DeepSeek-V4-Pro-0813

The production V4-Pro snapshot with stronger agents, low/high/max reasoning effort, and Responses API support.

CurrentLanguageReasoningCodingAgentWeights not released

MODEL NUMBER067

Specifications

Only published specifications are shown.

Total parameters

1.6T

Active parameters

49B

Architecture

MoE

Context

Input modalities

Text

Open weights

Status

Current

The production V4-Pro snapshot with stronger agents, low/high/max reasoning effort, and Responses API support.

PreviousDeepSeek-V4-Pro-Preview1.6T · 1M ctx

CurrentDeepSeek-V4-Pro-08131.6T · 1M ctx

New capabilities Responses API

DSA

Adjustable reasoningAgentCodingResponses API

2026-08-13General release

DeepSeek-V4-Pro-0813 reached general availability with adjustable reasoning effort.

Select a card to view the related model.