Model overview
- Model ID: deepseek/deepseek-v4-pro-0813
- Provider: deepseek
- Type: language
- Context window: 1,048,600 tokens
- Max output tokens: 1,048,600
Tags: implicit-caching, reasoning, tool-use, structured-output, open-weights
Model pricing
| Metric | Value |
|---|---|
Input tokens (/1M) | $1.32 |
Output tokens (/1M) | $3.96 |
Image generation | n/a |
Cached input read (/1M) | $0.13 |
Cached input write (/1M) | n/a |
Pricing source | gateway |