/ Models

Language models

DeepSeek: DeepSeek V4 Flash

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...

Maker
Deepseek
Context window
1M
Max output
393K
Input / 1M
$0.14
Output / 1M
$0.28
1M in + 1M out
$0.42

Everything else

Max output393K
Input / 1M$0.14
Output / 1M$0.28
Cache read / 1M$0.028
Cache write / 1M
1M in + 1M out$0.42
Takestext
Returnstext
Toolsyes
Reasoningoptional · xhigh, high
Open weightsyes
Released2026-04-24
Knowledge cutoff
Retires
Catalog iddeepseek/deepseek-v4-flash

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