NOUMENOpen app
NOUMEN

DeepSeek · Open weights

DeepSeek V4 Flash

Added Apr 24, 2026Open weights

Compare models

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

Loading models…

Use in the app

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek 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)
137 tokens
Longer than 14% of 468 models

Side by side

DeepSeek V4 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 FlashDeepSeekThis modelGLM 5.2 Thinking TEEZ.aiRemove
ProviderDeepSeekZ.ai
Discovery tierOpen weightsOpen weights
AddedApr 24, 2026Jun 16, 2026
Limits
Context window1.05M1.05M
Max output384KBest131.07K
Average output137 tokens2K tokens
Pricing, USD per 1M tokens
Input$0.14Best$1.40
Output$0.28Best$4.40
Cache read$0.0028Best$0.70
Performance
Throughput74.5 tok/s—
Time to first token2.2 s—
Request success (24h)99.8%Best87.5%
Benchmark indexes
Intelligence Index34.3Best33.7
Coding Index69.1Best68.8
Capabilities
ReasoningYesYes
ToolsYesYes
Structured outputYesYes
Reasoning effortnone, high, maxlow, medium, high, xhigh, max

Public evaluations

Benchmarks

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

  • DeepSeek V4 Flash
  • GLM 5.2 Thinking TEE

Intelligence Index

  • DeepSeek V4 Flash34.3
  • GLM 5.2 Thinking TEE33.7

DeepSeek V4 Flash tested at max reasoning effort

DeepSeek V4 Flash: Better than 78% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • DeepSeek V4 Flash: 69.1Top
    • GLM 5.2 Thinking TEE: 68.8

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • DeepSeek V4 Flash: 54.0%Top
    • GLM 5.2 Thinking TEE: 28.4%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • DeepSeek V4 Flash: 23.0%Top
    • GLM 5.2 Thinking TEE: 6.2%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • DeepSeek V4 Flash: 1,257 EloTop
    • GLM 5.2 Thinking TEE: 1,227 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • DeepSeek V4 Flash: 1,433 EloTop
    • GLM 5.2 Thinking TEE: 1,373 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • DeepSeek V4 Flash: 11.0%Top
    • GLM 5.2 Thinking TEE: 10.4%

  • AA-LCRv1.1

    Reasoning across long documents

    • DeepSeek V4 Flash: 79.7%Top
    • GLM 5.2 Thinking TEE: 78.3%

  • MLCR-AA

    Long-context reasoning over medical records

    • DeepSeek V4 Flash: —
    • GLM 5.2 Thinking TEE: 12.8%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • DeepSeek V4 Flash: 38.6%
    • GLM 5.2 Thinking TEE: 41.1%Top

  • GPQA Diamond

    Graduate-level science questions

    • DeepSeek V4 Flash: 90.8%Top
    • GLM 5.2 Thinking TEE: 89.5%

  • IFBench

    Following precise output instructions

    • DeepSeek V4 Flash: —
    • GLM 5.2 Thinking TEE: 73.3%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • DeepSeek V4 Flash: 12.1%Top
    • GLM 5.2 Thinking TEE: 1.0%

  • SciCode

    Scientific computing in Python

    • DeepSeek V4 Flash: 50.3%
    • GLM 5.2 Thinking TEE: 51.2%Top

Legacy evaluations

  • Terminal-Bench Hard

    Earlier terminal task suite

    • DeepSeek V4 Flash: —
    • GLM 5.2 Thinking TEE: 50.8%

  • τ²-Bench Telecom

    Tool use in a customer-support simulation

    • DeepSeek V4 Flash: —
    • GLM 5.2 Thinking TEE: 99.1%

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • DeepSeek V4 Flash: 79.7%Top
    • GLM 5.2 Thinking TEE: 78.3%

Scores from Artificial Analysis, updated Oct 26, 2026. DeepSeek V4 Flash 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
74.5 tok/s
Faster than 49% of 254 models
Time to first token
2.2 s
Quicker than 71% of 254 models
Prompt cache hits
85.9%
About $0.0222 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 98.2%
  • 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",
    "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",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

DeepSeek

Other DeepSeek models, starting with the same family.