Enterprise DNAEnterprise DNA
DeepSeek logo

Models · Best coding

DeepSeek V4 Pro 0813

by DeepSeek

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Visit DeepSeek ↗

Our verdict

Not reviewed yet

We have not reviewed DeepSeek V4 Pro 0813 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 Pro 0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Notes

DeepSeek V4 Pro 0813 is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.111 per million tokens
Checked OpenRouter models API
Output price
$4.44 per million tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.132 per million cached input tokens
Checked OpenRouter models API
Price on atlas-cloud
$1.32 per million input tokens
Checked OpenRouter models API
Price on atlas-cloud
$3.96 per million output tokens
Checked OpenRouter models API
Price on baidu
$0.021 per million cached input tokens
Checked OpenRouter models API
Price on baidu
$0.659 per million input tokens
Checked OpenRouter models API
Price on baidu
$1.98 per million output tokens
Checked OpenRouter models API
Price on baseten
$0.132 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
91.7% (for 13 Aug 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
64.6% (for 13 Aug 2026)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
52.9% (for 13 Aug 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-pro-0813`.

  • openrouter · deepseek/deepseek-v4-pro-0813 · Docs

OpenRouter id: deepseek/deepseek-v4-pro-0813

Price

What DeepSeek V4 Pro 0813 costs, over time

Input price

$0.660 to $0.111

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

Source: OpenRouter models API. Checked .

Output price

$1.98 to $4.44

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$0.132 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudInput$1.32 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudOutput$3.96 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
baiduCached input$0.021 per million cached input tokensSince 11 Nov 202610 changesOpenRouter models API
baiduInput$0.659 per million input tokensSince 11 Nov 202610 changesOpenRouter models API
baiduOutput$1.98 per million output tokensSince 11 Nov 202610 changesOpenRouter models API
basetenCached input$0.132 per million cached input tokensSince 26 Oct 2026No change recordedOpenRouter models API
basetenInput$1.32 per million input tokensSince 26 Oct 2026No change recordedOpenRouter models API
basetenOutput$3.96 per million output tokensSince 26 Oct 2026No change recordedOpenRouter models API
cloudflareCached input$0.044 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cloudflareInput$1.32 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cloudflareOutput$3.96 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveCached input$0.044 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveInput$1.31 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
coreweaveOutput$3.96 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraCached input$0.100 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$1.30 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$2.60 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepseekCached input$0.022 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepseekInput$0.660 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepseekOutput$1.98 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
dekallmCached input$0.150 per million cached input tokensSince 30 Oct 20261 changeOpenRouter models API
dekallmInput$0.880 per million input tokensSince 30 Oct 20261 changeOpenRouter models API
dekallmOutput$3.80 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanCached input$0.044 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanInput$1.32 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanOutput$3.96 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudCached input$0.035 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudInput$1.06 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudOutput$3.17 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
ionstreamCached input$0.088 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
ionstreamInput$0.370 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
ionstreamOutput$2.93 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
nebiusCached input$0.040 per million cached input tokensSince 27 Oct 2026No change recordedOpenRouter models API
nebiusInput$1.32 per million input tokensSince 27 Oct 2026No change recordedOpenRouter models API
nebiusOutput$3.96 per million output tokensSince 27 Oct 2026No change recordedOpenRouter models API
novitaCached input$0.033 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaInput$0.990 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaOutput$2.97 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailCached input$0.044 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailInput$1.32 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailOutput$3.96 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
phalaCached input$0.099 per million cached input tokensSince 9 Nov 20262 changesOpenRouter models API
phalaInput$0.957 per million input tokensSince 9 Nov 20262 changesOpenRouter models API
phalaOutput$2.88 per million output tokensSince 9 Nov 20262 changesOpenRouter models API
qwenCached input$0.058 per million cached input tokensSince 9 Nov 20262 changesOpenRouter models API
qwenInput$0.581 per million input tokensSince 9 Nov 20262 changesOpenRouter models API
qwenOutput$1.74 per million output tokensSince 9 Nov 20262 changesOpenRouter models API
relaceCached input$0.100 per million cached input tokensSince 7 Nov 20264 changesOpenRouter models API
relaceInput$0.100 per million input tokensSince 7 Nov 20264 changesOpenRouter models API

Usage

How much DeepSeek V4 Pro 0813 is used

Tokens served a day

178.1B to 107.8B

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 Pro 0813 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 Index23.1indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index68.8indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index41.3indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Apex agents (best-across-versions)47.3percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Arc agi (best-across-versions)90.5percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)61.3percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)46percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)93.9percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)28.6percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)26.8percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)64.6percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)91.7percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Show 6 more scores
ScoreValueSourceChecked
Lmca (best-across-versions)45.5percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)43percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated98.6percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)50percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)52.9percentAs of 13 Aug 2026Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)66.2percentAs of 13 Aug 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: 0.042 to 0.020958

