DeepSeek: DeepSeek V4 Flash

flagship

DeepSeek · released 2025-11-01 · text->text

currently routing · 4.2k rpm

1.0M tokens

Context

$0.14 / 1M

Input

$0.28 / 1M

Output

— t/s

Speed

proprietary

License

/ ABOUT

DeepSeek V4 Flash is a fast and efficient variant of the V4 architecture, optimized for high-throughput inference while maintaining strong quality on coding and reasoning tasks.

Providers for DeepSeek: DeepSeek V4 Flash

1 routes · sorted by uptime

ClosedRouter routes requests to the providers best able to handle your prompt size and parameters, with automatic fallbacks to maximize uptime.

Provider

Context

Quant

Uptime · 30d

openrouter

1.0M

bf16

0.00%