Mistral AI · Fast · Updated 2026-11-22

Mistral Large 4 API Pricing & Cost Breakdown

Multilingual European workflows, EU compliance, and affordable 1M-context reasoning.

Input / 1M Tokens
$0.70
Cached Input / 1M
$0.070
Output / 1M Tokens
$2.10
Context Window
1.05M

Workload Cost Scenarios (30-Day Billing)

Cached input rate $0.07/1M (90% off); Batch API offers 50% discount.

Scenario In / Out per Req Uncached Monthly 50% Cache Hit Monthly
Hobby / Prototype (100 req/day) 1500 / 400 $5.67 $4.25
Growing Startup (2,500 req/day) 2500 / 700 $241.50 $182.44
Production Scale (50,000 req/day) 3000 / 800 $5,670.00 $4,252.50

Compare Mistral Large 4 Against Alternatives

Lower-Cost Alternative Models

GPT-6 Luna ($0.50/1M out) Claude Haiku 5.5 ($0.50/1M out) DeepSeek V4.1 Flash ($0.60/1M out) Llama 4 Maverick ($1.00/1M out)

Frequently Asked Questions

What is Mistral Large 4 API pricing per 1M tokens?

Standard input is $0.70/1M, cached input is $0.070/1M, and output is $2.10/1M.

What is the context window of Mistral Large 4?

Mistral Large 4 supports a 1.05M token context window with up to 262,144 max output tokens.

How much does prompt caching save on Mistral Large 4?

Prompt caching reduces cached input token rates by 90% compared with uncached input.

What workloads is Mistral Large 4 best suited for?

Multilingual European workflows, EU compliance, and affordable 1M-context reasoning.