DeepSeek · Open weights
DeepSeek V3.1 Terminus (Thinking)
Thinking-enabled DeepSeek-V3.1-Terminus with improved language consistency, upgraded Code/Search Agents, and stronger stability and reliability versus V3.1. FP8.
- Tools
- Structured output
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.25
- Output
- $0.70
Reference prices as published by the model provider. API example
Specifications
- Context window
- 128K
- Max output
- 65.5K
- Average output (7 days)
- 362 tokens
- Longer than 37% of 468 models
Side by side
DeepSeek V3.1 Terminus (Thinking) compared
Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.
| DeepSeek V3.1 Terminus (Thinking)DeepSeekThis model | DeepSeek V3.1 TerminusDeepSeekRemove | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Discovery tier | Open weights | Open weights |
| Added | Jan 1, 2024 | Aug 2, 2025 |
| Limits | ||
| Context window | 128K | 128K |
| Max output | 65.54K | 65.54K |
| Average output | 362 tokens | 364 tokens |
| Pricing, USD per 1M tokens | ||
| Input | $0.25 | $0.25 |
| Output | $0.70 | $0.70 |
| Performance | ||
| Throughput | 21.6 tok/sBest | 20.2 tok/s |
| Time to first token | 6.4 s | 2.7 sBest |
| Request success (24h) | 99.5% | 100.0%Best |
| Benchmark indexes | ||
| Intelligence Index | 14.8Best | 13.9 |
| Coding Index | 43.5 | — |
| Math Index | 89.7Best | 53.7 |
| Capabilities | ||
| Tools | Yes | Yes |
| Structured output | Yes | Yes |
| Reasoning effort | — | — |
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
- DeepSeek V3.1 Terminus (Thinking)
- DeepSeek V3.1 Terminus
Intelligence Index
- DeepSeek V3.1 Terminus (Thinking)14.8
- DeepSeek V3.1 Terminus13.9
DeepSeek V3.1 Terminus (Thinking): Better than 37% of 326 scored models
Indexes
Coding Index
Composite of the coding evaluations
- DeepSeek V3.1 Terminus (Thinking): 43.5
- DeepSeek V3.1 Terminus: —
Math Index
Composite of the math evaluations
- DeepSeek V3.1 Terminus (Thinking): 89.7Top
- DeepSeek V3.1 Terminus: 53.7
Agentic work
AutomationBench-AA
Workflow automation, penalized for guardrail violations
- DeepSeek V3.1 Terminus (Thinking): 2.7%
- DeepSeek V3.1 Terminus: —
AutomationBench-AA tasks completed
Workflows finished end to end without a guardrail violation
- DeepSeek V3.1 Terminus (Thinking): 0.2%
- DeepSeek V3.1 Terminus: —
AA-Briefcasev1.1
Agentic knowledge work, rated head to head
- DeepSeek V3.1 Terminus (Thinking): 458 Elo
- DeepSeek V3.1 Terminus: —
GDPval-AAv2.1
Economically valuable occupational tasks, rated head to head
- DeepSeek V3.1 Terminus (Thinking): 709 Elo
- DeepSeek V3.1 Terminus: —
Document reasoning
GDP.pdf
Professional reasoning over PDF documents, all-pass rate
- DeepSeek V3.1 Terminus (Thinking): 5.4%
- DeepSeek V3.1 Terminus: —
AA-LCRv1.1
Reasoning across long documents
- DeepSeek V3.1 Terminus (Thinking): 69.3%Top
- DeepSeek V3.1 Terminus: 45.3%
Reasoning and knowledge
Humanity’s Last Exam
Expert-level questions across academic fields
- DeepSeek V3.1 Terminus (Thinking): 16.4%Top
- DeepSeek V3.1 Terminus: 8.7%
GPQA Diamond
Graduate-level science questions
- DeepSeek V3.1 Terminus (Thinking): 79.2%Top
- DeepSeek V3.1 Terminus: 75.1%
MMLU-Pro
Multi-subject knowledge and reasoning
- DeepSeek V3.1 Terminus (Thinking): 85.1%Top
- DeepSeek V3.1 Terminus: 83.6%
IFBench
Following precise output instructions
- DeepSeek V3.1 Terminus (Thinking): 57.0%Top
- DeepSeek V3.1 Terminus: 41.2%
Coding
Terminal-Benchv4.0
Practical software engineering in a terminal
- DeepSeek V3.1 Terminus (Thinking): 0.0%
- DeepSeek V3.1 Terminus: —
SciCode
Scientific computing in Python
- DeepSeek V3.1 Terminus (Thinking): 38.0%
- DeepSeek V3.1 Terminus: —
LiveCodeBench
Recent competitive programming problems
- DeepSeek V3.1 Terminus (Thinking): 79.8%Top
- DeepSeek V3.1 Terminus: 52.9%
Math
AIME 2025
Competition mathematics, 2025 problems
- DeepSeek V3.1 Terminus (Thinking): 89.7%Top
- DeepSeek V3.1 Terminus: 53.7%
Legacy evaluations
Terminal-Bench Hard
Earlier terminal task suite
- DeepSeek V3.1 Terminus (Thinking): 30.3%
- DeepSeek V3.1 Terminus: 31.8%Top
τ²-Bench Telecom
Tool use in a customer-support simulation
- DeepSeek V3.1 Terminus (Thinking): 37.1%Top
- DeepSeek V3.1 Terminus: 37.1%Top
AA-LCR (unversioned)
Long-context reasoning, earlier grading
- DeepSeek V3.1 Terminus (Thinking): 69.3%Top
- DeepSeek V3.1 Terminus: 45.3%
Scores from Artificial Analysis, updated Oct 26, 2026. Artificial Analysis
Live routing data
Performance and reliability
Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.
- Throughput
- 21.6 tok/s
- Faster than 14% of 254 models
- Time to first token
- 6.4 s
- Quicker than 27% of 254 models
- Prompt cache hits
- 73.2%
- Request success (24h)
- 99.5%
- Reliable
Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.
- Healthy (98% or more)
- Degraded (90–98%)
- Down (under 90%)
- No requests
Developers
Use it through the API
Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.
curl https://www.noumen.xyz/api/v1/chat/completions \
-H "Authorization: Bearer $NOUMEN_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-ai/DeepSeek-V3.1-Terminus:thinking",
"messages": [{ "role": "user", "content": "Explain this stack trace." }]
}'import os
from openai import OpenAI
client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
model="deepseek-ai/DeepSeek-V3.1-Terminus:thinking",
messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)DeepSeek
Related models
Other DeepSeek models, starting with the same family.