NOUMENOpen app
NOUMEN

DeepSeek · Open weights

DeepSeek V3.1

Added Jul 26, 2025Open weights

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

Use in the app

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. This is the non-thinking version. Quantized at FP8.

  • Tools
  • PDF input
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)
293 tokens
Longer than 30% of 465 models

Side by side

Compare models

Put DeepSeek V3.1 next to up to three other models. The comparison stays in the link, so you can share it.

Compare models

Choose up to 3 models to compare.0 of 3 chosen

Loading models…

TryGrok 4.3Qwen3.5 9BGPT 5.1All 3

Public evaluations

Benchmarks

Independent evaluation results, with how each score ranks among the models in the Noumen catalog.

Intelligence Index

13.7

Better than 34% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Math Index

    49.7

    Composite of the math evaluations

    Better than 47% of 118 scored models

Document reasoning

  • AA-LCRv1.1

    47.0%

    Reasoning across long documents

    Better than 26% of 309 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    6.7%

    Expert-level questions across academic fields

    Better than 23% of 323 scored models

  • GPQA Diamond

    73.5%

    Graduate-level science questions

    Better than 32% of 291 scored models

  • MMLU-Pro

    83.3%

    Multi-subject knowledge and reasoning

    Better than 74% of 132 scored models

  • IFBench

    37.8%

    Following precise output instructions

    Better than 20% of 215 scored models

Coding

  • LiveCodeBench

    57.7%

    Recent competitive programming problems

    Better than 54% of 129 scored models

Math

  • AIME 2025

    49.7%

    Competition mathematics, 2025 problems

    Better than 47% of 118 scored models

Legacy evaluations

  • Terminal-Bench Hard

    24.2%

    Earlier terminal task suite

    Better than 45% of 212 scored models

  • τ²-Bench Telecom

    34.8%

    Tool use in a customer-support simulation

    Better than 28% of 214 scored models

  • AA-LCR (unversioned)

    47.0%

    Long-context reasoning, earlier grading

    Better than 26% 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
14.4 tok/s
Faster than 4% of 250 models
Time to first token
2.1 s
Quicker than 71% of 250 models
Prompt cache hits
37.1%
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.

Hourly request success · last 72 hoursLowest hour 96.6%
  • 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.

Read the quickstart
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",
    "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",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

DeepSeek

Other DeepSeek models, starting with the same family.