DeepSeek: DeepSeek V4 Flash

deepseek/deepseek-v4-flash

Tool useJSONReasoningStreaming

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...

Pricing

Input

$0.098 / 1M

Output

$0.197 / 1M

Specs

Context

1,048,576 tokens

Input

text

Output

text

Released: 2026-04

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Open weights · HuggingFace

3,483,641 downloads/mo

1,317 likes

mit text-generation

View on HuggingFace →

Use this model →