Mistral Large 2 token cost & pricing
Mistral Large 2 is the European frontier option, at $2 per million input and $6 per million output. Its differentiators are strong multilingual performance, solid function calling and EU-based data handling, which matters for regulated industries.
Mistral Large 2 specifications
| Vendor | Mistral |
|---|---|
| Input price | $2 / 1M tokens |
| Output price | $6 / 1M tokens |
| Context window | 128,000 tokens |
| Max output | 32,768 tokens |
| Open weights | No |
| Price rank | 11 of 17 (cheapest first) |
| Best for | multilingual, eu |
What Mistral Large 2 costs in practice
Four common workloads, priced at list rates. Monthly figures assume 30 days.
| Workload | Per request | Requests/day | Per month |
|---|---|---|---|
| Chatbot · 1K in / 500 out | $0.0050 | 10,000 | $1,500 |
| RAG Q&A · 8K in / 400 out | $0.02 | 5,000 | $2,760 |
| Doc summary · 30K in / 1K out | $0.07 | 1,000 | $1,980 |
| Code agent · 60K in / 3K out | $0.14 | 500 | $2,070 |
How many requests does $100 buy?
Assuming a 1,000-token prompt and a 500-token response per request.
How Mistral Large 2 pricing actually works
A 3x input-to-output ratio, which is gentler than most of this table. Absolute prices sit between Gemini 2.5 Pro and Claude Sonnet 4.5. For EU teams facing data-residency requirements, the compliance value often outweighs the per-token gap.
When to use Mistral Large 2
Choose it for multilingual European-language products, function-calling agents, and any deployment where data must stay in the EU. For English-only workloads at scale, cheaper models usually win on pure economics.
How to cut your Mistral Large 2 bill
Keep prompts in the target language rather than translating to English first — Mistral handles European languages natively, and a translation round-trip can double your token count for no quality gain.
Cheaper alternatives to Mistral Large 2
- Qwen3 MaxAlibaba10% cheaper
- Claude Haiku 4.5Anthropic25% cheaper
- Kimi K2Moonshot61% cheaper
- Gemini 2.5 FlashGoogle65% cheaper
Run the numbers on your own prompt
Paste your actual text into the token counter to get an exact count instead of an estimate. Nothing is uploaded.
Open the calculator →