DeepSeek: DeepSeek V3.1 Terminus (exacto)
Review
The DeepSeek V3.1 Terminus (exacto) variant has no independent benchmark data, making it difficult to assess beyond its shared pricing and context window with the main Terminus model — businesses should rely on the benchmarked version for capability assessment.
Assessment date: April 16, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes. It extends the DeepSeek-V3 base with a two-phase long-context training process, reaching up to 128K tokens, and uses FP8 microscaling for efficient inference. Users can control the reasoning behaviour with the reasoning enabled boolean. Learn more in our docs The model improves tool use, code generation, and reasoning efficiency, achieving performance comparable to DeepSeek-R1 on difficult benchmarks while responding more quickly. It supports structured tool calling, code agents, and search agents, making it suitable for research, coding, and agentic workflows.
Capabilities
Architecture
| Modality | Text → Text |
| Tokenizer | DeepSeek |
| Instruct Type | deepseek-v3.1 |
How does DeepSeek: DeepSeek V3.1 Terminus (exacto) stack up?
Compare side-by-side with other legacy models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.21 | $0.000210 |
| Output | $0.79 | $0.000790 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
