Enterprise DNAEnterprise DNA
DeepSeek logo

Models · Best vision

DeepSeek V4.1 Flash

by DeepSeek

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.

Visit DeepSeek ↗

Our verdict

Not reviewed yet

We have not reviewed DeepSeek V4.1 Flash yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About DeepSeek V4.1 Flash

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.

Notes

DeepSeek V4.1 Flash is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.051 per million tokens
Checked OpenRouter models API
Output price
$0.567 per million tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.013 per million cached input tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.135 per million input tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.540 per million output tokens
Checked OpenRouter models API
Price on baidu
$0.0028 per million cached input tokens
Checked OpenRouter models API
Price on baidu
$0.140 per million input tokens
Checked OpenRouter models API
Price on baidu
$0.559 per million output tokens
Checked OpenRouter models API
Price on baseten
$0.0070 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
89.8% (for 9 Sept 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
67.4% (for 9 Sept 2026)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
42.9% (for 9 Sept 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `deepseek/deepseek-v4.1-flash`.

  • openrouter · deepseek/deepseek-v4.1-flash · Docs

OpenRouter id: deepseek/deepseek-v4.1-flash

Price

What DeepSeek V4.1 Flash costs, over time

Input price

$0.150 to $0.051

US dollars per million input tokens. 20 Sept 2026 to 10 Nov 2026, 38 days.

Source: OpenRouter models API. Checked .

Output price

$0.600 to $0.567

US dollars per million output tokens. 20 Sept 2026 to 10 Nov 2026, 38 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
atlas-cloudCached input$0.013 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudInput$0.135 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudOutput$0.540 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
baiduCached input$0.0028 per million cached input tokensSince 10 Nov 20269 changesOpenRouter models API
baiduInput$0.140 per million input tokensSince 10 Nov 20269 changesOpenRouter models API
baiduOutput$0.559 per million output tokensSince 10 Nov 20269 changesOpenRouter models API
basetenCached input$0.0070 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenInput$0.300 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenOutput$1.20 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
cohereCached input$0.0030 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cohereInput$0.195 per million input tokensSince 10 Nov 20261 changeOpenRouter models API
cohereOutput$0.660 per million output tokensSince 10 Nov 20261 changeOpenRouter models API
coreweaveCached input$0.0020 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveInput$0.130 per million input tokensSince 27 Oct 20261 changeOpenRouter models API
coreweaveOutput$0.650 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
crusoeCached input$0.0070 per million cached input tokensSince 1 Nov 20262 changesOpenRouter models API
crusoeInput$0.290 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
crusoeOutput$1.20 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
decartCached input$0.018 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
decartInput$0.090 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
decartOutput$0.180 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraCached input$0.0034 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.112 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$0.336 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanCached input$0.0060 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanInput$0.225 per million input tokensSince 27 Oct 20261 changeOpenRouter models API
digitaloceanOutput$0.900 per million output tokensSince 27 Oct 20261 changeOpenRouter models API
fireworksCached input$0.0042 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
fireworksInput$0.210 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
fireworksOutput$0.840 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudCached input$0.0036 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudInput$0.180 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudOutput$0.720 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexCached input$0.030 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexInput$0.300 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
google-vertexOutput$1.20 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
inference-netCached input$0.0080 per million cached input tokensSince 1 Nov 20263 changesOpenRouter models API
inference-netInput$0.103 per million input tokensSince 1 Nov 20263 changesOpenRouter models API
inference-netOutput$0.600 per million output tokensSince 1 Nov 20265 changesOpenRouter models API
makoraCached input$0.0058 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
makoraInput$0.260 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
makoraOutput$1.17 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
mancerCached input$0.050 per million cached input tokensSince 9 Nov 20261 changeOpenRouter models API
mancerInput$0.212 per million input tokensSince 11 Nov 20264 changesOpenRouter models API
mancerOutput$0.750 per million output tokensSince 10 Nov 20262 changesOpenRouter models API
modalCached input$0.030 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
modalInput$0.300 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
modalOutput$1.20 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
modelrunCached input$0.0060 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
modelrunInput$0.170 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much DeepSeek V4.1 Flash is used

Tokens served a day

3.1T to 2.3T

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How DeepSeek V4.1 Flash scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index24.7indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,463EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena web development rating (Elo)1,664EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena vision rating (Elo)1,279EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Apex agents (best-across-versions)39.5percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Arc agi (best-across-versions)94.5percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)72.9percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)48percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)89.9percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)43.9percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)26.8percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)67.4percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Show 9 more scores
ScoreValueSourceChecked
Furniture assembly (best-across-versions)34.2percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)89.8percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Lmca (best-across-versions)47percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)43percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated98.3percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)54percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)42.9percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Surface evolver bench (best-across-versions)46.3percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Weirdml v3 (best-across-versions)11.6percentAs of 9 Sept 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Compare

Compare DeepSeek V4.1 Flash side by side

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    cached input per mtok: 0.0105 to 0.0021

