NOUMENOpen app
NOUMEN

DeepSeek · Open weights

DeepSeek V4.1 Flash Thinking

Added Sep 8, 2026Open weights

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

Use in the app

DeepSeek V4.1 Flash supports text and image input, reasoning, tool calling, and structured output with a 1M-token context window. This is a rate-limited beta with limited capacity, intended for testing rather than production use.

  • Reasoning
  • Tools
  • Vision
  • Structured output
Input
Text, Images
Output
Text
Reasoning effort
none · low · high · max
Discovery tier
Open weights

Pricing

USD per 1M tokens
Input
$0.09
Output
$0.25
Cache read
$0.006

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
384K
Average output (7 days)
785 tokens
Longer than 64% of 465 models

Side by side

DeepSeek V4.1 Flash Thinking compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Compare models

Choose up to 3 models to compare.1 of 3 chosen

Loading models…

DeepSeek V4.1 Flash ThinkingDeepSeekThis modelDeepSeek V4.1 Flash 1017 ThinkingDeepSeekRemove
ProviderDeepSeekDeepSeek
Discovery tierOpen weightsOpen weights
AddedSep 8, 2026Oct 17, 2026
Limits
Context window1M1.05MBest
Max output384K393.22KBest
Average output785 tokens1.2K tokens
Pricing, USD per 1M tokens
Input$0.09Best$0.10
Output$0.25Best$0.60
Cache read$0.006$0.003Best
Performance
Throughput261.1 tok/s261.1 tok/s
Time to first token2.7 s2.4 sBest
Request success (24h)99.9%Best99.8%
Benchmark indexes
Intelligence Index39.545.1Best
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesYes
Reasoning effortnone, low, high, maxnone, low, high, max

Public evaluations

Benchmarks

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

  • DeepSeek V4.1 Flash Thinking
  • DeepSeek V4.1 Flash 1017 Thinking

Intelligence Index

  • DeepSeek V4.1 Flash Thinking39.5
  • DeepSeek V4.1 Flash 1017 Thinking45.1

DeepSeek V4.1 Flash Thinking tested at max reasoning effort

DeepSeek V4.1 Flash Thinking: Better than 84% of 326 scored models

3.8Catalog models by score55.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • DeepSeek V4.1 Flash Thinking: 68.9%Top
    • DeepSeek V4.1 Flash 1017 Thinking: 66.6%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • DeepSeek V4.1 Flash Thinking: 35.5%
    • DeepSeek V4.1 Flash 1017 Thinking: 36.7%Top

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • DeepSeek V4.1 Flash Thinking: 1.7%
    • DeepSeek V4.1 Flash 1017 Thinking: —

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • DeepSeek V4.1 Flash Thinking: 1,419 Elo
    • DeepSeek V4.1 Flash 1017 Thinking: 1,570 EloTop

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • DeepSeek V4.1 Flash Thinking: 1,600 Elo
    • DeepSeek V4.1 Flash 1017 Thinking: 1,746 EloTop

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • DeepSeek V4.1 Flash Thinking: 12.8%
    • DeepSeek V4.1 Flash 1017 Thinking: 17.2%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • DeepSeek V4.1 Flash Thinking: 84.0%Top
    • DeepSeek V4.1 Flash 1017 Thinking: 82.7%

  • MLCR-AA

    Long-context reasoning over medical records

    • DeepSeek V4.1 Flash Thinking: 23.9%
    • DeepSeek V4.1 Flash 1017 Thinking: 26.7%Top

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • DeepSeek V4.1 Flash Thinking: 39.2%
    • DeepSeek V4.1 Flash 1017 Thinking: 43.3%Top

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • DeepSeek V4.1 Flash Thinking: 26.8%
    • DeepSeek V4.1 Flash 1017 Thinking: 33.8%Top

  • SciCode

    Scientific computing in Python

    • DeepSeek V4.1 Flash Thinking: 51.9%
    • DeepSeek V4.1 Flash 1017 Thinking: 55.9%Top

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • DeepSeek V4.1 Flash Thinking: 84.0%Top
    • DeepSeek V4.1 Flash 1017 Thinking: 82.7%

Scores from Artificial Analysis, updated Oct 26, 2026. DeepSeek V4.1 Flash Thinking was tested at max reasoning effort; compare scores measured at the same effort.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
261.1 tok/s
Faster than 90% of 250 models
Time to first token
2.7 s
Quicker than 62% of 250 models
Prompt cache hits
86.7%
About $0.0171 per 1M input tokens with caching
Request success (24h)
99.9%
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 98.4%
  • 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/deepseek-v4.1-flash:thinking",
    "reasoning_effort": "none",
    "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/deepseek-v4.1-flash:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

DeepSeek

Other DeepSeek models, starting with the same family.