id: amd
npm: @ai-sdk/openai-compatible
env: AMD_API_KEY
api: https://developer.amd.com.cn/radeon/api/v1
Models
DeepSeek V4 Flash 0731
DeepSeek-V4-Flashin $0.14/M
out $0.28/M
cache read $0.00/M
ctx: 1,000,000
max out: 384,000
in: text
out: text
reasoning
tools
vision
structured
temp
open weights