█

AI/TLDR

Buy me a coffee
Buy me a coffee

Model comparison

Devstral 2 / Devstral Small 2 vs Devstral Medium & Small 1.1 (25.07)

Short answer

Devstral 2 / Devstral Small 2 scores higher on 1 of the 1 benchmarks both models report; Devstral Medium & Small 1.1 (25.07) is cheaper on input tokens ($0.1 vs $0.4 per 1M, 4×); Devstral 2 / Devstral Small 2 has the larger context window (256K vs 128K).

Specs and pricing side by side

SpecDevstral 2 / Devstral Small 2Devstral Medium & Small 1.1 (25.07)
MakerMistral AIMistral AIsame
Released2025-12-092025-07-10
Context window256K128K
Max output256Knot published
Input price$0.40 / 1M tokens (Devstral 2); $0.10 / 1M tokens (Devstral Small 2)$0.10 / 1M tokens (Devstral Small 1.1); $0.40 / 1M tokens (Devstral Medium)
Output price$2.00 / 1M tokens (Devstral 2); $0.30 / 1M tokens (Devstral Small 2)$0.30 / 1M tokens (Devstral Small 1.1); $2.00 / 1M tokens (Devstral Medium)
ParametersDevstral 2: 123B; Devstral Small 2: 24BDevstral Small 1.1: 24B; Devstral Medium: not disclosed
LicenseDevstral 2: Modified MIT; Devstral Small 2: Apache 2.0Devstral Small 1.1: Apache 2.0; Devstral Medium: proprietary (API only)
WeightsOpen weightsOpen weightssame
ModalitiesTextTextsame
Knowledge cutoff20252025same

Benchmarks both models report

BenchmarkDevstral 2 / Devstral Small 2Devstral Medium & Small 1.1 (25.07)
SWE-Bench Verified72.2%53.6%

Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.

Which one should you pick?

Pick Devstral 2 / Devstral Small 2 if…

  • You care about SWE-Bench Verified (it scores higher on 1 shared benchmark).
  • You need the longer context (256K vs 128K).
  • Your use case is: agentic software engineering: exploring codebases and editing multiple files.

Pick Devstral Medium & Small 1.1 (25.07) if…

  • Cost matters: input tokens cost 4× less ($0.1 vs $0.4 per 1M).
  • Your use case is: open, self-hostable coding agents (Devstral Small 1.1).

FAQ

Which is better, Devstral 2 / Devstral Small 2 or Devstral Medium & Small 1.1 (25.07)?

Devstral 2 / Devstral Small 2 scores higher on 1 of the 1 benchmarks both models report; Devstral Medium & Small 1.1 (25.07) is cheaper on input tokens ($0.1 vs $0.4 per 1M, 4×); Devstral 2 / Devstral Small 2 has the larger context window (256K vs 128K). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.

How much cheaper is Devstral Medium & Small 1.1 (25.07)?

Devstral 2 / Devstral Small 2: $0.40 / 1M tokens (Devstral 2); $0.10 / 1M tokens (Devstral Small 2) input, $2.00 / 1M tokens (Devstral 2); $0.30 / 1M tokens (Devstral Small 2) output. Devstral Medium & Small 1.1 (25.07): $0.10 / 1M tokens (Devstral Small 1.1); $0.40 / 1M tokens (Devstral Medium) input, $0.30 / 1M tokens (Devstral Small 1.1); $2.00 / 1M tokens (Devstral Medium) output (list API prices as published by each maker).

What are the context windows of Devstral 2 / Devstral Small 2 and Devstral Medium & Small 1.1 (25.07)?

Devstral 2 / Devstral Small 2 offers 256K with up to 256K output; Devstral Medium & Small 1.1 (25.07) offers 128K.

Is Devstral 2 / Devstral Small 2 newer than Devstral Medium & Small 1.1 (25.07)?

Devstral 2 / Devstral Small 2 was released 2025-12-09; Devstral Medium & Small 1.1 (25.07) was released 2025-07-10.

Go deeper