Model board / Codestral (v25.08)

Codestral (v25.08)

Name: Codestral (v25.08)
Brand: Mistral
Price: 0.9 USD

latest Mistral

Verified 2026-10-15 against the pages listed below. Prices are USD per 1M tokens, list rate — no committed-use, enterprise or volume discount.

Input

$0.3

Cached input

$0.03

Cache write

—

Output

$0.9

Context window

128,000

Max output

—

Weights

closed

Caching

unverified

cached input $0.03 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: Mistral Premier tier — proprietary, per the models doc

Watch out

Added on 2026-08-27 to close a real gap: this board tracked agentic coding but had nowhere to put a completion model, and they are different purchases — FIM capability, a much tighter latency budget, and no reasoning mode. Despite the open-weight history of the Codestral name, the current v25.08 is listed under Mistral's Premier tier, which is proprietary

What we would use it for

Inline code completion and fill-in-the-middle, where latency matters more than reasoning

What this has cost, week by week

Output price at each refresh since 2026-08-27. 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.

08-27 $0.9→09-03 $0.9→09-10 $0.9→09-17 $0.9→09-24 $0.9→10-01 $0.9→10-08 $0.9→10-15 $0.9

newly stated2026-09-03 · cached_in — $0.03 from the same newly cited page. No change to what Mistral charges.

newly stated2026-09-24 · window — 128K window from Mistral's per-model page for Codestral 25.08, newly cited. No change to the model.

Where these numbers came from

No number on this page was written that was not read from one of those pages on 2026-10-15. 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.

Jobs this is one of our picks for

Code completion — Fill-in-the-middle and next lines, at keystroke latency (code-completion)

The rest of the board

This row sits alongside 69 others on the model board, refreshed every week. The same data as JSON, and the terms for using it, are at /board-data.