Enterprise DNAEnterprise DNA
DeepSeek logo

Models · Best coding

DeepSeek V4 Flash 0731

by DeepSeek

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total.

Visit DeepSeek ↗

Our verdict

Not reviewed yet

We have not reviewed DeepSeek V4 Flash 0731 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 Flash 0731

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Notes

DeepSeek V4 Flash 0731 is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.043 per million tokens
Checked OpenRouter models API
Output price
$0.300 per million tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.028 per million cached input tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.440 per million input tokens
Checked OpenRouter models API
Price on atlas-cloud
$1.32 per million output tokens
Checked OpenRouter models API
Price on baidu
$0.0019 per million cached input tokens
Checked OpenRouter models API
Price on baidu
$0.060 per million input tokens
Checked OpenRouter models API
Price on baidu
$0.180 per million output tokens
Checked OpenRouter models API
Price on baseten
$0.028 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
91% (for 31 July 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
57.5% (for 31 July 2026)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
33.6% (for 31 July 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-flash-0731`.

  • openrouter · deepseek/deepseek-v4-flash-0731 · Docs

OpenRouter id: deepseek/deepseek-v4-flash-0731

Price

What DeepSeek V4 Flash 0731 costs, over time

Input price

$0.065 to $0.043

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$0.180 to $0.300

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
atlas-cloudCached input$0.028 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudInput$0.440 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudOutput$1.32 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
baiduCached input$0.0019 per million cached input tokensSince 10 Nov 20268 changesOpenRouter models API
baiduInput$0.060 per million input tokensSince 10 Nov 20268 changesOpenRouter models API
baiduOutput$0.180 per million output tokensSince 10 Nov 20268 changesOpenRouter models API
basetenCached input$0.028 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenInput$0.130 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
basetenOutput$0.260 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
chutesCached input$0.044 per million cached input tokensSince 2 Nov 2026No change recordedOpenRouter models API
chutesInput$0.440 per million input tokensSince 2 Nov 2026No change recordedOpenRouter models API
chutesOutput$1.32 per million output tokensSince 2 Nov 2026No change recordedOpenRouter models API
cloudflareCached input$0.014 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cloudflareInput$0.440 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cloudflareOutput$1.32 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
cohereCached input$0.070 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cohereInput$0.140 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cohereOutput$0.280 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveCached input$0.050 per million cached input tokensSince 7 Nov 20261 changeOpenRouter models API
coreweaveInput$0.130 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveOutput$0.270 per million output tokensSince 7 Nov 20261 changeOpenRouter models API
deepinfraCached input$0.015 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.060 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$0.180 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanCached input$0.024 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanInput$0.119 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanOutput$0.238 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudCached input$0.0091 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudInput$0.286 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudOutput$0.858 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
inceptronCached input$0.027 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
inceptronInput$0.130 per million input tokensSince 26 Oct 20261 changeOpenRouter models API
inceptronOutput$0.495 per million output tokensSince 31 Oct 20263 changesOpenRouter models API
mancerCached input$0.075 per million cached input tokensSince 9 Nov 20261 changeOpenRouter models API
mancerInput$0.150 per million input tokensSince 9 Nov 20262 changesOpenRouter models API
mancerOutput$0.500 per million output tokensSince 7 Nov 20261 changeOpenRouter models API
morphCached input$0.036 per million cached input tokensSince 7 Nov 2026No change recordedOpenRouter models API
morphInput$0.142 per million input tokensSince 7 Nov 2026No change recordedOpenRouter models API
morphOutput$0.400 per million output tokensSince 7 Nov 2026No change recordedOpenRouter models API
nebiusCached input$0.010 per million cached input tokensSince 7 Nov 2026No change recordedOpenRouter models API
nebiusInput$0.140 per million input tokensSince 7 Nov 2026No change recordedOpenRouter models API
nebiusOutput$0.280 per million output tokensSince 7 Nov 2026No change recordedOpenRouter models API
novitaCached input$0.026 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaInput$0.409 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaOutput$1.23 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailCached input$0.050 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailInput$0.140 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailOutput$0.280 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
phalaCached input$0.020 per million cached input tokensSince 9 Nov 20262 changesOpenRouter models API
phalaInput$0.308 per million input tokensSince 9 Nov 20262 changesOpenRouter models API

Usage

How much DeepSeek V4 Flash 0731 is used

Tokens served a day

1.6T to 445.1B

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 Flash 0731 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 Index34.3indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index69.1indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index41indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Design Arena rating (Elo)1,234EloAs of 10 Nov 2026Design Arena via OpenRouter
Arc agi (best-across-versions)89percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)61.4percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)32percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)90.9percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)18.8percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)24.4percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)57.5percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)91percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Show 7 more scores
ScoreValueSourceChecked
Lmca (best-across-versions)41.7percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)34percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated94.4percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)56percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Simplebench (best-across-versions)61.1percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)33.6percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)63percentAs of 31 July 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

