Skip to content
Bencher

Models · Mistral AI · Out sinceReleased 9 Dec 2025

Devstral 2

Available on OpenRouterOn OpenRouterBeing retiredDeprecatedCan run on your own serversOpen weights

Devstral 2 is made by Mistral AI. We don't have enough test results yet to rank it. It's cheap to use. Its makers have published it, so you can run it on your own servers.

Previous Mistral coding model; deprecated 2026-05-22, retirement 2026-07-31, replaced by Mistral Medium 3.5. Price from OpenRouter listing.

Writing & creativity
—
Research & analysis
—
Coding
—
Price
Cheap$0.40 / $2
Price per 1M (blended)Blended / 1M
$0.80
MemoryContext
262K
Longest answerMax output
—
Test resultsResults
1 (0 independent0 indep.)
Out sinceReleased
9 Dec 2025
Made byVendor
Mistral AI
UnderstandsInputs
—

Scores are out of 100 for each area, compared with every model we track; “#” is its rank. Context is how much text it can read at once (1M is roughly 700,000 words). Blended price mixes the cost of what you send and what it writes back.

Thinking levels

Reasoning settings

You can't choose how long this one thinks.

No adjustable reasoning setting listed.

Read more

Links

Using it through OpenRouter

On OpenRouter

OpenRouter is a service that gives access to many AI models in one place. This model is listed there as mistralai/devstral-2512.

Route it as mistralai/devstral-2512 at $0.40 in / $2 out per 1M tokens, 262K context. Listed since 9 Dec 2025.

frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_p

Run it yourself

Self-hosting

On your own servers,Licence, sizeunder your own control.and hardware.

Compare all open models →All open-weights models →

Details comingselfHost data pending

This model can be downloaded and run on your own servers. We're collecting its licence, size and hardware needs now.Open-weights model; licence, parameter count, hardware tier and base-model availability will appear after the next data run.

Every test result

Every result

All the numbers,with where they came from.

Every result we've found for this model, with who measured it and a link to where we read it.

All raw rows (vendor and independent kept separate), with setting label, source, date, harness and notes.

All results for this model
NotesNotes
SWE-bench Verified72.2%DefaultMaker's own figureVendor-reportedMistral AI ↗22 May 2026—'vs previous Mistral coding models' chart in the Mistral Medium 3.5 post.