# DeepSeek V3.1 Terminus

> DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while 

DeepSeek V3.1 Terminus has a SharkScore of 22.9/100, ranked #445 of 608 in Models (updated 2026-11-19).

- Website: https://openrouter.ai/deepseek/deepseek-v3.1-terminus (openrouter.ai)
- Kind: Model · Pricing: Open source
- Maker: DeepSeek
- Categories: Models, Model APIs & inference
- Verified by the maker: no

## Why it scores 22.9

| Part | Score (0–100) | Weight |
|---|---|---|
| Adoption | 0 | 30% |
| User reviews | no data | 25% |
| Maintenance | 1 | 20% |
| Trust & transparency | 80 | 15% |
| Momentum | no data | 10% |

Evidence covers 87% of the score's weight. Compared with other listings in Models.

## Evidence

| Signal | Value |
|---|---|
| Traffic rank (Tranco) | — |
| GitHub stars | — |
| Stars, last 90 days | — |
| Downloads, 30 days | 9.2K |
| Reviews | none yet |
| Last update | 416 days ago |
| Uptime, 30 days | — |
| Public pricing / Free tier / API / MCP | yes / yes / yes / no |

## RankShark review

Automated evaluation by RankShark · 2026-11-18 · method review-1.0 · https://rankshark.pro/how-we-review
We were not paid for this review.

As of 2026-11-18, DeepSeek V3.1 Terminus is a text model with a 163,840-token context window and listed usage rates of $0.27 per million input tokens and $1 per million output tokens. [E2; RankShark measurement, 2026-11-18]

DeepSeek V3.1 Terminus is an update to DeepSeek V3.1. The vendor says it addresses language consistency and agent-capability issues; its model card says the weights are licensed under MIT and describes running the model locally. [E1; E2]

### Pros

- The model card reports improvements on several agent-use benchmarks, including BrowseComp, SWE Verified, and Terminal-bench, compared with DeepSeek-V3.1.
- The model card says the weights are licensed under MIT and describes a local-running path.
- OpenRouter lists a 163,840-token context window and per-token usage prices.

### Cons

- The model card notes a known FP8 scale-format issue in self_attn.o_proj, which it says will be corrected in a future release.
- The OpenRouter listing specifies text input and output modalities, not image or audio modalities.
- No free plan or free trial stated on the pages we checked.
- Whether customer data is used for model training is not stated on the pages we checked.

### Pricing

| Plan | Price | Limits |
|---|---|---|
| OpenRouter per-token usage | $0.27 per 1 million input tokens; $1 per 1 million output tokens | The listing shows a 163,840-token context window. No per-request limits are stated. |

Checked 2026-11-18

### Sources

- https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Terminus (fetched 2026-11-18)
- https://openrouter.ai/deepseek/deepseek-v3.1-terminus (fetched 2026-11-18)

## Top alternatives

1. [Qwen3.8 27B](https://rankshark.pro/tools/qwen38-27b) — SharkScore 67.1. Qwen3.8 27B is an open-weight dense vision-language model from Qwen.
2. [Qwen3.6 35B A3B](https://rankshark.pro/tools/qwen36-35b-a3b) — SharkScore 65.5. Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t
3. [Qwen3.8 Flash](https://rankshark.pro/tools/qwen38-flash) — SharkScore 64.7. Qwen3.8 Flash is a multimodal reasoning model from Alibaba.
4. [Qwen3.6 27B](https://rankshark.pro/tools/qwen36-27b) — SharkScore 64.3. Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.
5. [gpt-oss](https://rankshark.pro/tools/gpt-oss) — SharkScore 63.5. OpenAI's open-weight reasoning models.

---
Source: https://rankshark.pro/tools/deepseek-v31-terminus · Method v2026-11-18.2: https://rankshark.pro/how-ranking-works · Payment never changes a rank.
