NOUMENOpen app
NOUMEN

DeepSeek · Open weights

DeepSeek V4 Flash (Thinking)

Added Apr 24, 2026Open weights

Compare models

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

Loading models…

Use in the app

DeepSeek V4 Flash Thinking enables DeepSeek's reasoning mode on the efficiency-optimized Mixture-of-Experts model with a 1M-token context window, built for fast inference, high-throughput workloads, reasoning, coding, and agent workflows.

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

Pricing

USD per 1M tokens
Input
$0.14
Output
$0.28
Cache read
$0.0028

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
384K
Average output (7 days)
689 tokens
Longer than 61% of 465 models

Side by side

Compare models

Put DeepSeek V4 Flash (Thinking) 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…

TryGemini 3.6 FlashMuse Spark 1.1GLM 5.2 Thinking TEEAll 3

Public evaluations

Benchmarks

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

Intelligence Index

34.3

Tested at max reasoning effort

Better than 78% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    69.1

    Composite of the coding evaluations

    Better than 73% of 168 scored models

Agentic work

  • AutomationBench-AA

    54.0%

    Workflow automation, penalized for guardrail violations

    Better than 67% of 173 scored models

  • AutomationBench-AA tasks completed

    23.0%

    Workflows finished end to end without a guardrail violation

    Better than 67% of 173 scored models

  • AA-Briefcasev1.1

    1,257 Elo

    Agentic knowledge work, rated head to head

    Better than 63% of 166 scored models

  • GDPval-AAv2.1

    1,433 Elo

    Economically valuable occupational tasks, rated head to head

    Better than 66% of 187 scored models

Document reasoning

  • GDP.pdf

    11.0%

    Professional reasoning over PDF documents, all-pass rate

    Better than 45% of 171 scored models

  • AA-LCRv1.1

    79.7%

    Reasoning across long documents

    Better than 75% of 309 scored models

Reasoning and knowledge

  • Humanity’s Last Exam

    38.6%

    Expert-level questions across academic fields

    Better than 72% of 323 scored models

  • GPQA Diamond

    90.8%

    Graduate-level science questions

    Better than 79% of 291 scored models

Coding

  • Terminal-Benchv4.0

    12.1%

    Practical software engineering in a terminal

    Better than 62% of 171 scored models

  • SciCode

    50.3%

    Scientific computing in Python

    Better than 48% of 174 scored models

Legacy evaluations

  • AA-LCR (unversioned)

    79.7%

    Long-context reasoning, earlier grading

    Better than 75% of 309 scored models

Scores from Artificial Analysis, updated Oct 26, 2026. DeepSeek V4 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
65.5 tok/s
Faster than 46% of 250 models
Time to first token
1.1 s
Quicker than 95% of 250 models
Prompt cache hits
37.4%
About $0.0887 per 1M input tokens with caching
Request success (24h)
99.4%
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 88.7%
  • 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-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-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.