aiapicostcalcUnit economicsPricesBrandsCompareBenchmarksSkills & PluginsFind my modelGuidesChanges

Mistral API pricing: all 6 models, cheapest first

Mistral lists 6 Mistral models with a price on its official API pricing page, from Ministral 3 3B at $0.1 input and $0.1 output per 1M tokens to Mistral Large 4 at $0.7 and $2.1 per 1M. Every rate below is checked 2026-11-18, links to its model page and names the official source.

Last verified 2026-11-18 · Sources: Mistral pricing page, checked 2026-11-18 · Report an error

By Shangyi Duan · Reviewed against the Mistral pricing page

All 6 Mistral models, cheapest first

ModelInput /1MCached /1MOutput /1M1,000 calls (10K in / 1K out)Checked
Ministral 3 3B$0.1–$0.1$0.00112026-11-15
Ministral 3 8B$0.15–$0.15$0.001652026-11-15
Mistral Small 4$0.15–$0.6$0.00212026-11-15
Ministral 3 14B$0.2–$0.2$0.00222026-11-15
Codestral 25.08$0.3–$0.9$0.00392026-11-15
Mistral Large 4$0.7$0.07$2.1$0.00912026-11-15

Prices are the standard list rate per 1M tokens on the official Mistral pricing page, checked 2026-11-18. The 1,000-call column uses a 10,000-input / 1,000-output workload with no caching; price your own token shape in the Mistral calculator.

What the price range means

Across the 6 Mistral models priced here, 1M input tokens cost $0.1 to $0.7 (a 7.0x spread) and 1M output tokens cost $0.1 to $2.1. The cheapest input rate is Ministral 3 3B at $0.1 per 1M; the highest is Mistral Large 4 at $0.7. At a 10,000-input / 1,000-output workload the cheapest model here costs $0.0011 per 1,000 calls and the most expensive costs $0.0091.

Input and output are priced separately, so the order changes with the workload: a model with a low input rate climbs a RAG-style table, while a model with a low output rate climbs a long-answer table. The table above holds one fixed shape (10,000 in / 1,000 out) so the rows are directly comparable; price your own shape in the Mistral API cost calculator or the homepage calculator.

1 of the 6 models list a separate cached-input rate; where a model does not, this table reuses its standard input rate and shows a dash.

How Mistral bills tokens

Mistral publishes a per-token list price for every model in the table: input, output and, for 1 of them, a cheaper cached-input rate. The rate applies per 1M tokens; the method page explains how a price is read from the official page and what happens when one cannot be verified.

Batch requests are billed at half the standard rate for 6 of these models (Ministral 3 3B, Ministral 3 8B, Mistral Small 4, Ministral 3 14B and others). Batch only pays off for work nobody is waiting on.

Context windows run from 128K tokens on Codestral 25.08 to 1000K on Mistral Large 4. A request larger than the window is rejected, so a long-document workload has to be split or moved to a larger-context model; that changes the number of calls, not just the rate.

Which Mistral model to price first

Start with the cheapest model that passes your own test, not with the most expensive one. Ministral 3 3B has the lowest input rate in this lineup at $0.1 per 1M tokens; if its answers hold up on your prompts, moving a workload down to it is usually worth more than any caching or batch tweak. If it fails, step up one row at a time in the table above and re-run the same prompts, so the quality difference you pay for is one you can see.

Cost per call is not the same as cost per finished task: a cheaper model that needs two attempts, a longer prompt or manual fixes costs more than its rate suggests. The benchmark comparison puts measured scores next to these prices, and the coding-cost ranking prices completed coding tasks rather than single calls.

Related

Questions

How many Mistral models does this page price?

This page prices 6 Mistral models, every one copied from the official Mistral pricing page and checked 2026-11-18. Each row links to a per-model page with the full rate tiers, worked examples and the source URL, so a number here can always be traced back.

Does Mistral charge less for cached input tokens?

Yes. 1 of the 6 models list a cached-input rate below the standard input rate; the cheapest cached read here is $0.07 per 1M tokens. Cached pricing only applies to a repeated prefix the provider has stored, so the saving depends on how much of your prompt is identical between calls.

Which Mistral model is cheapest per 1M tokens?

Ministral 3 3B has the lowest input rate at $0.1 per 1M tokens and $0.1 per 1M output tokens. At a 10,000-input / 1,000-output workload the cheapest model is Ministral 3 3B at $0.0011 per 1,000 calls, while Mistral Large 4 at $0.7/$2.1 carries the highest input rate in this lineup.

Which Mistral model has the largest context window?

The largest context window here is 1000K tokens on Mistral Large 4. A larger window does not make a model cheaper: cost the input side of the bill first and check the window only for the documents you need to send in one request.

Next step → Price a Mistral workload per user

Price data last checked 2026-11-18 against official sources · how we verify

Price-change alerts

One short email when a provider changes a price or a promo ends. No spam, unsubscribe any time.