Mistral AI · Fast · Updated 2026-11

Mistral Large 2 API Pricing & Cost Breakdown

Multilingual European workflows, EU data residency, and JSON function calling.

Input / 1M Tokens
$2.00
Cached Input / 1M
$2.000
Output / 1M Tokens
$6.00
Context Window
128K

Workload Cost Scenarios (30-Day Billing)

Strong French/German/Spanish/English coverage with EU hosting options.

Scenario In / Out per Req Uncached Monthly 50% Cache Hit Monthly
Hobby / Prototype (100 req/day) 1500 / 400 $16.20 $16.20
Growing Startup (2,500 req/day) 2500 / 700 $690.00 $690.00
Production Scale (50,000 req/day) 3000 / 800 $16,200.00 $16,200.00

Lower-Cost Alternative Models

Gemini 2.0 Flash ($0.40/1M out) Qwen 2.5 72B ($0.40/1M out) Grok 3 Mini ($0.50/1M out) GPT-4o mini ($0.60/1M out)

Frequently Asked Questions

What is Mistral Large 2 API pricing per 1M tokens?

Standard input is $2.00/1M, cached input is $2.000/1M, and output is $6.00/1M.

What is the context window of Mistral Large 2?

Mistral Large 2 supports a 128K token context window with up to 16,384 max output tokens.

How much does prompt caching save on Mistral Large 2?

Prompt caching reduces cached input token rates by 0% compared with uncached input.

What workloads is Mistral Large 2 best suited for?

Multilingual European workflows, EU data residency, and JSON function calling.