open models
Built for agents that replay context.
The repeated part of each call hits the cache and bills at the cached input rate.
5 of 9 models
Reset- Input
- USD0.90
- per million input tokens
- Cached input
- USD0.09
- per million cached input tokens
- Output
- USD2.43
- per million output tokens
- Cache hit rate
- cache hit rate, not yet published
DeepSeek V4.1 Flash 1017
Availabledeepseek-v4-1-flash-1017Trending
Tool calling / JSON mode / Streaming / Image input
- Input
- USD0.15
- per million input tokens
- Cached input
- USD0.01
- per million cached input tokens
- Output
- USD0.60
- per million output tokens
- Cache hit rate
- 99.4%
- cache hit rate, last 24 hours
- Input
- USD0.11
- per million input tokens
- Cached input
- USD0.03
- per million cached input tokens
- Output
- USD0.45
- per million output tokens
- Cache hit rate
- 99.4%
- cache hit rate, last 24 hours
- Input
- USD0.10
- per million input tokens
- Cached input
- USD0.01
- per million cached input tokens
- Output
- USD0.40
- per million output tokens
- Cache hit rate
- 87.7%
- cache hit rate, last 24 hours
- Input
- USD0.10
- per million input tokens
- Cached input
- USD0.01
- per million cached input tokens
- Output
- USD0.40
- per million output tokens
- Cache hit rate
- 96.4%
- cache hit rate, last 24 hours
Looking for another model? Request a model
Prices as of 2026-11-12.