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 3.96 to 1.97604

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 1.32 to 0.65868

    Source: OpenRouter models API

  4. Price changed

    cached input per mtok: 0.020958 to 0.042

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 1.97604 to 3.96

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 0.65868 to 1.32

    Source: OpenRouter models API

  7. Price changed

    cached input per mtok: 0.284 to 0.097

    Source: OpenRouter models API

  8. Price changed

    output per mtok: 4.3 to 4.44

    Source: OpenRouter models API

  9. Price changed

    input per mtok: 0.285 to 0.111

    Source: OpenRouter models API

  10. Price changed

    cached input per mtok: 0.1122 to 0.05808

    Source: OpenRouter models API

  11. Price changed

    output per mtok: 3.366 to 1.7424

    Source: OpenRouter models API

  12. Price changed

    input per mtok: 1.122 to 0.5808

    Source: OpenRouter models API

  13. Price changed

    cached input per mtok: 0.15 to 0.099

    Source: OpenRouter models API

  14. Price changed

    output per mtok: 4.36 to 2.8776

    Source: OpenRouter models API

  15. Price changed

    input per mtok: 1.45 to 0.957

    Source: OpenRouter models API

  16. Price changed

    cached input per mtok: 0.031458 to 0.020958

    Source: OpenRouter models API

  17. Price changed

    output per mtok: 2.96604 to 1.97604

    Source: OpenRouter models API

  18. Price changed

    input per mtok: 0.98868 to 0.65868

    Source: OpenRouter models API

  19. Price changed

    cached input per mtok: 0.11 to 0.284

    Source: OpenRouter models API

  20. Price changed

    output per mtok: 4 to 4.3

    Source: OpenRouter models API

USAGE / OPENROUTER

How much DeepSeek V4 Pro 0813 is used

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

Tokens, last 7 days
789B ▲3.3%
Requests, last 7 days
44.6M
Tool calls, last 7 days
8.1M
Intelligence score
23.1
Average cost per request
58.2¢
Price per million tokens
$0.111 in · $4.44 out
0250B500B19 Sept: 178B tokens, 3.7M requests20 Sept: 136B tokens, 2.9M requests21 Sept: 158B tokens, 3.2M requests22 Sept: 165B tokens, 2.8M requests23 Sept: 168B tokens, 3M requests24 Sept: 141B tokens, 3.7M requests25 Sept: 96.8B tokens, 2.2M requests26 Sept: 157B tokens, 3.4M requests27 Sept: 132B tokens, 2.9M requests28 Sept: 134B tokens, 2.9M requests29 Sept: 124B tokens, 2.9M requests30 Sept: 114B tokens, 2.5M requests1 Oct: 106B tokens, 2.8M requests2 Oct: 126B tokens, 2.8M requests3 Oct: 85.6B tokens, 2.3M requests4 Oct: 81.1B tokens, 2.1M requests5 Oct: 151B tokens, 6.8M requests6 Oct: 188B tokens, 8.7M requests7 Oct: 202B tokens, 9.2M requests8 Oct: 254B tokens, 10M requests9 Oct: 166B tokens, 8.6M requests10 Oct: 172B tokens, 7.9M requests11 Oct: 170B tokens, 7.8M requests12 Oct: 120B tokens, 7.1M requests13 Oct: 115B tokens, 6.5M requests14 Oct: 128B tokens, 6.5M requests15 Oct: 158B tokens, 6.8M requests16 Oct: 161B tokens, 7.2M requests17 Oct: 126B tokens, 6.5M requests18 Oct: 101B tokens, 6.4M requests19 Oct: 122B tokens, 6.4M requests20 Oct: 142B tokens, 6.5M requests21 Oct: 178B tokens, 7.1M requests22 Oct: 173B tokens, 7.2M requests23 Oct: 122B tokens, 6.5M requests24 Oct: 112B tokens, 5.9M requests25 Oct: 90.8B tokens, 5.9M requests26 Oct: 117B tokens, 6.5M requests27 Oct: 121B tokens, 7M requests28 Oct: 138B tokens, 6.7M requests29 Oct: 123B tokens, 7.2M requests30 Oct: 110B tokens, 6.3M requests31 Oct: 104B tokens, 5.7M requests1 Nov: 80.7B tokens, 5.5M requests2 Nov: 100B tokens, 6.2M requests3 Nov: 108B tokens, 6.6M requests4 Nov: 109B tokens, 6.5M requests5 Nov: 125B tokens, 6.9M requests6 Nov: 155B tokens, 7.6M requests7 Nov: 94B tokens, 5.6M requests8 Nov: 82.2B tokens, 5.8M requests9 Nov: 115B tokens, 6.2M requests10 Nov: 108B tokens, 6.1M requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with DeepSeek V4 Pro 0813.

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-pro-0813
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
12 Aug 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

deepseek/deepseek-v4-pro-0813: 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-Pro-0813 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.

Intelligence Index: 23.1 (2026-11-09) ↗Coding Index: 68.8 (2026-11-09) ↗Agentic Index: 41.3 (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 →