/ Models

Language models

DeepSeek V4 Flash Latest

This model always redirects to the latest model in the DeepSeek V4 Flash family.

Maker
Deepseek
Context window
1M
Max output
Input / 1M
$0.08
Output / 1M
$0.252
1M in + 1M out
$0.332

Everything else

Max output
Input / 1M$0.08
Output / 1M$0.252
Cache read / 1M$0.025
Cache write / 1M
1M in + 1M out$0.332
Takestext
Returnstext
Toolsyes
Reasoningoptional · max, high, low
Open weightsno
Released2026-08-01
Knowledge cutoff
Retires
Catalog id~deepseek/deepseek-v4-flash-latest

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models