NOUMENOpen app
NOUMEN

DeepSeek · Open weights

DeepSeek Flash Latest

Added Aug 2, 2026Open weights

Compare models

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

Loading models…

Use in the app

Moving alias for DeepSeek V4.1 Flash 1017, with text and image input, tool calling, structured output, and optional reasoning. Zero data retention and JSON Schema output are available on eligible routes; output limits and reasoning levels depend on the selected route.

  • 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
$0.10
Output
$0.60
Cache read
$0.003

Reference prices as published by the model provider. API example

Specifications

Context window
1M
Max output
393.2K

Side by side

DeepSeek Flash Latest 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 Flash LatestDeepSeekThis modelInklingthinkingmachinesRemove
ProviderDeepSeekthinkingmachines
Discovery tierOpen weightsOpen weights
AddedAug 2, 2026Jul 15, 2026
Limits
Context window1.05MBest1.05M
Max output393.22KBest32.77K
Average output—596 tokens
Pricing, USD per 1M tokens
Input$0.10Best$1.00
Output$0.60Best$4.05
Cache read$0.003Best$0.17
Performance
Throughput252.2 tok/s—
Time to first token2.2 s—
Request success (24h)99.7%100.0%Best
Benchmark indexes
Intelligence Index24.725.0Best
Coding Index—52.1
Capabilities
ReasoningYesNo
ToolsYesYes
VisionYesYes
Structured outputYesYes
Audio inputNoYes
Reasoning effortnone, low, high, max—

Public evaluations

Benchmarks

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

  • DeepSeek Flash Latest
  • Inkling

Intelligence Index

  • DeepSeek Flash Latest24.7
  • Inkling25.0

DeepSeek Flash Latest: Better than 60% of 326 scored models

3.8Catalog models by score55.1

Indexes

  • Coding Index

    Composite of the coding evaluations

    • DeepSeek Flash Latest: —
    • Inkling: 52.1

Agentic work

  • AutomationBench-AA

    Workflow automation, penalized for guardrail violations

    • DeepSeek Flash Latest: 47.8%Top
    • Inkling: 5.0%

  • AutomationBench-AA tasks completed

    Workflows finished end to end without a guardrail violation

    • DeepSeek Flash Latest: 14.2%Top
    • Inkling: 0.3%

  • Harvey LAB-AAv1.1

    Legal tasks passed in full, with no material hallucination

    • DeepSeek Flash Latest: —
    • Inkling: 0.0%

  • AA-Briefcasev1.1

    Agentic knowledge work, rated head to head

    • DeepSeek Flash Latest: 1,118 EloTop
    • Inkling: 832 Elo

  • GDPval-AAv2.1

    Economically valuable occupational tasks, rated head to head

    • DeepSeek Flash Latest: 1,340 EloTop
    • Inkling: 1,072 Elo

Document reasoning

  • GDP.pdf

    Professional reasoning over PDF documents, all-pass rate

    • DeepSeek Flash Latest: 3.8%
    • Inkling: 12.8%Top

  • AA-LCRv1.1

    Reasoning across long documents

    • DeepSeek Flash Latest: 55.3%
    • Inkling: 77.3%Top

  • MLCR-AA

    Long-context reasoning over medical records

    • DeepSeek Flash Latest: —
    • Inkling: 6.1%

Reasoning and knowledge

  • Humanity’s Last Exam

    Expert-level questions across academic fields

    • DeepSeek Flash Latest: 10.8%
    • Inkling: 31.9%Top

  • GPQA Diamond

    Graduate-level science questions

    • DeepSeek Flash Latest: —
    • Inkling: 87.2%

Coding

  • Terminal-Benchv4.0

    Practical software engineering in a terminal

    • DeepSeek Flash Latest: 5.6%Top
    • Inkling: 1.0%

  • SciCode

    Scientific computing in Python

    • DeepSeek Flash Latest: 35.5%
    • Inkling: 47.0%Top

Legacy evaluations

  • AA-LCR (unversioned)

    Long-context reasoning, earlier grading

    • DeepSeek Flash Latest: 55.3%
    • Inkling: 77.3%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
252.2 tok/s
Faster than 90% of 254 models
Time to first token
2.2 s
Quicker than 71% of 254 models
Prompt cache hits
90.2%
About $0.0125 per 1M input tokens with caching
Request success (24h)
99.7%
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 98.5%
  • 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-latest",
    "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-latest",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

DeepSeek

Other DeepSeek models, starting with the same family.