AI model · DeepSeek
DeepSeek V4 Flash 0423
Model ID: deepseek/deepseek-v4-flash
- Input
- $0.03 per 1M tokens
- Output
- $0.06 per 1M tokens
- Context
- 1M tokens at once
- Max output
- 384K tokens per reply
- Released
- 24 Apr 2026 DeepSeek
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- YesOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
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...
Sources
- DeepSeek: DeepSeek V4 Flash 0423 on OpenRouter — read 2 Oct 2026