Groq
Shared by midudev↗The fastest inference on the market. No credit card.
1,000 requests per day131K context
Alibaba
Use Qwen 3 for free
Alibaba’s family, from 0.6B you can run on a laptop to MoE giants. Hosted APIs name the exact weight; this page is the family.
- API id
- qwen3
- Context
- 128K
- Weights
- Open
- Free routes
- 16
Where to run Qwen 3 for free
Vercel AI Gateway
Shared by midudev↗One key, hundreds of models, $5 of credits every month. No markup on tokens.
$5 of credits per month1M context
AMD Radeon Cloud
↗AMD’s Token Factory: five shared free APIs and $10 of usage every day, reset at midnight.
$10 of usage per day1M context
Cloudflare Workers AI
↗Models at the edge, one fetch away from your Worker.
10,000 neurons per day262K context
Hugging Face
↗Inference Providers: thousands of open models with monthly credits.
$0.10 of credits per month131K context
ModelScope
↗Alibaba’s hub: 50 free models over API, many of them frontier Chinese ones.
2,000 requests per day50 models
Ollama Cloud
↗The same models and commands as local Ollama, but running on someone else’s GPU.
Monthly starter credits1M context
Alibaba Model Studio
↗Qwen straight from the source, with a 1M-context tier and free quota to start.
1M tokens per model for 90 days1M context
SiliconFlow
↗Chinese open models with a permanently free tier, distills included.
Per-model caps after KYC131K context
Tools that work with it
Hugging Face Spaces
Thousands of open-model demos ready to try in the browser.
Free accessCommunity demos
