DeepSeek V4 Pro 0813
DeepSeekdeepseek-v4-pro-0813
Released Aug 13, 2026
Providers
5
Context
1.0M
Input
$0.28/M
Output
$2.00/M
Aliases:deepseek-pro-0813ds-v4-pro-0813
DeepSeek's flagship reasoning model with 1M context window, updated to the DeepSeek-V4-Pro-0813 build served by DeepSeek's direct API. Supports tool calling, extended thinking, and high-quality generation.
novita/deepseek-v4-pro-0813Quantfp8
- Input
- $1.32/M
- Output
- $3.96/M
- Context
- 1.0M
- Max out
- 393K
- Cache read
- $0.04/M
- Cache write
- $1.32/M
- Thinking out
- $3.96/M
relace/deepseek-v4-pro-0813Quantfp4
- Input
- $0.50/M
- Output
- $2.00/M
- Context
- 1.0M
- Max out
- 393K
- Cache read
- $0.05/M
- Cache write
- $0.50/M
- Thinking out
- $2.00/M
cloudflare/deepseek-v4-pro-0813QuantUnspecified
- Input
- $1.32/M
- Output
- $3.96/M
- Context
- 1.0M
- Max out
- 384K
- Cache read
- $0.04/M
- Cache write
- $1.32/M
- Thinking out
- $3.96/M
nebius/deepseek-v4-pro-0813Quantfp8
- Input
- $1.32/M
- Output
- $3.96/M
- Context
- 1.0M
- Max out
- 384K
- Caching
- Not offered
- Thinking out
- $3.96/M
wafer/deepseek-v4-pro-0813QuantUnspecified
- Input
- $0.28/M
- Output
- $3.96/M
- Context
- 1.0M
- Max out
- 384K
- Cache read
- $0.04/M
- Cache write
- $0.28/M
- Thinking out
- $3.96/M