DeepSeek
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...
Cost / 1M tokens
Low usage$0.27
input
—
cached input
$1.00
output
Context Window
164K
Up to 147K max output
Modalities
text → text
DeepSeek tokenizer
Quickstart & API
deepseek/deepseek-v3.1-terminusBest for & Strengths
Key Strengths
Recommended Workloads in ChatOSS
- Coding agents
- Complex reasoning & debugging
- Open-source AI workflows
Verified Evaluations
Benchmarks & Frontier Comparison
How DeepSeek V3.1 Terminus compares against leading open-weight and proprietary frontier models across independent agentic coding and reasoning suites.
| Benchmark (Metric) | DeepSeek V3.1 Terminus | DeepSeek V4.1 Flash | GLM 5.3 | Kimi K3.1 Pro | Claude Opus 5.5 |
|---|---|---|---|---|---|
| Agentic & Software Engineering | |||||
| ChatOSS Agentic Coding Index (%) | — | 63.2% | 58.3% | 65% | 74.1% |
| SWE-Bench Verified (%) | — | 91.5% | 95.4% | 94.8% | 97% |
| DeepSWE v1.1 (Pass@1 %) | — | 77% | 69% | 73.5% | 74.2% |
| Vibe Code Bench v1.1 (%) | — | 87.7% | 78.1% | 88.4% | 90.3% |
| Terminal-Bench 4.0 (%) | — | 42.3% | 42% | 46.2% | 65.2% |
| Code Migration (%) | — | 45.6% | 44.2% | 52% | 66.7% |
| Intelligence & Token Economics | |||||
| Artificial Analysis Intelligence Index (0–100) | 14.8 | 39.5 | 44.8 | 55.1 | 57.6 |
| Input Price (/ 1M tokens) | $0.27 | $0.15 | $1.40 | $2.00 | $4.00 |
| Output Price (/ 1M tokens) | $1.00 | $0.60 | $4.40 | $10.00 | $20.00 |
Artificial Analysis Intelligence Index
Artificial Analysis
Design Arena: 3D
Design Arena · Rank #72 (56% win)
Design Arena: Code Generation
Design Arena · Rank #73 (56% win)
Design Arena: Data Visualization
Design Arena · Rank #73 (53.4% win)
Design Arena: Game Dev
Design Arena · Rank #89 (52.5% win)
Active Provider Endpoints (2)
Upstream inference providers serving DeepSeek V3.1 Terminus, with per-provider pricing, context limits, quantization, and 24-hour uptime.
| Provider | Input / 1M | Output / 1M | Cache Read / 1M | Context | Max Output | Quantization | Uptime (24h) |
|---|---|---|---|---|---|---|---|
SiliconFlow siliconflow/fp8 | $0.27 | $1.00 | — | 164K | 147K | fp8 | 97.3% |
StreamLake streamlake | $0.343 | $1.03 | — | 128K | 32K | — | 99.9% |
Supported API Parameters
Parameters accepted by this model when called through ChatOSS or OpenRouter.
Compare Similar Models
Browse all models →DeepSeek
DeepSeek V4.1 Flash 1017
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
DeepSeek
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
DeepSeek
DeepSeek V4 Flash Vision Exp
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the base model on text capabilities including agents,...
DeepSeek
DeepSeek V4 Pro 0813
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Anthropic
Claude Opus 5.5
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code...
Moonshot AI
Kimi K3.1 Pro
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...