How much does Mistral Large 3 cost?

$0.5000 per million input tokens and $1.50 per million output tokens. On a typical chat turn of 1,500 input and 300 output tokens that is $0.001200 per request, or $120.00 per month at 100,000 requests. Read from Mistral AI's own documentation on August 5, 2026.

What is the context window of Mistral Large 3?

256,000 tokens. That budget covers everything in the request — system prompt, conversation history, tool definitions, documents — plus the response itself, not just your input.

Why is output more expensive than input on Mistral Large 3?

Output costs 3.0 times input here. Input is processed in a single parallel pass, while output is generated one token at a time with a full pass over the model for each. That is why a model that answers concisely can be cheaper in production than one with a lower headline rate.

Mistral AI

Mistral Large 3 pricing

$0.5000 per million input tokens, $1.50 per million output. 256K token context window. Read from Mistral AI’s own documentation on August 5, 2026.

Input: $0.5000
Cached input: —
Output: $1.50
Context window: 256K
Token counting: Estimate
Price verified: 2026-08-05

Open-weight model, so self-hosting is an alternative to these API rates. Cached input is discounted but not published per model.

Source: Mistral AI pricing documentation. Prices change without notice — verify before committing spend.

What Mistral Large 3 costs on real work

Four workload shapes at 100,000 requests a month. The point of showing four is that the ranking between models changes depending on which one describes you.

Mistral Large 3 cost by workload shape
Workload	In	Out	Per request	Per month
ClassificationShort input, one-word answer. Input-dominated.	500	50	$0.000325	$32.50
Chat turnA system prompt plus a few turns of history.	1,500	300	$0.001200	$120.00
Document summaryA long document in, a paragraph out.	20,000	800	$0.0112	$1,120.00
Code generationOutput-heavy — where output pricing dominates.	2,000	1,500	$0.003250	$325.00

Put your own numbers in the cost calculator, or measure a real prompt first in the token counter.

Counting tokens for Mistral Large 3

Mistral AI does not publish a tokenizer that runs in a browser, so any pre-flight count for Mistral Large 3 is an estimate rather than a measurement.

Mistral publishes its Tekken tokenizer only as a Python package, with no browser build. Counted with o200k_base and scaled; Tekken generally produces more tokens than o200k_base on the same English text.

Treat it as accurate to within roughly ten to twenty percent. That is fine for budgeting and wrong for sizing a prompt right at a context window boundary — where precision matters, use Mistral AI’s own token counting endpoint from your backend. The methodology page sets out every scaling factor used here.

Other Mistral AI models

The tier question: is a cheaper model in the same family enough for your task?

Other Mistral AI models compared with Mistral Large 3
Model	Input	Output	Context	Chat turn
Mistral Large 3 — this page	$0.5000	$1.50	256K	$0.001200
Mistral Medium 3.5	$1.50	$7.50	256K	$0.004500
Mistral Small 4	$0.1500	$0.6000	256K	$0.000405
Magistral Medium	$2.00	$5.00	256K	$0.004500
Devstral 2	$0.4000	$2.00	256K	$0.001200
Ministral 3 8B	$0.1500	$0.1500	256K	$0.000270

Alternatives from other providers

Models priced nearest to Mistral Large 3, not the cheapest on the market — those are the ones actually worth evaluating against it.

Frequently asked questions

How much does Mistral Large 3 cost?: $0.5000 per million input tokens and $1.50 per million output tokens. On a typical chat turn of 1,500 input and 300 output tokens that is $0.001200 per request, or $120.00 per month at 100,000 requests. Read from Mistral AI's own documentation on August 5, 2026.
Can I count Mistral Large 3 tokens exactly?: No. Mistral AI does not publish a tokenizer that runs in a browser, so any pre-flight count for Mistral Large 3 is an estimate. Mistral publishes its Tekken tokenizer only as a Python package, with no browser build. Counted with o200k_base and scaled; Tekken generally produces more tokens than o200k_base on the same English text. Treat it as accurate to within roughly ten to twenty percent and never as the basis for sizing a prompt right at a context window boundary.
What is the context window of Mistral Large 3?: 256,000 tokens. That budget covers everything in the request — system prompt, conversation history, tool definitions, documents — plus the response itself, not just your input.
Why is output more expensive than input on Mistral Large 3?: Output costs 3.0 times input here. Input is processed in a single parallel pass, while output is generated one token at a time with a full pass over the model for each. That is why a model that answers concisely can be cheaper in production than one with a lower headline rate.