DeepSeek: DeepSeek V3.1 Terminus
by DeepSeekDeepSeek: DeepSeek V3.1 Terminus is a large language model from DeepSeek. It costs $0.270 per million input tokens and $1.00 per million output tokens. Its context window is 164K tokens.
- Input / 1M tokens
- $0.270
- Output / 1M tokens
- $1.00
- Cached input / 1M
- $0.135
- Context window
- 164K
On repeated prefixes
tokens
Who serves it cheapest
4 hosts serve DeepSeek V3.1 Terminus. Same weights, same API - the price difference is pure margin and routing.
| Provider | Input / 1M | Output / 1M | Context | Throughput | Uptime 24h |
|---|---|---|---|---|---|
| SiliconFlowCheapestfp8 | $0.270 | $1.00 | 164K | - | 98.2% |
| Novitafp8 | $0.270 | $1.00 | 131K | - | 99.9% |
| AtlasCloudfp8 | $0.300 | $0.950 | 131K | - | 98.4% |
| StreamLake | $0.343 | $1.03 | 128K | - | 98.7% |
The spread between SiliconFlow and StreamLake is 1.1× for identical weights. Quantization and context limits differ, so check both columns before switching.
Benchmarks
Independent scores published alongside the catalogue.
- Intelligence index
- 15.4
- Coding index
- 43.5
- Agentic index
- 8.9
About 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 addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
Specifications
| Model ID | deepseek/deepseek-v3.1-terminus |
|---|---|
| Provider | DeepSeek |
| Context window | 164K tokens |
| Max output | 33K tokens |
| Input modalities | text |
| Output modalities | text |
| Knowledge cutoff | 2025-03-31 |
| Open weights | Yes - deepseek-ai/DeepSeek-V3.1-Terminus |
| Released | September 22, 2025 |
Cheaper alternatives
Models that cost less than DeepSeek V3.1 Terminus while keeping at least half its context window and every input modality it supports.
Frequently asked
How much does DeepSeek: DeepSeek V3.1 Terminus cost?
$0.270 per million input tokens and $1.00 per million output tokens. Cached input reads cost $0.135 per million tokens.
What is the context window of DeepSeek: DeepSeek V3.1 Terminus?
164K tokens, with up to 33K tokens of output per request.
Which provider serves DeepSeek: DeepSeek V3.1 Terminus cheapest?
SiliconFlow at $0.270 per million input tokens - 1.1× cheaper than StreamLake, the most expensive of the 4 hosts serving it.
Confirm against the source: DeepSeek official pricing.