DeepSeek-V4-Flash Preview

mit

DeepSeek-V4-Flash hybrid model with both non-thinking and thinking (default) modes.

Context
1M
Max output
384K
Input price
$0.14/1M tokens
Output price
$0.28/1M tokens

Capabilities

vision
tool call
structured output
reasoning
json mode
streaming
fine tuning
batch

Details

Model IDdeepseek-v4-flash
Provider Azure AI Foundry
Creator DeepSeek
Familydeepseek
Licensemit
Parameters—
Statusactive
Input modalitiestext
Output modalitiestext
Architecture—
Knowledge cutoff—
Training data cutoff—
Release date
Deprecation date—
Typechat
Reasoning tokensYes
Max input—
Open weightYes
Sourceofficial
Last updated

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.14
Output
$0.28
Cache write
—
Cache read
$0
Batch in
—
Batch out
—

Family Comparison: deepseek

ModelContextMax outPricing
DeepSeek-V3-0324 Preview——
DeepSeek-V3.1 Preview——
DeepSeek-V3.2-Speciale Preview——
DeepSeek-V3.2 Preview——
DeepSeek-V4-Fast Preview——
DeepSeek-V4-Flash Preview1M384K

API

GET/v1/models/azure/deepseek-v4-flash