Mistral model prices on OpenRouter: input and output per million tokens

26 models from Mistral are under observation; 26 have both prices as of . Lowest output price: Mistral Nemo at $0.03 per 1M tokens. Methodology · Source: AI model API price records

Subscription limits · Terms tracker · Model prices · What's new

All providers

What typical tasks cost with these models

ModelChat: 1,000 repliesSummaries: 100 documentsCoding: one working day
Mistral Large 3 2512$0.95$0.27$0.84

Calculated at the model provider's own API price. For the same tasks through OpenRouter and on other models, see LLM API pricing comparison by task.

Not building on an API? Ready-made AI tools for writing, speech and images charge per month or per credit instead of per token: AI tool prices and the usage each plan includes.

ModelInput per 1M tokensOutput per 1M tokensContext (tokens)Listed since
Mistral: Mistral Nemo$0.03$0.03131,072Jul 19, 2024
Mistral: Mistral Small 3$0.05$0.0832,768Jan 30, 2025
Mistral: Ministral 3 3B 2512$0.10$0.10131,072Dec 2, 2025
Mistral: Ministral 3 8B 2512$0.15$0.15262,144Dec 2, 2025
Mistral: Ministral 3 14B 2512$0.20$0.20262,144Dec 2, 2025
Mistral: Mistral Small 3.2 24B$0.09$0.25256,000Jun 20, 2025
Mistral: Voxtral Small 24B 2507$0.10$0.3032,768Oct 30, 2025
Mistral: Mistral Small 3.1 24B$0.35$0.56128,000Mar 17, 2025
Mistral: Mistral Small 4$0.15$0.60262,144Mar 16, 2026
Mistral: Saba$0.20$0.6032,768Feb 17, 2025
Mistral: Codestral 2508$0.30$0.90256,000Aug 1, 2025
Mistral: Mistral Large 3 2512$0.50$1.50262,144Dec 1, 2025
Mistral: Devstral 2 2512$0.40$2.00262,144Dec 9, 2025
Mistral: Mistral Medium 3$0.40$2.00131,072May 7, 2025
Mistral: Mistral Medium 3.1$0.40$2.00131,072Aug 13, 2025
Mistral: Mistral Large 4$0.68$2.091,048,576Oct 6, 2026
Mistral Large$2.00$6.00128,000Feb 26, 2024
Mistral Large 2407$2.00$6.00131,072Nov 19, 2024
Mistral: Mixtral 8x22B Instruct$2.00$6.0065,536Apr 17, 2024
Mistral: Mistral Medium 3.5$1.50$7.50262,144Apr 30, 2026

Batch variants (6)

OpenRouter lists these as separate batch variants at a different price; batch requests are not answered right away, so these prices are kept apart from live prices.

ModelInput per 1M tokensOutput per 1M tokensContext (tokens)Listed since
Mistral: Ministral 3 8B 2512 (batch)$0.08$0.08262,144Dec 2, 2025
Mistral: Mistral Small 4 (batch)$0.08$0.30262,144Mar 16, 2026
Mistral: Codestral 2508 (batch)$0.15$0.45256,000Aug 1, 2025
Mistral: Mistral Large 3 2512 (batch)$0.25$0.75262,144Dec 1, 2025
Mistral: Mistral Medium 3.1 (batch)$0.20$1.00131,072Aug 13, 2025
Mistral: Mistral Medium 3.5 (batch)$0.75$3.75262,144Apr 30, 2026

Unknown means no value was recorded at our latest check; it is never shown as zero. Prices in USD as OpenRouter lists them; we do not add taxes.

How these numbers are produced

Each row is one model at one provider in our ai-models section. Prices are the input and output prices per one million tokens from the latest check of that model; the context length is the value read on the same pass. The table is sorted by our latest output price, lowest first; rows without an output price come last. The order is by price only.

A provider gets its own page when we track at least 5 of its models.

Each model links to its page with dates, the source link and the full history.