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: 0.04 to 0.06

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 0.28 to 0.42

    Source: OpenRouter models API

  3. Price changed

    cached input per mtok: 0.014 to 0.001904

    Source: OpenRouter models API

  4. Price changed

    output per mtok: 1.32 to 0.17952

    Source: OpenRouter models API

  5. Price changed

    input per mtok: 0.44 to 0.05984

    Source: OpenRouter models API

  6. Price changed

    cached input per mtok: 0.095 to 0.035

    Source: OpenRouter models API

  7. Price changed

    output per mtok: 0.23 to 0.3

    Source: OpenRouter models API

  8. Price changed

    input per mtok: 0.1 to 0.0434

    Source: OpenRouter models API

  9. Price changed

    cached input per mtok: 0.0028 to 0.0042

    Source: OpenRouter models API

  10. Price changed

    output per mtok: 0.264 to 0.396

    Source: OpenRouter models API

  11. Price changed

    input per mtok: 0.088 to 0.132

    Source: OpenRouter models API

  12. Price changed

    cached input per mtok: 0.0352 to 0.0176

    Source: OpenRouter models API

  13. Price changed

    output per mtok: 1.056 to 0.528

    Source: OpenRouter models API

  14. Price changed

    input per mtok: 0.352 to 0.176

    Source: OpenRouter models API

  15. Price changed

    cached input per mtok: 0.029 to 0.014

    Source: OpenRouter models API

  16. Price changed

    output per mtok: 0.23 to 1.32

    Source: OpenRouter models API

  17. Price changed

    input per mtok: 0.09 to 0.44

    Source: OpenRouter models API

  18. Price changed

    cached input per mtok: 0.028 to 0.0196

    Source: OpenRouter models API

  19. Price changed

    output per mtok: 1.32 to 0.924

    Source: OpenRouter models API

  20. Price changed

    input per mtok: 0.44 to 0.308

    Source: OpenRouter models API

USAGE / OPENROUTER

How much DeepSeek V4 Flash 0731 is used

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

Tokens, last 7 days
3.1T ▼17.5%
Requests, last 7 days
314M
Tool calls, last 7 days
29.4M
Average cost per request
14.7¢
Price per million tokens
$0.043 in · $0.3 out
01T2T19 Sept: 1.6T tokens, 89.4M requests20 Sept: 1.1T tokens, 82M requests21 Sept: 1.2T tokens, 79.3M requests22 Sept: 1.2T tokens, 81.9M requests23 Sept: 1.2T tokens, 73.3M requests24 Sept: 1.1T tokens, 73.9M requests25 Sept: 1.1T tokens, 66.8M requests26 Sept: 1.1T tokens, 65.1M requests27 Sept: 841B tokens, 68.1M requests28 Sept: 948B tokens, 66.6M requests29 Sept: 946B tokens, 64M requests30 Sept: 968B tokens, 60.4M requests1 Oct: 922B tokens, 57.9M requests2 Oct: 749B tokens, 56.7M requests3 Oct: 709B tokens, 65.5M requests4 Oct: 749B tokens, 50.4M requests5 Oct: 853B tokens, 57.6M requests6 Oct: 838B tokens, 57.8M requests7 Oct: 714B tokens, 57.2M requests8 Oct: 668B tokens, 56M requests9 Oct: 681B tokens, 55.4M requests10 Oct: 542B tokens, 46.7M requests11 Oct: 620B tokens, 43M requests12 Oct: 601B tokens, 43.2M requests13 Oct: 599B tokens, 43.4M requests14 Oct: 996B tokens, 51.3M requests15 Oct: 691B tokens, 50.8M requests16 Oct: 621B tokens, 48M requests17 Oct: 584B tokens, 49.4M requests18 Oct: 608B tokens, 52.6M requests19 Oct: 626B tokens, 56.1M requests20 Oct: 586B tokens, 53.9M requests21 Oct: 576B tokens, 49.7M requests22 Oct: 586B tokens, 45.6M requests23 Oct: 601B tokens, 43.4M requests24 Oct: 505B tokens, 38.9M requests25 Oct: 511B tokens, 47M requests26 Oct: 625B tokens, 47.7M requests27 Oct: 663B tokens, 50.9M requests28 Oct: 578B tokens, 45.8M requests29 Oct: 510B tokens, 43M requests30 Oct: 539B tokens, 48.9M requests31 Oct: 527B tokens, 46.6M requests1 Nov: 495B tokens, 46.9M requests2 Nov: 571B tokens, 53.6M requests3 Nov: 533B tokens, 53.1M requests4 Nov: 533B tokens, 51.7M requests5 Nov: 488B tokens, 50.6M requests6 Nov: 413B tokens, 42.8M requests7 Nov: 370B tokens, 38.1M requests8 Nov: 381B tokens, 38.8M requests9 Nov: 468B tokens, 46.3M requests10 Nov: 445B tokens, 46.2M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with DeepSeek V4 Flash 0731.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-08. Hosting routes and app features can differ.

DeveloperDeepSeek
Exact model identifierdeepseek/deepseek-v4-flash-0731
Inputtext
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
31 Jul 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

deepseek/deepseek-v4-flash-0731: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-08
openrouter.ai ↗

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

Checked 2026-11-08
Licence source ↗

Licence declared in the deepseek-ai/DeepSeek-V4-Flash-0731 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.

Build an appWorkflow & 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.

Coding Index: 69.1 (2026-11-09) ↗Agentic Index: 41 (2026-11-09) ↗Design Arena: 1234 (2026-11-09) ↗
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 →