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 Inception: Mercury Coder
DeepSeek: DeepSeek V3.1 Terminus wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
Mercury Coder is the first diffusion large language model (dLLM). Applying a breakthrough discrete diffusion approach, the model runs 5-10x faster than even speed optimized models like Claude 3.5 Haiku and GPT-4o Mini while matching their p…
Model details →Side-by-side comparison
| Capability | DeepSeek: DeepSeek V3.1 Terminus | Inception: Mercury Coder | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 164K | 128K | 🏆 DeepSeek: DeepSeek V3.1 Terminus |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.21 | $0.25 | 🏆 DeepSeek: DeepSeek V3.1 Terminus |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.79 | $0.75 | 🏆 Inception: Mercury Coder |
| 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 Inception: Mercury Coder?
DeepSeek: DeepSeek V3.1 Terminus wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between DeepSeek: DeepSeek V3.1 Terminus and Inception: Mercury Coder?
Input: $0.21 vs $0.25 per 1M tokens. Output: $0.79 vs $0.75 per 1M tokens.
What context windows do DeepSeek: DeepSeek V3.1 Terminus and Inception: Mercury Coder support?
DeepSeek: DeepSeek V3.1 Terminus supports up to 164K tokens. Inception: Mercury Coder supports up to 128K tokens.
Do both DeepSeek: DeepSeek V3.1 Terminus and Inception: Mercury Coder support tool calling?
DeepSeek: DeepSeek V3.1 Terminus: yes. Inception: Mercury Coder: yes.