TypeTime-limited7Free Tier123New User28Free Only7
AccessAPI57Desktop37CLI22Web87App21
TagCoding29Agents30Work26Chat30Image31Video24Audio23Search16Embedded3Platforms21OCR4Scraping6Document Parsing6TTS8Compute2

AMD Radeon Cloud Free Inference

· Verified 2026-10-30
Platforms
Provider
AMD
Access
API
AMD Radeon Cloud official free inference (via Token Factory): free shared model APIs covering DeepSeek-V4-Flash, Qwen3.8-Flash-Next, MiniCPM5-2B, OpenAI-compatible, metered by requests/min and per-period spend cap

Free Tier

  • Quota
    Free shared model APIs: 20 req/min per account (gateway) + per-period spend cap
    Cycle
    Daily
    Platform: 30 RPM/key, 8 concurrent; gateway: 20 RPM/account (60s sliding window); daily spend cap accumulates per Beijing calendar day and resets at 00:00 (UTC+8)
    Models：DeepSeek V4-FlashQwen3.8-Flash-NextMiniCPM5-2B

Providers offering this model

  • AMDFree shared model APIs: 20 req/min per account (gateway) + per-period spend cap

Similar free resources

  • NVIDIA NIMFree: up to 40 requests/min for most models, no per-token billing; personal limit shown in dashboard
  • iFlytek Xingchen MaaSSome models are time-limited free: Spark-X2.5-4B (native 1M token context), DeepSeek-OCR.
  • OpenRouter:free models: 20 req/min; 50/day before top-up, 1,000/day after $10 purchased
  • PerchanceFree access to numerous AI generators; many AI image, chat, and story generators require no sign-up and have unlimited use.

About this data：Last checked · Added · Source developer.amd.com.cn