LLMPrice.io

Devstral API pricing 2512

Published on-demand rates for Mistral's mistral/devstral-2512, captured 2026-08-29 from public pricing data and committed to our archive. Context window 256k tokens; first observed in our archive 2025-12-15.

MeterUSD per 1M tokens
Input$0.400
Output$2.00
Cached inputno published cache-read rate; the whole input bills at the standard rate

Standard on-demand rates. Excludes batch endpoints and negotiated pricing; confirm on Mistral's pricing page before committing.

What it costs on a real workload

Per 1M tokens processed, at the rates above. How the four profiles are defined.

ProfileIn / out mixCached shareCost
Retrieval800k / 200k70%$0.720
Chat500k / 500k30%$1.20
Content200k / 800k20%$1.68
Agent900k / 100k85%$0.560

Compare every model on these profiles →

Observed rate history

No repricing observed since this model entered our archive on 2025-12-15. When a rate moves, the change appears here and on the sitewide ticker.

What the record shows

Devstral has not repriced once since it entered our archive on 2025-12-15. That is the ordinary case rather than the exception: providers ship new models at lower rates far more often than they cut the price of one already in service, which is why a cheaper option usually arrives as a new name rather than as a smaller number on this page.

Against the 44 models we price, it is the 19th cheapest for retrieval-shaped work, which reads a great deal and writes little, and the 19th cheapest for content-shaped work, which does the reverse. The two are close, so it holds its position whichever way your workload leans.

It charges 5.0 times more for output than for input, against a median of 5.0 times across the set. That is close to typical for the models we track.

Mistral publishes no cache-read rate for it, so a prompt prefix you send on every call costs the same as text the model has never seen. On a cache-heavy workload that is a structural disadvantage against models that publish one, and it is why the agent profile above prices its whole input at the standard rate.

Whether it accepts image input is not stated in the source we capture, and we do not guess at it.

Its 256k token context window holds roughly 192,000 words of English text in a single request. A workload that does not fit cannot run here at any price, which is a capability limit rather than a cost one.

Priced near this one

Closest to Devstral on a retrieval workload, cheaper and more expensive alike. Cost only; we publish no quality score.

ModelProviderInputOutputvs Devstral
Mistral LargeMistral$0.500$1.503% less
Grok Code FastxAI$1.00$2.004% more
Gemini 3.5 Flash LiteGoogle$0.300$2.5018% less
Grok 4.3xAI$1.25$2.5027% more

Retrieval profile: 800k in, 200k out, 70% cached where offered.

Price your own prompt on it Estimate a whole project Plain rate card Mistral's console →

No affiliate or referral arrangements: the console link carries no parameters and nothing on this page is paid placement. Devstral is a trademark of its owner; LLMPrice.io is independent and unaffiliated.