Mistral Large 3 API Pricing & Cost Calculator

Q: Does Mistral Large 3 support prompt caching?

Yes, Mistral offers a 90% discount on cached input tokens, reducing the input price to $0.05 per million for matches.

Mistral Large 3 is Mistral's flagship frontier model, offering robust multilingual reasoning and advanced agentic features.

Input tokens

100,000

50% cached

Output tokens

5,000

per request

Volume

100 / monthly

Standard API

Cost Comparison

Based on 100,000 input tokens (50% cached), 5,000 output tokens, and 100 requests.

Mistral Large 3

$3.75

Gemini 3.5 Flash

$5.25

Claude Haiku 4.5

$8.00

Gemini 3.1 Pro (<=200k)

$17.00

GPT-5.4

$21.25

Claude Sonnet 4.6

$24.00

Claude Opus 4.7

$40.00

GPT-5.5

$42.50

Open full calculator to adjust tokens, caching, or add other models

How this is calculated

Mistral Large 3 is priced at $0.50 per million input tokens and $2.00 per million output tokens, supporting a 90% caching discount ($0.05 per million) and a 50% batch discount ($0.25 per million inputs, $1.00 per million outputs).

Verdict

Mistral Large 3 is the ideal solution for European-hosted enterprise tasks. Its competitive pricing and 90% cache discount keep high-intelligence workloads highly economical.