoint rate limits for asynchronous processing.

Special Billing Conditions

Tekken tokenizer achieves ~30% higher compression on source code and non-English text.

Active Mistral AI Models(3 models verified)

All 30 Models →

Model	Context	Input / 1M	Cached / 1M	Output / 1M	Batch Discount	Actions
Mistral Large 3 mistral-large-2512	256k	$0.50	$0.05	$1.50	50% off	Specs →
Mistral Small 4 mistral-small-2603	256k	$0.15	$0.015	$0.60	50% off	Specs →
Codestral 2501 codestral-2501	256k	$0.20	$0.06	$0.60	N/A	Specs →

Calculate your monthly Mistral AI bill

Simulate prompt caching hit rates, batch discounts, and output token costs with zero server logging.

Open Cost Calculator →