Context
1.0M
Input
$0.07/M
Output
$0.14/M
Aliases:deepseek-v4-flashds-v4-flash
DeepSeek's fast, cost-efficient general-purpose model with 1M context window, updated July 2026 with substantially enhanced agentic capabilities. Supports tool calling and thinking mode.
relace/deepseek-v4-flash-0731Quantfp4
- Input
- $0.07/M
- Output
- $0.14/M
- Context
- 1.0M
- Max out
- 384K
- Cache read
- $0.01/M
- Cache write
- $0.07/M
- Thinking out
- $0.14/M