Mistral API models and pricing

We track 13 models on Mistral API (15 listings) from 3 labs. The cheapest paid model is Mistral Embed, at $0.10 per million input tokens and Free per million output tokens. Input prices range from $0.10 to $1.50 and output prices from $0.10 to $7.50 per million tokens. The largest context window is 1M tokens (DeepSeek V4.1 Flash 1017, Mistral Large 4 and 2 other models). Prices last verified 18 Nov 2026.

Prices in USD per million tokens. Official site

Cheapest models on Mistral API

Input / output per million tokens, paid models, by combined price.

Newest models on Mistral API

By the lab's release date.

All Mistral API models and prices

ModelLabInputOutputContextSource
DeepSeek V4.1 Flash 1017
deepseek-v4-1-flash-1017
DeepSeek$0.30$1.201Mmodels.dev
Mistral Large 4
mistral-large-4-0-8
Mistral AI$0.70$2.101Mmodels.dev
Mistral Large 4
mistral-large-latest
Mistral AI$0.70$2.101Mmodels.dev
Mistral Large 4
mistral-large-4
Mistral AI$0.70$2.101Mmodels.dev
GLM-5.3-Flash
zai-glm-5-3-flash
Zhipu AI (Z.ai)$0.15$0.501Mmodels.dev
GLM-5.3
zai-glm-5-3
Zhipu AI (Z.ai)$1.40$4.401Mmodels.dev
Mistral Medium 3.5
mistral-medium-2604
Mistral AI$1.50$7.50262Kmodels.dev
Mistral Small 4
mistral-small-2603
Mistral AI$0.15$0.60262Kmodels.dev
Ministral 3 14B
ministral-14b-2512
Mistral AI$0.20$0.20262Kmodels.dev
Ministral 3 8B
ministral-8b-2512
Mistral AI$0.15$0.15262Kmodels.dev
Ministral 3 3B
ministral-3b-2512
Mistral AI$0.10$0.10131Kmodels.dev
Codestral 25.08
codestral-2508
Mistral AI$0.30$0.90256Kmodels.dev
Voxtral Small
voxtral-small-2507
Mistral AI$0.10$0.4033Kmodels.dev
Mistral Large 3
mistral-large-2512
Mistral AI$0.50$1.50262Kmodels.dev
Mistral Embed
mistral-embed
Mistral AI$0.10Free8Kmodels.dev

Frequently asked questions

How much does Mistral API cost per million tokens?

Prices on Mistral API depend on the model. Across the 13 models we track, input costs $0.10 to $1.50 per million tokens and output costs $0.10 to $7.50 per million tokens. Prices last verified 18 Nov 2026.

What is the cheapest model on Mistral API?

Mistral Embed from Mistral AI is the cheapest paid model we track on Mistral API, at $0.10 per million input tokens and Free per million output tokens. Next are Ministral 3 3B ($0.10 / $0.10) and Ministral 3 8B ($0.15 / $0.15). Prices last verified 18 Nov 2026.

How many models does Mistral API offer?

We currently track 13 active models on Mistral API from 3 labs, led by Mistral AI (10), Zhipu AI (Z.ai) (2) and DeepSeek (1).

Which model on Mistral API has the largest context window?

DeepSeek V4.1 Flash 1017, Mistral Large 4 and 2 other models share the largest context window we track on Mistral API: 1,048,576 tokens (1M).