DeepSeek: DeepSeek V3.1 Terminus
Analysis Summary
DeepSeek V3.1 Terminus is a September 2025 release from DeepSeek with strong benchmark performance across math (89.7), coding (LiveCodeBench 0.798), and general reasoning (GPQA 0.792, MMLU Pro 0.851). Tool use and function calling are supported across a 163K context window, and the agentic index of 33.7 indicates moderate multi-step reliability.
For businesses, it fits coding assistance, mathematical analysis, and structured document workflows. The agentic index is solid but not top-tier, so fully autonomous pipelines may require additional orchestration. Instruction-following and long-context reasoning scores are competitive, making it a capable choice for content-heavy tasks.
At $0.27 input and $0.95 output per million tokens, it offers strong price-performance for its benchmark tier. Teams needing a cost-effective model with verified coding and reasoning capability will find it a credible option, with the standard regional accessibility adjustment applied given limited enterprise adoption outside its home market.
Assessed June 30, 2026
Editorial notes
DeepSeek V3.1 Terminus posts strong math, coding, and reasoning benchmarks with tool use and a 163K context window at very competitive pricing.
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
How DeepSeek: DeepSeek V3.1 Terminus compares
DeepSeek: DeepSeek V3.1 Terminus ranks #96 of 385 AI models we track for overall intelligence, #135 of 293 for agentic tasks. Its 164K-token context window is larger than 61% of the models we list. At $0.27 per million input tokens it is cheaper than 45% of comparable models.
About DeepSeek: DeepSeek V3.1 Terminus
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..
Capabilities
Architecture Detail
| Instruct Type | deepseek-v3.1 |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does DeepSeek: DeepSeek V3.1 Terminus stack up?
Compare side-by-side with other professional models.
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.27 | $0.000270 |
| Output | $0.95 | $0.000950 |
Live Performance
Live endpoint metrics, refreshed every 30 minutes.
Leaderboard Categories
External Resources
Frequently asked questions about DeepSeek: DeepSeek V3.1 Terminus
How much does DeepSeek: DeepSeek V3.1 Terminus cost?
DeepSeek: DeepSeek V3.1 Terminus costs $0.27 per million input tokens and $0.95 per million output tokens.
What is the context window of DeepSeek: DeepSeek V3.1 Terminus?
DeepSeek: DeepSeek V3.1 Terminus has a context window of 163,840 tokens (164K).
What can DeepSeek: DeepSeek V3.1 Terminus do?
DeepSeek: DeepSeek V3.1 Terminus supports tool use and function calling.
Who created DeepSeek: DeepSeek V3.1 Terminus?
DeepSeek: DeepSeek V3.1 Terminus is developed by DeepSeek and was released on September 22, 2025.
