DeepSeek · Deepseek V4 Pro · active

DeepSeek-V4-Pro

DeepSeek-V4-Pro is an open-weight language model published by DeepSeek.

deepseek-ai/DeepSeek-V4-Pro
Statusactive
InputText
OutputText
Context1M
Total / active parameters1.6T / 49B
Licensemit
APIYes
Open weights / self-hostYes / Yes
DeepSeek-V4-ProDeepSeekLiveBench2026-06-2576.79percent35,0141,270deepseek-v4-proaverage per caseThird-party benchmark

Provider availability

Serving endpoints and pricing

ProviderRoute modelTierInputOutputRegionObservedSource
deepseek/deepseek-v4-proStandard routing$0.772$1.5441UnknownAug 28, 2026Provider-reported

This page represents one immutable developer model ID. Serving endpoints, pricing, regions, quantizations, and service tiers attach separately and never create duplicate model records.

Technical specification

Developer model IDdeepseek-ai/DeepSeek-V4-Pro
VersionDeepSeek-V4-Pro
ReleasedApr 24, 2026
ArchitectureDeepseekV4ForCausalLM
Maximum outputUnknown
Knowledge cutoffNot reported

Capabilities

chatgenerationreasoning
ReasoningYes
VisionNo
Tool callingNo

Version lineage

PredecessorUnknown
SuccessorsUnknown
Aliasesdeepseek-ai/DeepSeek-V4-Pro, deepseek-ai/DeepSeek-V4-Pro

Explicit unknowns

  • Maximum output
  • Knowledge cutoff

Comparable peers

Related model comparisons

All comparisons →

Questions

DeepSeek-V4-Pro FAQs

What is DeepSeek-V4-Pro?+

DeepSeek-V4-Pro is an open-weight language model published by DeepSeek. It is developed by DeepSeek and its current sourced lifecycle status is active.

What inputs and outputs does DeepSeek-V4-Pro support?+

DeepSeek-V4-Pro's current record lists Text as input and Text as output.

How much context does DeepSeek-V4-Pro support?+

The current record lists a 1,048,576-token context window and does not report a maximum output length.

Is DeepSeek-V4-Pro available through an API?+

DeepSeek-V4-Pro is marked as API-available. The directly sourced provider records currently include OpenRouter.

How large is DeepSeek-V4-Pro?+

The current record lists 1.6T total parameters and 49B active parameters. Its architecture is DeepseekV4ForCausalLM.

What capabilities and tasks does DeepSeek-V4-Pro support?+

DeepSeek-V4-Pro's recorded capabilities are chat, generation, and reasoning. Its supported tasks are text.

Can DeepSeek-V4-Pro be self-hosted?+

DeepSeek-V4-Pro is an open-weight model. Self-hosting is supported, and the recorded license is mit.

Does DeepSeek-V4-Pro have related versions or aliases?+

No predecessor is recorded. No successor is recorded. Recorded aliases are deepseek-ai/DeepSeek-V4-Pro.

Which models can DeepSeek-V4-Pro be compared with?+

The current compatible peer set includes DeepSeek-V3.2, DeepSeek-R1, DeepSeek-V4-Pro-Base, DeepSeek-V4-Flash, and DeepSeek-V4-Flash-Base. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons

How current is the Model Markets record for DeepSeek-V4-Pro?+

DeepSeek-V4-Pro was last verified Aug 28, 2026 from DeepSeek's primary source, “deepseek-ai/DeepSeek-V4-Pro developer model repository.” The evidence is classified as official fact.

Primary evidence

Sources and observation date