All Models

DeepSeek V4 Flash 0423

deepseek Reasoning Tool Calling Open Weights Structured Output

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...

Providers 1
Released Apr 24, 2026
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

49.9
Intelligence Index
69.1
Coding Index

Available Providers (1)

Provider Model ID Input Cost Output Cost Context Max Output Docs
Venice AI deepseek-v4-flash $0.14/MTok $0.28/MTok 1M 32.8K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output