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 0.05 to 0.07

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.2 to 0.2125

    Source: OpenRouter models API

  4. Price changed

    output per mtok: 0.96 to 0.64

    Source: OpenRouter models API

  5. Price changed

    cached input per mtok: 0.0075 to 0.0105

    Source: OpenRouter models API

  6. Price changed

    output per mtok: 0.3 to 0.42

    Source: OpenRouter models API

  7. Price changed

    input per mtok: 0.075 to 0.105

    Source: OpenRouter models API

  8. Price changed

    cached input per mtok: 0.005 to 0.006

    Source: OpenRouter models API

  9. Price changed

    output per mtok: 0.7 to 0.8

    Source: OpenRouter models API

  10. Price changed

    input per mtok: 0.024 to 0.05

    Source: OpenRouter models API

  11. Price changed

    output per mtok: 0.5 to 0.75

    Source: OpenRouter models API

  12. Price changed

    input per mtok: 0.125 to 0.2

    Source: OpenRouter models API

  13. Price changed

    output per mtok: 1.2 to 0.66

    Source: OpenRouter models API

  14. Price changed

    input per mtok: 0.3 to 0.195

    Source: OpenRouter models API

  15. Price changed

    cached input per mtok: 0.005994 to 0.002796

    Source: OpenRouter models API

  16. Price changed

    output per mtok: 1.1988 to 0.5592

    Source: OpenRouter models API

  17. Price changed

    input per mtok: 0.2997 to 0.1398

    Source: OpenRouter models API

  18. Price changed

    output per mtok: 1.2 to 0.567

    Source: OpenRouter models API

  19. Price changed

    input per mtok: 0.3 to 0.051

    Source: OpenRouter models API

  20. Price changed

    cached input per mtok: 0.015 to 0.0075

    Source: OpenRouter models API

In the AI Pulse

Recent daily briefs from the Enterprise DNA AI Pulse that mention this. The short daily read on what is actually happening in AI.

See today's AI Pulse →

USAGE / OPENROUTER

How much DeepSeek V4.1 Flash is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
16.9T ▲8.3%
Requests, last 7 days
523M
Tool calls, last 7 days
144M
People's vote
1463
Average cost per request
13.8¢
Price per million tokens
$0.051 in · $0.567 out
05T10T19 Sept: 3.1T tokens, 45.6M requests20 Sept: 2.5T tokens, 39.9M requests21 Sept: 2.4T tokens, 46.5M requests22 Sept: 2.7T tokens, 45M requests23 Sept: 2.8T tokens, 49.1M requests24 Sept: 2.8T tokens, 49.7M requests25 Sept: 3T tokens, 47M requests26 Sept: 2.5T tokens, 42M requests27 Sept: 3.4T tokens, 62.7M requests28 Sept: 3.7T tokens, 64.5M requests29 Sept: 3.9T tokens, 67.4M requests30 Sept: 3.5T tokens, 62.3M requests1 Oct: 3.5T tokens, 63.7M requests2 Oct: 3.6T tokens, 72.2M requests3 Oct: 3.9T tokens, 76.2M requests4 Oct: 3.4T tokens, 59.6M requests5 Oct: 6.5T tokens, 89.6M requests6 Oct: 5.1T tokens, 79.1M requests7 Oct: 7.5T tokens, 105M requests8 Oct: 5.5T tokens, 92.3M requests9 Oct: 5.6T tokens, 105M requests10 Oct: 5T tokens, 102M requests11 Oct: 5.7T tokens, 132M requests12 Oct: 6T tokens, 124M requests13 Oct: 5T tokens, 102M requests14 Oct: 4.5T tokens, 103M requests15 Oct: 5.2T tokens, 108M requests16 Oct: 5.4T tokens, 129M requests17 Oct: 4.1T tokens, 110M requests18 Oct: 2.6T tokens, 64.7M requests19 Oct: 2.8T tokens, 73.8M requests20 Oct: 2.8T tokens, 75.4M requests21 Oct: 2.9T tokens, 84.1M requests22 Oct: 2.9T tokens, 74.5M requests23 Oct: 2.5T tokens, 70.5M requests24 Oct: 2.3T tokens, 76.5M requests25 Oct: 1.9T tokens, 63.8M requests26 Oct: 2.2T tokens, 65.3M requests27 Oct: 2.4T tokens, 72.1M requests28 Oct: 2.4T tokens, 72.2M requests29 Oct: 2.2T tokens, 69.7M requests30 Oct: 1.8T tokens, 63.4M requests31 Oct: 1.7T tokens, 63.7M requests1 Nov: 2.1T tokens, 69.5M requests2 Nov: 2.4T tokens, 72.4M requests3 Nov: 2.9T tokens, 81.4M requests4 Nov: 3T tokens, 82.3M requests5 Nov: 2.6T tokens, 73M requests6 Nov: 2.5T tokens, 80.5M requests7 Nov: 2.1T tokens, 63.8M requests8 Nov: 2.1T tokens, 66M requests9 Nov: 2.3T tokens, 80.9M requests10 Nov: 2.3T tokens, 76M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with DeepSeek V4.1 Flash.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-11. Hosting routes and app features can differ.

DeveloperDeepSeek
Exact model identifierdeepseek/deepseek-v4.1-flash
Inputtext, image
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
MIT, open weights
Context length
1M tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
10 Sept 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

deepseek/deepseek-v4.1-flash: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-11
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-11
Licence source ↗

Licence declared in the deepseek-ai/DeepSeek-V4.1-Flash model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 24.7 (2026-10-26) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →