GLM-4.7 Flash is free on 11 providers today. Permanent free tiers come first, then one-time trials.
| Provider | API model ID | Context | Free limits | Sign-up |
|---|---|---|---|---|
| Cloudflare Workers AI | @cf/zai-org/glm-4.7-flash |
Long context | Varies by model | No card |
| Api.Airforce | glm-4.7-flash |
128K | 1 RPM | No card |
| Inferbase | zai-glm-4-7-flash |
200K | 100 managed requests per day | No card |
| MegaNova AI | zai-org/GLM-4.7-Flash |
131K | Tier 1 (free): 20-200 RPM | No card |
| Z.AI (GLM) | glm-4.7-flash |
128K | ~1 request/second (Flash models) | Free account |
| ModelScope | ZhipuAI/GLM-4.7-Flash |
— | 500 requests/day per model | Phone |
| Vercel AI Gateway | zai/glm-4.7-flash |
200K | Lower per-model limits than the paid tier (429 on excess) | Free account |
| AIHubMix (free models) | glm-4.7-flash-free |
200K | 5 RPM per account on most *-free routes | Free account |
| Zhipu BigModel (China) | glm-4.7-flash |
200K | Low concurrency on free Flash models (GLM-4.7-Flash reported at 1 concurrent request) | Phone |
| Kiosapi.id | zai/glm-4.7-flash |
— | 5 requests/minute (free models) | Free account |
| NovAI Trial | glm-4.7-flash |
200K | 5 requests/min before the first top-up | No card |
Free lists change often. Each provider page shows its full limits and code examples, and every change is logged in the changelog. Want to call it from Claude Code or Cursor? Use the setup generator.