Devstral Medium vs Devstral Small
No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.
Price in rating: Included · Exclude price
Mistral AI
Devstral Medium
28/100- ECI—
- Price—
- Context128K
Mistral AI
Devstral Small
28/100- ECI—
- Price—
- Context128K
Add a model
Make it a three-way comparison.
Capability evidence is incomplete
There is not enough shared capability evidence to name an overall winner. The scores (Devstral Medium 28/100, Devstral Small 28/100) compare the available specifications and price. The score weighs inputs & features 60%, context window 40%. 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
- Longest contextAbout the sameDevstral Medium 128,000 · Devstral Small 128,000 tokens
- Widest inputsSame inputsDevstral Medium: Text · Devstral Small: Text
- Self-hostingDevstral SmallPublishes downloadable weights
| Measure | Weight | Devstral Medium | Devstral Small |
|---|---|---|---|
| Inputs & features | 60% | 25 | 25 |
| Context window | 40% | 32 | 32 |
| Specs & price only | 100% | 28/100 | 28/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | ||
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | — | — |
| Output | — | — |
| Cached input | — | — |
| Blended (3:1) | — | — |
| Long-context rate | — | — |
| Price source | — | — |
| Limits | ||
| Context window | 128,000 tokens | 128,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | No | No |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | No | No |
| Tool calling | Yes | Yes |
| Structured output | No | No |
| Availability | ||
| Weights | Proprietary | Open |
| API model ID | — | — |
| API providers | — | — |
| Released | Jul 10, 2025 | Jul 10, 2025 |
| Knowledge cutoff | May 2025 | May 2025 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
Devstral Medium—
Devstral Small—
Which should you choose?
Which is better: Devstral Medium or Devstral Small?
There is not enough shared capability evidence to name an overall winner. The scores (Devstral Medium 28/100, Devstral Small 28/100) compare the available specifications and price. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Devstral Medium or Devstral Small?
None of these models has a published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. Devstral Medium 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 Medium 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 Medium and Devstral Small share the same 128,000-token context window. Maximum output per response: Devstral Medium up to 128,000, Devstral Small up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Devstral Medium accepts text; Devstral Small accepts text. They handle the same number of input types.
Are any of these open source?
Devstral Small publishes its weights and can be self-hosted; Devstral Medium is proprietary.
Which is newer?
Devstral Medium is the newest, released Jul 10, 2025. Devstral Small came out Jul 10, 2025. Knowledge cutoff: Devstral Medium May 2025, Devstral Small May 2025.
How do you decide the winner?
This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 Nov 18, 2026.