Magistral Medium pricing
$2.00 per million input tokens, $5.00 per million output. 256K token context window. Read from Mistral AI’s own documentation on August 5, 2026.
- Input
- $2.00 per 1M tokens
- Cached input
- — not published
- Output
- $5.00 2.5× input
- Context window
- 256K verified
- Token counting
- Estimate o200k_base
- Price verified
- 2026-08-05 today
Reasoning model. Reasoning tokens are billed at the output rate and do not appear in the visible answer.
Source: Mistral AI pricing documentation. Prices change without notice — verify before committing spend.
What Magistral Medium 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.
| Workload | In | Out | Per request | Per month |
|---|---|---|---|---|
| ClassificationShort input, one-word answer. Input-dominated. | 500 | 50 | $0.001250 | $125.00 |
| Chat turnA system prompt plus a few turns of history. | 1,500 | 300 | $0.004500 | $450.00 |
| Document summaryA long document in, a paragraph out. | 20,000 | 800 | $0.0440 | $4,400.00 |
| Code generationOutput-heavy — where output pricing dominates. | 2,000 | 1,500 | $0.0115 | $1,150.00 |
Put your own numbers in the cost calculator, or measure a real prompt first in the token counter.
Counting tokens for Magistral Medium
Mistral AI does not publish a tokenizer that runs in a browser, so any pre-flight count for Magistral Medium 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?
| Model | Input | Output | Context | Chat turn |
|---|---|---|---|---|
| Magistral Medium — this page | $2.00 | $5.00 | 256K | $0.004500 |
| Mistral Medium 3.5 | $1.50 | $7.50 | 256K | $0.004500 |
| Mistral Large 3 | $0.5000 | $1.50 | 256K | $0.001200 |
| Mistral Small 4 | $0.1500 | $0.6000 | 256K | $0.000405 |
| 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 Magistral Medium, not the cheapest on the market — those are the ones actually worth evaluating against it.
Frequently asked questions
- How much does Magistral Medium cost?
- $2.00 per million input tokens and $5.00 per million output tokens. On a typical chat turn of 1,500 input and 300 output tokens that is $0.004500 per request, or $450.00 per month at 100,000 requests. Read from Mistral AI's own documentation on August 5, 2026.
- Can I count Magistral Medium tokens exactly?
- No. Mistral AI does not publish a tokenizer that runs in a browser, so any pre-flight count for Magistral Medium 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 Magistral Medium?
- 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 Magistral Medium?
- Output costs 2.5 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.