DeepSeek · Open weights
DeepSeek V3.1 Thinking
Thinking enabled version of Deepseek V3.1. DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. It does better at tool calling and agent tasks, and has higher thinking efficiency than its predecessor. Quantized at FP8.
- Tools
- Input
- Text
- Output
- Text
- Discovery tier
- Open weights
Pricing
USD per 1M tokens- Input
- $0.20
- 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)
- 483 tokens
- Longer than 48% of 468 models
Side by side
Compare models
Put DeepSeek V3.1 Thinking next to up to three other models. The comparison stays in the link, so you can share it.
Public evaluations
Benchmarks
Independent evaluation results, with how each score ranks among the models in the Noumen catalog.
Intelligence Index
13.5
Better than 34% of 326 scored models
Indexes
Math Index
89.7Composite of the math evaluations
Better than 87% of 118 scored models
Document reasoning
AA-LCRv1.1
56.7%Reasoning across long documents
Better than 35% of 309 scored models
Reasoning and knowledge
Humanity’s Last Exam
14.3%Expert-level questions across academic fields
Better than 40% of 323 scored models
GPQA Diamond
77.9%Graduate-level science questions
Better than 41% of 291 scored models
MMLU-Pro
85.1%Multi-subject knowledge and reasoning
Better than 87% of 132 scored models
IFBench
41.5%Following precise output instructions
Better than 31% of 215 scored models
Coding
LiveCodeBench
78.4%Recent competitive programming problems
Better than 79% of 129 scored models
Math
AIME 2025
89.7%Competition mathematics, 2025 problems
Better than 87% of 118 scored models
Legacy evaluations
Terminal-Bench Hard
25.0%Earlier terminal task suite
Better than 47% of 212 scored models
τ²-Bench Telecom
37.4%Tool use in a customer-support simulation
Better than 32% of 214 scored models
AA-LCR (unversioned)
56.7%Long-context reasoning, earlier grading
Better than 35% of 309 scored models
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
- 14.2 tok/s
- Faster than 4% of 253 models
- Time to first token
- 2.5 s
- Quicker than 66% of 253 models
- Prompt cache hits
- 63.9%
- Request success (24h)
- 100.0%
- 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: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: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.