Enterprise DNAEnterprise DNA
DeepSeek logo

Models · Best coding

DeepSeek V4 Pro 0423

by DeepSeek

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.

Visit DeepSeek ↗

Our verdict

Not reviewed yet

We have not reviewed DeepSeek V4 Pro 0423 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 0423

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window.

Best for

Text-first reasoning and coding

Notes

DeepSeek V4 Pro 0423 is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Exploring a long text specification
  • text input; text output on the listed OpenRouter route

Cons

  • Sending images to this text-only catalogue route
  • Assuming open weights establishes hosting privacy or legal rights
  • Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.

Key facts

What we have checked

Input price
$0.887 per million tokens
Checked OpenRouter models API
Output price
$1.77 per million tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.130 per million cached input tokens
Checked OpenRouter models API
Price on atlas-cloud
$1.68 per million input tokens
Checked OpenRouter models API
Price on atlas-cloud
$3.38 per million output tokens
Checked OpenRouter models API
Price on azure
$0.160 per million cached input tokens
Checked OpenRouter models API
Price on azure
$1.91 per million input tokens
Checked OpenRouter models API
Price on azure
$3.83 per million output tokens
Checked OpenRouter models API
Price on baidu
$0.074 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
90.9% (for 24 Apr 2026)
Checked Epoch AI (CC BY 4.0)
Swe bench verified
77.6% (for 24 Apr 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
45.3% (for 24 Apr 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`.

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

OpenRouter id: deepseek/deepseek-v4-pro

Price

What DeepSeek V4 Pro 0423 costs, over time

Input price

$1.03 to $0.887

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

Source: OpenRouter models API. Checked .

Output price

$2.07 to $1.77

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$0.130 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudInput$1.68 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudOutput$3.38 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureCached input$0.160 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureInput$1.91 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
azureOutput$3.83 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
baiduCached input$0.074 per million cached input tokensSince 11 Nov 202612 changesOpenRouter models API
baiduInput$0.889 per million input tokensSince 11 Nov 202612 changesOpenRouter models API
baiduOutput$1.78 per million output tokensSince 11 Nov 202612 changesOpenRouter models API
cloudflareCached input$0.200 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cloudflareInput$1.15 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
cloudflareOutput$2.55 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
crusoeCached input$0.150 per million cached input tokensSince 26 Oct 2026No change recordedOpenRouter models API
crusoeInput$1.74 per million input tokensSince 26 Oct 2026No change recordedOpenRouter models API
crusoeOutput$3.48 per million output tokensSince 26 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
digitaloceanCached input$0.209 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanInput$1.04 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanOutput$2.09 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudCached input$0.080 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudInput$0.957 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudOutput$1.91 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
nebiusCached input$0.140 per million cached input tokensSince 7 Nov 2026No change recordedOpenRouter models API
nebiusInput$1.75 per million input tokensSince 7 Nov 2026No change recordedOpenRouter models API
nebiusOutput$3.50 per million output tokensSince 7 Nov 2026No change recordedOpenRouter models API
novitaCached input$0.135 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaInput$1.60 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaOutput$3.20 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenCached input$0.118 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenInput$1.42 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenOutput$2.83 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
rekaCached input$0.080 per million cached input tokensSince 26 Oct 20261 changeOpenRouter models API
rekaInput$0.800 per million input tokensSince 26 Oct 20261 changeOpenRouter models API
rekaOutput$1.60 per million output tokensSince 26 Oct 20261 changeOpenRouter models API
relaceCached input$0.250 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
relaceInput$0.900 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
relaceOutput$1.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowCached input$0.135 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowInput$1.00 per million input tokensSince 28 Oct 20261 changeOpenRouter models API
siliconflowOutput$1.50 per million output tokensSince 7 Nov 20261 changeOpenRouter models API
streamlakeCached input$0.074 per million cached input tokensSince 11 Nov 202612 changesOpenRouter models API
streamlakeInput$0.887 per million input tokensSince 11 Nov 202612 changesOpenRouter models API
streamlakeOutput$1.77 per million output tokensSince 11 Nov 202612 changesOpenRouter models API
veniceCached input$0.330 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceInput$1.65 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceOutput$3.30 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much DeepSeek V4 Pro 0423 is used

Tokens served a day

100B to 90.6B

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 0423 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 Index12.6indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index59.4indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index26.3indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Design Arena rating (Elo)1,239EloAs of 10 Nov 2026Design Arena via OpenRouter
Chess puzzles (best-across-versions)19percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Cl bench life (best-across-versions)13.5percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)90.7percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)17.6percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)2.4percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)45.3percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)90.9percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Lmca (best-across-versions)41.2percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Show 7 more scores
ScoreValueSourceChecked
Mystery game puzzles (best-across-versions)17percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated96.7percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)16percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)47percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Surface evolver bench (best-across-versions)40percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Swe bench verified (best-across-versions)77.6percentAs of 24 Apr 2026Epoch AI (CC BY 4.0)
Weirdml (best-across-versions)48.9percentAs of 24 Apr 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: 0.079605 to 0.0739355

