Back to models

DeepSeek: DeepSeek V4 Pro 0813

DeepSeek · Text

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

Model ID deepseek/deepseek-v4-pro-0813Updated Aug 22, 2026EasyX.AI · Platform adopted

Pricing & billing

Billing unit: 1M tokens. Vendor reference price; conversion is approximate.

ItemUSD referenceList price (USD)
Input$0.66$0.66
Output$1.98$1.98
Cache read$0.022$0.022
Cache write—No public pricing—No public pricing

Specifications

Form
Text model
Input modalities
Text
Output modalities
Text
Context length
1M
Max output
944K
Weights
Open weights
Family
deepseek-thinking
Released
Aug 13, 2026

Uses and capabilities

Capabilities Text model、Function calling、Structured output、Reasoning、Prompt caching、Open weights

Function calling

Structured output

Reasoning

Prompt caching

Open weights

Sources

Use these links to verify specs and pricing — they may point to the vendor's site or to a third-party catalog.