Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI. Positioned as a step up from Devstral Small, it achieves 61.6% on SWE-Bench Verified, placing it ahead of Ge…
Model details →Mistral: Devstral Medium vs Z.ai: GLM 4 32B
Z.ai: GLM 4 32B wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
GLM 4 32B is a cost-effective foundation language model. It can efficiently perform complex tasks and has significantly enhanced capabilities in tool use, online search, and code-related intelligent tasks. It is made by the same lab behin…
Model details →Side-by-side comparison
| Capability | Mistral: Devstral Medium | Z.ai: GLM 4 32B | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 131K | 128K | 🏆 Mistral: Devstral Medium |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.40 | $0.10 | 🏆 Z.ai: GLM 4 32B |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $2.00 | $0.10 | 🏆 Z.ai: GLM 4 32B |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Mistral: Devstral Medium better than Z.ai: GLM 4 32B?
Z.ai: GLM 4 32B wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Mistral: Devstral Medium and Z.ai: GLM 4 32B?
Input: $0.40 vs $0.10 per 1M tokens. Output: $2.00 vs $0.10 per 1M tokens.
What context windows do Mistral: Devstral Medium and Z.ai: GLM 4 32B support?
Mistral: Devstral Medium supports up to 131K tokens. Z.ai: GLM 4 32B supports up to 128K tokens.
Do both Mistral: Devstral Medium and Z.ai: GLM 4 32B support tool calling?
Mistral: Devstral Medium: yes. Z.ai: GLM 4 32B: yes.