Mistral Large 2 — pricing, providers, and benchmarks
Mistral Large 2 is Mistral AI's flagship dense model — 123B parameters, 128K context, released July 2024 — positioned as a Llama 3.1 405B competitor at lower hosting cost. Pricing on hosted providers typically lands at $1.50–$2.00 per 1M input tokens and $4.00–$6.00 per 1M output, reflecting its premium positioning. Worth the premium over a 70B model when you need consistently strong instruction-following, multilingual support across European languages, or precise structured output. Notably licensed under the Mistral Research License (non-commercial by default; commercial use requires a paid license from Mistral directly), so check terms before deploying through a third-party provider for commercial use.
Provider pricing
Sorted by total monthly cost for 100M input + 10M output tokens.
| Provider | Input / 1M | Output / 1M | Monthly cost | Context |
|---|---|---|---|---|
| OpenRouter | $1.8000 | $5.4000 | $234.00 | 131k |
Frequently asked questions
How much does it cost to run Mistral Large 2 for 100M tokens?▾
Running Mistral Large 2 with 100M input and 10M output tokens per month costs approximately $234.00 on OpenRouter, the cheapest available provider as of the latest pricing data. Costs vary significantly depending on your input/output ratio and whether you use prompt caching.
What is the cheapest provider for Mistral Large 2?▾
OpenRouter currently offers Mistral Large 2 at the lowest total cost for a standard workload. Prices change frequently — check the table above for the latest data.
What context window does Mistral Large 2 support?▾
Mistral Large 2 supports a context window of 131,072 tokens. Individual providers may cap this lower — see the pricing table for per-provider context limits.