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 1.91052 to 1.774452

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.95526 to 0.887226

    Source: OpenRouter models API

  4. Price changed

    cached input per mtok: 0.14 to 0.07364

    Source: OpenRouter models API

  5. Price changed

    output per mtok: 3.38 to 1.77788

    Source: OpenRouter models API

  6. Price changed

    input per mtok: 1.69 to 0.88894

    Source: OpenRouter models API

  7. Price changed

    cached input per mtok: 0.074501 to 0.079605

    Source: OpenRouter models API

  8. Price changed

    output per mtok: 1.788024 to 1.91052

    Source: OpenRouter models API

  9. Price changed

    input per mtok: 0.894012 to 0.95526

    Source: OpenRouter models API

  10. Price changed

    cached input per mtok: 0.0742 to 0.14

    Source: OpenRouter models API

  11. Price changed

    output per mtok: 1.7914 to 3.38

    Source: OpenRouter models API

  12. Price changed

    input per mtok: 0.8957 to 1.69

    Source: OpenRouter models API

  13. Price changed

    output per mtok: 1.91052 to 1.774452

    Source: OpenRouter models API

  14. Price changed

    input per mtok: 0.95526 to 0.887226

    Source: OpenRouter models API

  15. Price changed

    cached input per mtok: 0.0665985 to 0.074501

    Source: OpenRouter models API

  16. Price changed

    output per mtok: 1.598364 to 1.788024

    Source: OpenRouter models API

  17. Price changed

    input per mtok: 0.799182 to 0.894012

    Source: OpenRouter models API

  18. Price changed

    cached input per mtok: 0.06692 to 0.0742

    Source: OpenRouter models API

  19. Price changed

    output per mtok: 1.61564 to 1.7914

    Source: OpenRouter models API

  20. Price changed

    input per mtok: 0.80782 to 0.8957

    Source: OpenRouter models API

USAGE / OPENROUTER

How much DeepSeek V4 Pro 0423 is used

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

Tokens, last 7 days
552B ▼5.8%
Requests, last 7 days
22.3M
Tool calls, last 7 days
5.5M
Intelligence score
12.6
Average cost per request
87.6¢
Price per million tokens
$0.887 in · $1.77 out
0100B200B19 Sept: 100B tokens, 4.5M requests20 Sept: 91.6B tokens, 4.3M requests21 Sept: 118B tokens, 4.6M requests22 Sept: 124B tokens, 4.6M requests23 Sept: 115B tokens, 4.3M requests24 Sept: 119B tokens, 4M requests25 Sept: 109B tokens, 4.2M requests26 Sept: 78.8B tokens, 3.5M requests27 Sept: 82.2B tokens, 3.3M requests28 Sept: 110B tokens, 4.2M requests29 Sept: 107B tokens, 3.8M requests30 Sept: 102B tokens, 4M requests1 Oct: 107B tokens, 4M requests2 Oct: 110B tokens, 4.4M requests3 Oct: 96B tokens, 3.8M requests4 Oct: 98.6B tokens, 3.8M requests5 Oct: 120B tokens, 4.3M requests6 Oct: 119B tokens, 4.3M requests7 Oct: 114B tokens, 4.4M requests8 Oct: 101B tokens, 3.9M requests9 Oct: 95.6B tokens, 3.7M requests10 Oct: 88.8B tokens, 3.5M requests11 Oct: 96.5B tokens, 3.9M requests12 Oct: 102B tokens, 3.7M requests13 Oct: 109B tokens, 3.7M requests14 Oct: 107B tokens, 4.9M requests15 Oct: 96.2B tokens, 3.7M requests16 Oct: 85.5B tokens, 3.5M requests17 Oct: 67.6B tokens, 3.5M requests18 Oct: 86.5B tokens, 4.1M requests19 Oct: 103B tokens, 3.8M requests20 Oct: 100B tokens, 4M requests21 Oct: 95B tokens, 3.7M requests22 Oct: 91B tokens, 3.7M requests23 Oct: 78.6B tokens, 3M requests24 Oct: 80.6B tokens, 3.2M requests25 Oct: 94.4B tokens, 3.8M requests26 Oct: 87.5B tokens, 3.1M requests27 Oct: 88.9B tokens, 3.8M requests28 Oct: 85.3B tokens, 3.4M requests29 Oct: 89.6B tokens, 3.3M requests30 Oct: 83.4B tokens, 3.3M requests31 Oct: 64.4B tokens, 2.7M requests1 Nov: 74.1B tokens, 3.4M requests2 Nov: 104B tokens, 3.2M requests3 Nov: 85.3B tokens, 4.2M requests4 Nov: 78.7B tokens, 3M requests5 Nov: 81.2B tokens, 3.5M requests6 Nov: 74.4B tokens, 3M requests7 Nov: 65.7B tokens, 2.9M requests8 Nov: 80.2B tokens, 3.3M requests9 Nov: 81.3B tokens, 3.3M requests10 Nov: 90.6B tokens, 3.4M 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 0423.

Specifications reviewed; 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-pro
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
24 Apr 2026
Listed retirement date
Not established

Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.

Consider it for

  • Exploring a long text specification
  • Drafting code and test plans from explicit requirements

Watch for

  • Sending images to this text-only catalogue route
  • Assuming open weights establishes hosting privacy or legal rights

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Write a pure function specification for allocating 100 cents across three equal recipients. Explain the remainder rule and give tests without importing libraries.

Check the result: Allocation sums to 100, uses integers and gives a deterministic remainder rule.

Compare another approach

anthropic claude sonnet 5 5 ↗openai gpt 6 1 sol ↗
Inspect the sources and their scope
provider source ↗

Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.

Checked 2026-10-19
catalogue source ↗

deepseek/deepseek-v4-pro: 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-Pro 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: 12.6 (2026-11-09) ↗Coding Index: 59.4 (2026-11-09) ↗Agentic Index: 26.3 (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 →