# AMD Developer Cloud

Free Developer Tier · API key · code · Last updated: 08 Nov 2026

10 free models on AMD Developer Cloud including MiniCPM5-2B, Qwen3.8 Flash Next, and DeepSeek V4 Flash 0731. OpenAI-compatible endpoint (https://cloud.amd.com/api/v1), up to 1M context. Last updated: 08 Nov 2026.

The Grant: AMD Developer Cloud provides free inference access to open frontier models running on AMD Instinct ROCm GPU clusters.
The Output: OpenAI-compatible chat endpoints supporting DeepSeek, Qwen, and MiniCPM variants.
The Process: Register an AMD Developer account to access the inference API console.
The Condition: Subject to ROCm cluster capacity and developer fair-use quotas.

Source: https://cloud.amd.com/ · Last updated: 08 Nov 2026

| Model | Cost | Context | RPM | TPM | RPD | Day tokens | Verified |
| --- | --- | --- | --- | --- | --- | --- | --- |
| MiniCPM5-2B | $0 | 128K | 30 | Not published | 1,000 | Not published | 2026-11-08 |
| Qwen3.8 Flash Next | $0 | 256K | 30 | Not published | 1,000 | Not published | 2026-11-08 |
| DeepSeek V4 Flash 0731 | $0 | 1M | 30 | Not published | 1,000 | Not published | 2026-11-08 |
| MiniCPM-V 4.7 1B | $0 | 256K | 30 | Not published | 1,000 | Not published | 2026-11-08 |
| MiniCPM-V 4.7 35B-A3B | $0 | 256K | 30 | Not published | 1,000 | Not published | 2026-11-08 |
| Qwen3.8 27B | $0 | 256K | 30 | Not published | 1,000 | Not published | 2026-11-08 |
| MiMo-V2.6-Flash | $0 | 1M | 30 | Not published | 1,000 | Not published | 2026-11-08 |
| DeepSeek V4.1 Flash | $0 | 1M | 30 | Not published | 1,000 | Not published | 2026-11-08 |
| Gemma 4 31B IT | $0 | 256K | 30 | Not published | 1,000 | Not published | 2026-11-08 |
| GLM-5.3-Flash | $0 | 256K | 30 | Not published | 1,000 | Not published | 2026-11-08 |

Machine-readable: /data/amd-developer-cloud.json

Numbers cross-checked against official docs and third-party trackers as of 2026-11-08. Limits change without notice — this is a map, not a contract.