NOUMENOpen app
NOUMEN

DeepSeek · Open weights

DeepSeek V4.1 Flash

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)
376 tokens
Longer than 38% of 465 models

Side by side

DeepSeek V4.1 Flash 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 FlashDeepSeekThis modelLing 3.0 Flash VLinclusionaiRemove
ProviderDeepSeekinclusionai
Discovery tierOpen weightsOpen weights
AddedSep 8, 2026Sep 9, 2026
Limits
Context window1MBest262.14K
Max output384KBest32.77K
Average output376 tokens843 tokens
Pricing, USD per 1M tokens
Input$0.09$0.06Best
Output$0.25$0.18Best
Cache read$0.006Best$0.012
Performance
Throughput206.3 tok/s—
Time to first token1.8 s—
Request success (24h)99.8%Best99.5%
Benchmark indexes
Intelligence Index24.7Best24.6
Coding Index—57.0
Capabilities
ReasoningYesYes
ToolsYesYes
VisionYesYes
Structured outputYesNo
Video inputNoYes
Reasoning effortnone, low, high, maxnone, low, medium, high

Public evaluations

Benchmarks

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

  • DeepSeek V4.1 Flash
  • Ling 3.0 Flash VL

Intelligence Index

  • DeepSeek V4.1 Flash24.7
  • Ling 3.0 Flash VL24.6

DeepSeek V4.1 Flash: Better than 60% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • DeepSeek V4.1 Flash: —
    • Ling 3.0 Flash VL: 57.0

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • DeepSeek V4.1 Flash: 47.8%Top
    • Ling 3.0 Flash VL: 15.7%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • DeepSeek V4.1 Flash: 14.2%Top
    • Ling 3.0 Flash VL: 1.1%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • DeepSeek V4.1 Flash: 1,118 EloTop
    • Ling 3.0 Flash VL: 984 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • DeepSeek V4.1 Flash: 1,340 EloTop
    • Ling 3.0 Flash VL: 1,161 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • DeepSeek V4.1 Flash: 3.8%
    • Ling 3.0 Flash VL: 8.4%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • DeepSeek V4.1 Flash: 55.3%
    • Ling 3.0 Flash VL: 78.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • DeepSeek V4.1 Flash: —
    • Ling 3.0 Flash VL: 5.0%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • DeepSeek V4.1 Flash: 10.8%
    • Ling 3.0 Flash VL: 22.0%Top

  • GPQA Diamond

    Graduate-level science questions

    • DeepSeek V4.1 Flash: —
    • Ling 3.0 Flash VL: 86.2%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • DeepSeek V4.1 Flash: 5.6%Top
    • Ling 3.0 Flash VL: 0.0%

  • SciCode

    Scientific computing in Python

    • DeepSeek V4.1 Flash: 35.5%
    • Ling 3.0 Flash VL: 44.2%Top

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • DeepSeek V4.1 Flash: 55.3%
    • Ling 3.0 Flash VL: 78.3%Top

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
206.3 tok/s
Faster than 83% of 250 models
Time to first token
1.8 s
Quicker than 84% of 250 models
Prompt cache hits
86.7%
About $0.0172 per 1M input tokens with caching
Request success (24h)
99.8%
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 98.6%
  • 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/deepseek-v4.1-flash",
    "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",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

DeepSeek

Other DeepSeek models, starting with the same family.