Skip to main content
Mistral AI

Mistral API pricing

Every Mistral model we track, with the cheapest price per 1M tokens across 15 providers next to Mistral AI's own API price. Collected daily.

Cheapest input /1M
$0.029
Mistral Nemo
Models
23
Providers
15
Last updated
October 9, 2026

Mistral API prices by model

Standard (real-time) rates per 1M tokens, newest first. “Cheapest” is the lowest input price across every provider we track; batch and cached-input rates are on each model page.

Mistral API pricing by model
ModelCheapest inputOutputCheapest on
Mistral Small 4$0.150$0.600Empirio Labs
Mistral Large 4 Preview$0.680$2.09OpenRouter
Mistral Medium 3.5262K context$1.50$7.50Mistral AI
Mistral Small 3.2$0.094$0.250OpenRouter
Mistral Medium 3.1131K context$0.400$2.00OpenRouter
Mistral Small 3.1$0.351$0.555OpenRouter
Ministral 3 14B128K context$0.200$0.200Amazon AWS
Mistral Large 3256K context$0.500$1.50Amazon AWS
Ministral 3 3B$0.100$0.100Amazon AWS
Mistral Medium 3131K context$0.400$2.00OpenRouter
Mistral Small 3$0.050$0.080Heabsy
Magistral Small 1.2$0.500$1.50Amazon AWS
Mistral Nemo131K context$0.029$0.030Deep Infra
Mistral Small32K context$0.150$0.600OpenRouter
Mistral 7B32K context$0.110$0.110OVHcloud
Mistral Large128K context$0.500$1.50Prime Intellect
Ministral 3B131K context$0.100$0.100Mistral AI
Ministral 8B262K context$0.150$0.150Mistral AI
Mixtral 8x22B64K context$2.00$6.00OpenRouter
Mixtral 8x7B32K context$0.450$0.700Amazon AWS
Voxtral Small 24B32K context$0.100$0.300Amazon AWS
Devstral Medium131K context$0.400$2.00OpenRouter
Mistral Saba33K context$0.200$0.600OpenRouter

Official column shows input / output per 1M tokens on Mistral AI's own API.

Mistral price history

Average input price per 1M tokens across the providers serving each model, last 90 days.

Frequently Asked Questions

What is the cheapest Mistral API?

Of the 23 Mistral models we track, Mistral Nemo has the lowest input price right now: $0.029 per 1M input tokens on Deep Infra. Prices are collected daily from 15 providers — see the table above for every model.

Where is Mistral Small 4 cheapest?

Mistral Small 4 is served by 2 providers we track. The lowest standard input price is $0.150 per 1M tokens on Empirio Labs. Throughput, latency and context limits differ between hosts, so check the model page before committing.

Is a third-party host cheaper than Mistral AI's own API?

For 3 of the 23 Mistral models we track, another provider currently lists a lower input price than Mistral AI's own API. Compare the "Cheapest" and "Official" columns above; batch and cached-input rates are on each model page.

Other model families