AMD

Inference provider

Endpoints
6
Models
6

Models served

6 shown

ModelCreatorTypeIn $/1MOut $/1MContextMax outputToolsRegion
DeepSeek V4 Flash Latest
DeepSeek-V4-Flash
DeepSeekChat$0.14$0.281.05M384KRegion not stated
DeepSeek V4 Flash Vision Exp
DeepSeek-V4-Flash-Vision-Exp
DeepSeekChat$0.14$0.281M384KRegion not stated
DeepSeek V4.1 Flash
DeepSeek-V4.1-Flash
DeepSeekChat$0.14$0.281.05M384KRegion not stated
MiniCPM5-2B
MiniCPM5-2B
OpenBMBChat$0.124$0.743131K131KRegion not stated
Qwen3.8 Flash Next
Qwen3.8-Flash-Next
Alibaba (Qwen)Chat$0.15$0.47262K131KRegion not stated
Qwen3.8-27B
Qwen3.8-27B
Alibaba (Qwen)ChatListed at $0 (unverified)—131K32.8KRegion not stated

One row per model and variant. Dated pins appear on the model page, not as separate rows. Prices are indicative; verify with the provider.