deepseek
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...
Input Cost
$0.10
per 1M tokens
Output Cost
$0.20
per 1M tokens
Context Window
1,048,576
tokens
Developer ID: deepseek/deepseek-v4-flash
Related Models
deepseek
$0.20/1M
DeepSeek: DeepSeek V3
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction foll...
deepseek
$0.44/1M
DeepSeek: DeepSeek V4 Pro
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total pa...
deepseek
$0.29/1M
DeepSeek: R1 Distill Qwen 32B
DeepSeek R1 Distill Qwen 32B is a distilled large language model based on [Qwen 2.5 32B](h...