Context
1.0M
Input
$0.28/M
Output
$1.14/M
Aliases:deepseek-v4.1-flashds-v4-1-flashds-v4.1-flash
DeepSeek's smallest new-architecture model: natively multimodal with 1M context window, faster and cheaper than V4 Pro while exceeding it on agentic, coding and reasoning tasks. Supports image input, tool calling and thinking mode.
runanywhere/deepseek-v4-1-flashQuantfp8
- Input
- $0.28/M
- Output
- $1.14/M
- Context
- 1.0M
- Max out
- 66K
- Cache read
- $0.01/M
- Cache write
- $0.28/M
- Thinking out
- $1.14/M