Skip to content
RankShark

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

ModelOpen sourceby DeepSeeksince 2026
38.3

SharkScore

#147 in Models

Why it scores 38.3

DeepSeek V4 Pro 0423 has a SharkScore of 38.3/100, ranked #147 of 608 in Models (updated 2026-11-19).

Each part compares DeepSeek V4 Pro 0423 with other listings in Models. Evidence covers 87% of the score's weight.

Adoption
25 · 30%
User reviews
no data · 25%
Maintenance
21 · 20%
Trust & transparency
80 · 15%
Momentum
no data · 10%

Paying never changes this score. How ranking works · method v2026-11-18.2

RankShark review of DeepSeek V4 Pro 0423

Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review

We were not paid for this review.

As of 2026-11-18, DeepSeek V4 Pro is a text model with a 1,048,576-token context window and usage-based OpenRouter pricing. [E2]

DeepSeek V4 Pro is a text-in/text-out Mixture-of-Experts model with 1.6T total parameters and 49B activated parameters. It is listed on OpenRouter and is available for local deployment. [E1][E2]

Best for

  • People working with long text inputs or long-context tasks. · model card, OpenRouter
  • Developers seeking a model for reasoning, coding, or agentic tasks. · model card
  • Developers who want to access the model through OpenRouter or deploy it locally. · model card, OpenRouter

Not for

  • Workflows that require image, audio, or video input or output; the listing specifies text input and text output. · OpenRouter

Key features

  • Long context. The listing gives a 1,048,576-token context window; the model page describes a one-million-token context length. · model card, OpenRouter
  • Mixture-of-Experts model. The vendor says DeepSeek V4 Pro has 1.6T total parameters and 49B activated parameters. · model card
  • Reasoning modes. The vendor says the instruct model supports Non-think, Think High, and Think Max modes. · model card
  • Hybrid attention. The vendor says its architecture combines Compressed Sparse Attention and Heavily Compressed Attention. · model card
  • Local deployment. The vendor provides instructions for running the model locally, including weight conversion and interactive chat demos. · model card
  • OpenRouter endpoints. The listing includes chat completions, completions, messages, and responses endpoints. · OpenRouter

Pros

  • The listed context window is 1,048,576 tokens. · OpenRouter
  • The vendor describes three reasoning modes for the instruct model. · model card
  • The vendor provides local deployment instructions and model downloads. · model card

Cons

  • The vendor says this release does not include a Jinja-format chat template and instead provides encoding scripts and test cases. · model card
  • The listing specifies text as both the input and output modality. · OpenRouter
  • No free plan or free trial stated on the pages we checked.
  • Whether customer data is used for model training is not stated on the pages we checked.

Pricing

PlanPriceLimits
OpenRouter API usage$0.90 per million input tokens; $1.50 per million output tokensThe listing specifies a 1,048,576-token context window and a maximum of 393,216 completion tokens.

Checked 18 Nov 2026

Free plan
Not stated (checked 18 Nov 2026)
Free trial
Not stated (checked 18 Nov 2026)
Trains on customer data
Not stated (checked 18 Nov 2026)
Data retention
Not stated (checked 18 Nov 2026)
Data regions
Not stated (checked 18 Nov 2026)
Data processing agreement
Not stated (checked 18 Nov 2026)
AI models used
Not stated (checked 18 Nov 2026)
API
OpenRouter listing includes chat completions, completions, messages, and responses endpoints. · OpenRouter
SDKs
Not stated (checked 18 Nov 2026)
Webhooks
Not stated (checked 18 Nov 2026)
Platforms
OpenRouter listing; Hugging Face and ModelScope downloads; local deployment instructions. · model card, OpenRouter
Security claims
No security certification stated (checked 18 Nov 2026)

What we measured

Context window (OpenRouter listing) · now
1,048,576 tokens
Price per million tokens (OpenRouter listing) · now
$0.9 in, $1.5 out
Package downloads · 30 days
309,218
How we tested · sources
  • Hourly uptime and response-time checks of the product's URL.
  • Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
  • We did not sign up, pay, or use the product as a customer.
  • 18 Nov 2026: Plans or prices changed on the pricing page.
  • 18 Nov 2026: Plans or prices changed on the pricing page.

Something wrong? Report an error with a public link that shows it; corrections re-run the review.

Top alternatives to DeepSeek V4 Pro 0423

See all
  • 67.1

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

    ModelOpen source
  • 65.5

    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t

    ModelOpen source
  • 64.7

    Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

    ModelOpen source
  • 64.3

    Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

    ModelOpen source