AMD
Inference provider
- Hosted model listings
- 1
- Models created
- 0
- API base
https://developer.amd.com.cn/radeon/api/v1- Last verified
- Aug 17, 2026
Inference catalog
Models served by AMD
Provider-specific identifiers, limits, and source-linked prices.
| Model | Provider model ID | Context | Input / 1M | Output / 1M | Cached / 1M | Capabilities | Verified |
|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731DeepSeek | DeepSeek-V4-Flash |
1M | $0.14 | $0.28 | $0.003 | ReasoningToolsJSON | Aug 17, 2026 |