AI model · DeepSeek
DeepSeek V4 Flash Latest
Model ID: ~deepseek/deepseek-v4-flash-latest
- Input
- $0.01 per 1M tokens
- Output
- $0.81 per 1M tokens
- Context
- 1M tokens at once
- Max output
- 944K tokens per reply
- Released
- 1 Aug 2026 DeepSeek
What it can do
- YesReasoning
- YesTool calling
- NoImage input
- NoOpen weights
- NoFree to use
Takes text; gives text.
How its listing describes it
This model always redirects to the latest model in the DeepSeek V4 Flash family.
Sources
- DeepSeek: DeepSeek V4 Flash Latest on OpenRouter — read 2 Oct 2026