DeepSeek: DeepSeek V3.1 Terminus (exacto)
Analysis Summary
DeepSeek V3.1 Terminus exacto is a text model from DeepSeek with a 163,840-token context window, tool use, and function calling. Its coding index is strong, but its measured intelligence and agentic indices are low. Those results suggest a narrow profile: useful coding capability does not by itself establish reliable multi-step execution or broad reasoning.
For business teams, it may suit cost-sensitive coding assistance and text-based technical tasks with human review. It is a weaker choice for autonomous agents or workflows where the model must reliably plan and act across multiple steps. Vision is not listed. The exacto variant also has a lower intelligence result than the other Terminus entry provided, so teams should evaluate this specific version rather than assume sibling performance.
Its listed prices are low, making a targeted trial feasible. Prefer it where coding value matters more than general reasoning or agentic independence.
Assessed September 23, 2026
Editorial notes
DeepSeek V3.1 Terminus exacto has a strong coding result, tool and function calling, and low pricing, but its measured intelligence and agentic results are limited.
The DFO score ranks models on the Artificial Analysis Intelligence Index and is refreshed as new models launch. The write-up and verdict are our own. Feedback?
DFO Verdict
DeepSeek V3.1 Terminus exacto has a strong coding result, tool and function calling, and low pricing, but its measured intelligence and agentic results are limited.
Benchmarks
Artificial Analysis data refreshed Oct 8, 2026. Arena ratings from the Oct 2, 2026 text leaderboard, with style control.
How DeepSeek: DeepSeek V3.1 Terminus (exacto) compares
DeepSeek: DeepSeek V3.1 Terminus (exacto) ranks #162 of 435 AI models we track for overall intelligence, #76 of 198 for coding, #108 of 181 for agentic tasks. Its 164K-token context window is larger than 53% of the models we list. At $0.21 per million input tokens it is cheaper than 48% of comparable models.
Dark bar = input · light bar = output, scaled to the priciest peer.
1M tokens ≈ 8 full-length novels or ~2,500 pages of business documents in a single request.
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.21 | $0.000210 |
| Output | $0.79 | $0.000790 |
What would DeepSeek: DeepSeek V3.1 Terminus (exacto) cost your business?
Pick the job that looks most like yours, then fine-tune with the sliders. Estimates update live.
A website chatbot handling around 100 customer conversations a day, a few short messages each.
Full calculator with 697 models → Price Calculator
These numbers get smaller with the right architecture.
We route routine calls to cheap models and save DeepSeek: DeepSeek V3.1 Terminus (exacto) for the hard ones. Most clients cut their estimate by 60-80%.
Talk to our teamAbout DeepSeek: DeepSeek V3.1 Terminus (exacto)
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.
Frequently asked questions about DeepSeek: DeepSeek V3.1 Terminus (exacto)
How much does DeepSeek: DeepSeek V3.1 Terminus (exacto) cost?
DeepSeek: DeepSeek V3.1 Terminus (exacto) costs $0.21 per million input tokens and $0.79 per million output tokens.
What is the context window of DeepSeek: DeepSeek V3.1 Terminus (exacto)?
DeepSeek: DeepSeek V3.1 Terminus (exacto) has a context window of 163,840 tokens (164K).
Is DeepSeek: DeepSeek V3.1 Terminus (exacto) good for coding?
On our coding benchmark index, DeepSeek: DeepSeek V3.1 Terminus (exacto) ranks #76 of 198 models, placing it in the broader range of the field for code generation and debugging.
What can DeepSeek: DeepSeek V3.1 Terminus (exacto) do?
DeepSeek: DeepSeek V3.1 Terminus (exacto) supports tool use and function calling.
Who created DeepSeek: DeepSeek V3.1 Terminus (exacto)?
DeepSeek: DeepSeek V3.1 Terminus (exacto) is developed by DeepSeek and was released on September 22, 2025.