ZMIME
Comparison · 2 models · Updated Oct 4, 2026

Devstral 2 vs Devstral Small

Devstral Small comes out ahead, 57 to 42 on our weighted score, and it is the cheaper option too.

  1. Mistral AI

    Devstral 2

    Released Dec 9, 2025Deprecated

    42/100
    • ECI—
    • Price$0.40 / $2.00
    • Context262K
  2. Our pick

    Mistral AI

    Devstral Small

    Released Jul 10, 2025Deprecated

    57/100
    • ECI—
    • Price$0.10 / $0.30
    • Context128K
  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Devstral Small is our pick

Devstral Small is the better all-round choice, scoring 57/100 against Devstral 2 (42). It leads on price. Devstral 2 wins on context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceDevstral SmallDevstral Small $0.15 · Devstral 2 $0.80 per 1M tokens (3:1 blend)
  • Longest contextDevstral 2Devstral 2 262,144 · Devstral Small 128,000 tokens
  • Widest inputsSame inputsDevstral 2: Text · Devstral Small: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDevstral 2Devstral Small
Price50%5489
Inputs & features30%2525
Context window20%3724
Overall100%42/10057/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Devstral 2 vs Devstral Small specifications side by side
SpecificationDevstral 2Mistral AIDevstral SmallMistral AI
Capability
Capabilities Index (ECI)——
ECI rank——
Price per million tokens
Input$0.40$0.10 (best)
Output$2.00$0.30 (best)
Cached input——
Blended (3:1)$0.80$0.15 (best)
Long-context rateSame rateSame rate
Price sourceOfficial Mistral APIOfficial Mistral API
Limits
Context window262,144 tokens (best)128,000 tokens
Max output262,144 tokens (best)128,000 tokens
Inputs and features
TextYesYes
ImagesNoNo
PDFsNoNo
AudioNoNo
VideoNoNo
ReasoningNoNo
Tool callingYesYes
Structured outputNoNo
Availability
WeightsOpenOpen
API model IDdevstral-2512devstral-small-2507
API providers14 (best)2
ReleasedDec 9, 2025Jul 10, 2025
Knowledge cutoffDec 2025May 2025
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Devstral 2$8.00
  • Devstral Small$1.60
04 — Questions

Which should you choose?

Which is better: Devstral 2 or Devstral Small?

Devstral Small is the better all-round choice, scoring 57/100 against Devstral 2 (42). It leads on price. Devstral 2 wins on context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Devstral 2 or Devstral Small?

Devstral Small is cheaper at $0.10 input / $0.30 output per million tokens (official Mistral API price). Devstral 2 costs $0.40 input / $2.00 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.15 per million tokens for Devstral Small versus $0.80 for Devstral 2 (5.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers both models yet. Devstral 2 has not been scored yet and Devstral Small has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Devstral 2 and Devstral Small yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Both support tool calling for agent workflows.

Which has the bigger context window?

Devstral 2 has the largest context window at 262,144 tokens, against 128,000 for Devstral Small. Maximum output per response: Devstral 2 up to 262,144, Devstral Small up to 128,000 tokens.

Which can read images, PDFs, audio or video?

Devstral 2 accepts text; Devstral Small accepts text. They handle the same number of input types.

Are any of these open source?

Yes, both publish their weights, so you can self-host them.

Which is newer?

Devstral 2 is the newest, released Dec 9, 2025. Devstral Small came out Jul 10, 2025. Knowledge cutoff: Devstral 2 Dec 2025, Devstral Small May 2025.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.