TokenTally

Mistral cost planning

Mistral Large 2 pricing

Need EU data residency or custom deployment? Mistral Large 2 pairs enterprise governance with competitive pricing.

Last pricing check: Mar 13, 2026

$4.00 per 1M prompt tokens$16.00 per 1M completion tokens128,000 token context

Why teams choose this model

EU-hosted knowledge copilots
Financial and legal assistants
Data-rich analytics bots
Open main calculator

Scenario planning

Realistic cost examples

Numbers use Mistral Large 2 pricing

European support copilot

Compliant chat assistant routing across languages.

Per request

$0.0184

Per month

$92.00

Tokens sent

11,000,000

1400 prompt tokens800 completion tokens5,000 requests/mo

Regulated analytics

In-datacenter agent summarizing BI dashboards + SQL.

Per request

$0.0144

Per month

$46.08

Tokens sent

5,760,000

1200 prompt tokens600 completion tokens3,200 requests/mo

Policy QA

Employees ask natural-language questions over internal policies.

Per request

$0.01

Per month

$75.00

Tokens sent

9,750,000

900 prompt tokens400 completion tokens7,500 requests/mo

Compare with

Anthropic

Claude Opus 4.6 Pricing Guide

Updated Mar 13, 2026

Google

Gemini 1.5 Pro Pricing Guide

Updated Mar 13, 2026

Google

Gemini 2.5 Pro Pricing Guide

Updated Mar 13, 2026

FAQs

Can I self-host Mistral Large 2?

Yes. Mistral offers deployment options beyond the hosted API. Token pricing here reflects the default hosted tier.

How do I handle multi-lingual prompts?

Token counts vary by language. TokenTally’s counter keeps you honest even when prompts mix French, German, or English.

Does Large 2 have tool calling?

Yes—tool calls still tally tokens like any other output.

Pricing sources