deepseek-flash
DeepSeek-Flash is a fast, efficient model for reasoning, coding, and batch tasks.
- Context
- 1048576 tokens
- Max output
- 393216 tokens
- Input
- llm image
- Output
- llm
Pricing
Input: $0.15 / 1M tokens
Output: $0.6 / 1M tokens
Cached input: $0.003 / 1M tokens
Endpoints
- openai