DeepSeek V3.1 Terminus
Provider: DeepSeek CN
Overview
DeepSeek V3.1 Terminus is a flagship-class model handling general workloads with a 163,840-token context and thinking capabilities. Third-party hosting prices average $0.27 per million input tokens and $1.00 per million output tokens.
Strengths
- Supports 163,840-token context window
- Outputs up to 147,456 tokens
- Features built-in thinking capability
- Includes function-calling and JSON mode
Best use cases
- Complex agent workflows
- Structured data extraction tasks
- Long-form document analysis
Pricing position
Output pricing matches DeepSeek V3 0324 at $1.00 per million tokens, while output cost is half of Alibaba's Qwen3.5-122B-A10B ($2.08).
Caveats
No free tier is available, and context length is smaller than the 1,048,576-token Flash series.
Notes drafted by an LLM from the figures on this page (2026-11-10) and rewritten when the price changes.
Key facts
- Price basis
- Median third-party host price (no first-party API)
- Max output
- 147K tokens
- Knowledge cutoff
- 2025-03-31
- Listed on OpenRouter
- 2025-09-22
- Tracked since
- 2026-05-08
- Last updated
- 2026-11-10
Features
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.08 |
| 1M (small app) | 1 | 0.5 | $0.77 |
| 10M (mid scale) | 10 | 5 | $7.70 |
| 100M (large) | 100 | 50 | $77.00 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from DeepSeek
Similar-priced models
Source: OpenRouter API (deepseek/deepseek-v3.1-terminus)