DeepSeek

DeepSeek V4 Flash 0423

by DeepSeektext->text17 endpoints

Overview

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...

Capabilities

Text generation
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
Text
Output
Text

Technical Specifications

Context Window
1.0M tokens
Max Output
384K tokens
Tokenizer
DeepSeek
Uptime (24h)
9999.0%

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

Pricing

Per 1M tokens
Input$0.04
Output$0.09
Cache read$0.0086
Added
April 24, 2026
Last synced 9/19/2026