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 vs Qwen2.5 72B Instruct
DeepSeek: DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and mathematics, thanks to our specialized…
Model details →Side-by-side comparison
| Capability | DeepSeek: DeepSeek V3.1 Terminus | Qwen2.5 72B Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 164K | 33K | 🏆 DeepSeek: DeepSeek V3.1 Terminus |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.21 | $0.12 | 🏆 Qwen2.5 72B Instruct |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.79 | $0.39 | 🏆 Qwen2.5 72B Instruct |
| 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 |
Frequently asked questions
Is DeepSeek: DeepSeek V3.1 Terminus better than Qwen2.5 72B Instruct?
DeepSeek: DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct are evenly matched on 6 axes — pick the one whose provider, latency, or licensing fits your stack.
What's the price difference between DeepSeek: DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct?
Input: $0.21 vs $0.12 per 1M tokens. Output: $0.79 vs $0.39 per 1M tokens.
What context windows do DeepSeek: DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct support?
DeepSeek: DeepSeek V3.1 Terminus supports up to 164K tokens. Qwen2.5 72B Instruct supports up to 33K tokens.
Do both DeepSeek: DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct support tool calling?
DeepSeek: DeepSeek V3.1 Terminus: yes. Qwen2.5 72B Instruct: yes.