DeepSeek: DeepSeek V4 Flash 0731
deepseek/deepseek-v4-flash-0731
Description
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.
How this model compares
Overall covers the full catalog. By plan covers only models available on that tier (same rules as available models in your list). Position on min–average–max. Prices use the higher of prompt or completion per token, shown per 1M tokens.
Price (per 1M tokens)
Min
Max
This model
438 models in this groupPrice (per 1M tokens)
- Min
- $0.049
- Avg
- $11.394589
- Max
- $750.00
This model: $0.12 / 1M tokens
Context length (tokens)
Min
Max
This model
438 models in this groupContext length (tokens)
- Min
- 4,095 tokens
- Avg
- 507,637.121 tokens
- Max
- 2,000,000 tokens
This model: 1,310,720 tokens
Capabilities
Text → TextContext: 1,048,576 tokens
Input:
Text
Output:
Text