DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further …
Model details →DeepSeek: DeepSeek V3.1 Terminus (exacto) vs Mistral: Devstral Medium
DeepSeek: DeepSeek V3.1 Terminus (exacto) wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
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 →Side-by-side comparison
| Capability | DeepSeek: DeepSeek V3.1 Terminus (exacto) | Mistral: Devstral Medium | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 164K | 131K | 🏆 DeepSeek: DeepSeek V3.1 Terminus (exacto) |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.21 | $0.40 | 🏆 DeepSeek: DeepSeek V3.1 Terminus (exacto) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.79 | $2.00 | 🏆 DeepSeek: DeepSeek V3.1 Terminus (exacto) |
| 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. | Yes | — | 🏆 DeepSeek: DeepSeek V3.1 Terminus (exacto) |
Frequently asked questions
Is DeepSeek: DeepSeek V3.1 Terminus (exacto) better than Mistral: Devstral Medium?
DeepSeek: DeepSeek V3.1 Terminus (exacto) wins on 4 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between DeepSeek: DeepSeek V3.1 Terminus (exacto) and Mistral: Devstral Medium?
Input: $0.21 vs $0.40 per 1M tokens. Output: $0.79 vs $2.00 per 1M tokens.
What context windows do DeepSeek: DeepSeek V3.1 Terminus (exacto) and Mistral: Devstral Medium support?
DeepSeek: DeepSeek V3.1 Terminus (exacto) supports up to 164K tokens. Mistral: Devstral Medium supports up to 131K tokens.
Do both DeepSeek: DeepSeek V3.1 Terminus (exacto) and Mistral: Devstral Medium support tool calling?
DeepSeek: DeepSeek V3.1 Terminus (exacto): yes. Mistral: Devstral Medium: yes.