DeepSeek: DeepSeek V4 Flash 0731

deepseek/deepseek-v4-flash-0731

Description

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

How this model compares

Overall covers the full catalog. By plan covers only models available on that tier (same rules as available models in your list). Position on min–average–max. Prices use the higher of prompt or completion per token, shown per 1M tokens.

Price (per 1M tokens)

Min
Max
This model
330 models in this groupPrice (per 1M tokens)
Min
$0.04
Avg
$12.568263
Max
$750.00
This model: $0.28 / 1M tokens

Context length (tokens)

Min
Max
This model
330 models in this groupContext length (tokens)
Min
4,095 tokens
Avg
418,217.388 tokens
Max
2,000,000 tokens
This model: 1,048,576 tokens

Capabilities

Text → TextContext: 1,048,576 tokens
Input:
Text
Output:
Text
    DeepSeek: DeepSeek V4 Flash 0731