Devstral Medium vs Devstral Small 2 vs GLM-4.7-FlashX
Devstral Small 2 comes out ahead, 67 to 61 and 39 on our weighted score, and it is the cheaper option too.
Mistral AIDevstral Medium
39/100- ECI—
- Price$0.40 / $2.00
- Context128K
- Our pickMistral AI
Devstral Small 2
67/100- ECI—
- Price$0.10 / $0.30
- Context262K
Z.ai (Zhipu)GLM-4.7-FlashX
61/100- ECI—
- Price$0.07 / $0.40
- Context200K
Devstral Small 2 is our pick
Devstral Small 2 is the better all-round choice, scoring 67/100 against GLM-4.7-FlashX (61) and Devstral Medium (39). It leads on inputs & features and 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 Small 2Devstral Small 2 $0.15 · GLM-4.7-FlashX $0.152 · Devstral Medium $0.80 per 1M tokens (3:1 blend)
- Longest contextDevstral Small 2Devstral Small 2 262,144 · GLM-4.7-FlashX 200,000 · Devstral Medium 128,000 tokens
- Widest inputsDevstral Small 2Devstral Medium: Text · Devstral Small 2: Text, Images · GLM-4.7-FlashX: Text
- Self-hostingDevstral Small 2 and GLM-4.7-FlashXPublishes downloadable weights (Apache-2.0)
| Measure | Weight | Devstral Medium | Devstral Small 2 | GLM-4.7-FlashX |
|---|---|---|---|---|
| Price | 50% | 54 | 89 | 89 |
| Inputs & features | 30% | 25 | 50 | 35 |
| Context window | 20% | 24 | 37 | 32 |
| Overall | 100% | 39/100 | 67/100 | 61/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Devstral MediumMistral AI | Devstral Small 2Mistral AI | GLM-4.7-FlashXZ.ai (Zhipu) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $0.40 | $0.10 | $0.07 (best) |
| Output | $2.00 | $0.30 (best) | $0.40 |
| Cached input | — | — | $0.01 |
| Blended (3:1) | $0.80 | $0.15 (best) | $0.152 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Median of 1 providers | Official Z.AI API |
| Limits | |||
| Context window | 128,000 tokens | 262,144 tokens (best) | 200,000 tokens |
| Max output | 128,000 tokens | 262,144 tokens (best) | 131,072 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Proprietary | OpenApache-2.0 | Open |
| API model ID | devstral-medium-2507 | — | glm-4.7-flashx |
| API providers | 2 | 1 | 8 (best) |
| Released | Jul 10, 2025 | Dec 9, 2025 | Jan 19, 2026 |
| Knowledge cutoff | May 2025 | Dec 2025 | Apr 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$8.00
- Devstral Small 2$1.60
- GLM-4.7-FlashX$1.50
Which should you choose?
Which is better: Devstral Medium, Devstral Small 2 or GLM-4.7-FlashX?
Devstral Small 2 is the better all-round choice, scoring 67/100 against GLM-4.7-FlashX (61) and Devstral Medium (39). It leads on inputs & features and 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 Medium, Devstral Small 2 or GLM-4.7-FlashX?
Devstral Small 2 is cheaper at $0.10 input / $0.30 output per million tokens (median across 1 API provider). GLM-4.7-FlashX costs $0.07 input / $0.40 output per million tokens (official Z.AI API price); Devstral Medium 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 2 versus $0.152 for GLM-4.7-FlashX (1× as much) and $0.80 for Devstral Medium (5.3× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Devstral Medium has not been scored yet, Devstral Small 2 has not been scored yet and GLM-4.7-FlashX has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Devstral Medium, Devstral Small 2 and GLM-4.7-FlashX yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Devstral Small 2 has the largest context window at 262,144 tokens, against 200,000 for GLM-4.7-FlashX and 128,000 for Devstral Medium. Maximum output per response: Devstral Medium up to 128,000, Devstral Small 2 up to 262,144, GLM-4.7-FlashX up to 131,072 tokens.
Which can read images, PDFs, audio or video?
Devstral Medium accepts text; Devstral Small 2 accepts text and images; GLM-4.7-FlashX accepts text. Devstral Small 2 handles the widest range of inputs.
Are any of these open source?
Devstral Small 2 and GLM-4.7-FlashX publishes its weights (Apache-2.0) and can be self-hosted; Devstral Medium is proprietary.
Which is newer?
GLM-4.7-FlashX is the newest, released Jan 19, 2026. Devstral Small 2 came out Dec 9, 2025; Devstral Medium came out Jul 10, 2025. Knowledge cutoff: Devstral Medium May 2025, Devstral Small 2 Dec 2025, GLM-4.7-FlashX Apr 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.
