DeepSeek V3.1 Terminus by DeepSeek is a September 2025 refinement of V3.1 fixing language mixing, strengthening Code Agent and Search Agent performance. MIT licensed.
Capabilities, design details, and architectural traits
DeepSeek V3.1 Terminus is a September 22, 2025 update to DeepSeek V3.1, released as a targeted refinement addressing two officially documented problem areas from V3.1's initial deployment: language consistency and agent capability. It maintains the same architecture and hybrid thinking/non-thinking design as V3.1, with no structural changes.
Two officially documented fix areas:
Language consistency:
Agent capabilities:
Upon release, both deepseek-chat and deepseek-reasoner API aliases were upgraded to DeepSeek V3.1-Terminus: deepseek-chat → non-thinking mode; deepseek-reasoner → thinking mode.
Independent evaluations · Artificial Analysis
Evaluate specifications, pricing, and independent benchmark indices
| Model Details | |||
|---|---|---|---|
| General Info | |||
| Provider | DeepSeek | Anthropic | Anthropic |
| Release Date | September 22, 2025 | July 24, 2026 | June 9, 2026 |
| Knowledge Cutoff | Mar 2025 | May 2026 | - |
| Context & Limits | |||
| Context Window | 164K | 1M Best Context Window | 1M Best Context Window |
| Pricing (per 1M tokens) | |||
| Input Pricing | $0.27 Best Input Pricing | $5 | $10 |
| Output Pricing | $1 Best Output Pricing | $25 | $50 |
| Modalities | |||
| Inputs | text | textimage | textimagefile |
| Outputs | text | text | text |
| Benchmarks (0-100) | |||
| Intelligence Index | 21.7 | 63.1 Best Intelligence Index | 62.1 |
| Coding Index | - | 78.0 Best Coding Index | 76.5 |
| Agentic Index | - | 59.2 Best Agentic Index | 56.6 |
Graduate-level reasoning and expert Q&A evaluation.
Extremely difficult logical reasoning and knowledge.
Logical reasoning over long context windows.
Independent evaluation data provided by Artificial Analysis. To view the latest benchmarks and full details, visit their official site.
