Model board / Mistral Medium 3.5

Mistral Medium 3.5

Name: Mistral Medium 3.5
Brand: Mistral
Price: 7.5 USD

latest Mistral

Verified 2026-10-22 against the pages listed below. Prices are USD per 1M tokens, list rate — no committed-use, enterprise or volume discount.

Input

$1.50

Cached input

$0.15

Cache write

—

Output

$7.50

Context window

256,000

Max output

—

Weights

open

Caching

unverified

cached input $0.15 per 1M, printed per model on docs.mistral.ai/inference/pricing — the third Mistral pricing page, added to this row's sources on 2026-09-03. It is the −90% discount the other two pages describe only in prose

window stated on the model's own page; max output not stated

cached input bills at 10% of input in 64-token blocks, so a prompt under 64 tokens never hits; a prompt_cache_key raises the chance of a hit but does not guarantee one. Whether caching applies without the key, and the TTL, are not stated

Licence: Modified MIT (v26.04)

Watch out

This board carried "no caching" here until 2026-08-29 on the strength of a rate missing from the pages it cited, retracted it, then left cached_in null for one pass. Both are now closed: the rate was on a third Mistral page all along, and it is $0.15

What we would use it for

Agentic and coding work with EU data residency

What this has cost, week by week

Output price at each refresh since 2026-07-30. A vendor change is the provider changing its price. Our correction means this board changed what it prints and the provider's charge did not move — the two are never merged, because publishing the second as the first would be a price rise that never happened.

07-30 $7.50→08-06 $7.50→08-14 $7.50→08-20 $7.50→08-27 $7.50→09-03 $7.50→09-10 $7.50→09-17 $7.50→09-24 $7.50→10-01 $7.50→10-08 $7.50→10-15 $7.50→10-22 $7.50

our correction2026-08-06 · weights — Licence resolved against Mistral's models doc rather than left as 'check model card', which moved the row from partial to open. Mistral's terms did not change.

newly stated2026-09-03 · cached_in — $0.15 sourced from docs.mistral.ai/inference/pricing, a third Mistral pricing page that prints the cached-input column filled per model. Mistral's rate did not change — this board could not previously cite one, and the row carried null. The page is now cited by the row.

newly stated2026-09-24 · window — 256K window from Mistral's per-model page, newly cited.

Where these numbers came from

No number on this page was written that was not read from one of those pages on 2026-10-22. If one is wrong, send us the source URL and it is corrected in the next weekly refresh, with a changelog line saying what was wrong — contact@naderu.com.

The rest of the board

This row sits alongside 76 others on the model board, refreshed every week. The same data as JSON, and the terms for using it, are at /board-data.