50 models7 providersprices scraped nightly — no estimates
mistralai · mistral familyVerified May 18, 2026

Mistral Large 2

123B params · 131K context · mistral-research · released 2024-07 · 2 providers

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.

Cheapest right now
OpenRouter$5.40/1M out
sticky while scrolling · verified May 18, 2026
Cheapest now
$5.40
OpenRouter · unknown · $/1M out
90-day price Δ
cheapest-host trend
Fastest TTFT
no data
Providers
2
indexed providers
✓ verified May 18, 2026
#Provider$/1M in$/1M outTTFT p50tok/sQuant
1OpenRouterCHEAPEST$1.80$5.40unknowngo ↗
2Cerebras Inferencefp16go ↗

Prices verified May 18, 2026 by scraping 2 providers. Methodology · Raw data