GLM-5.3 Flash is free on 14 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-5.3-flash |
1M | Varies by model | No card |
| Pollinations.ai | z-ai/glm-5.3-flash |
1M | API key required (anonymous access removed); no card | No card |
| FreeInference | glm-5.3-flash |
1M | Not published ("generous quota"; HTTP 429 when rate-limited) | No card |
| LLM7.io | GLM-5.3-Flash |
400K | 1 req/s, 60/min, 250/hour (free token from dash.llm7.io) | No card |
| NVIDIA NIM | z-ai/glm-5.3-flash |
1M | ~40 RPM (varies per model, not published) | Phone |
| Zro (MoonMath) | glm-5.3-flash |
1M | Daily usage allowance (amount not published) | Free account |
| Gonka Broker | zai-org/GLM-5.3-Flash |
1M | Network limits (see docs.gonkabroker.com Limits & Quotas) | Phone |
| Moark (Gitee AI) | GLM-5.3-Flash |
— | Not published | Phone |
| GonkaRouter Trial | zai-org/GLM-5.3-Flash |
1M | Shared pool (up to ~1,000 requests/min) | No card |
| Fireworks AI Trial | accounts/fireworks/models/glm-5p3-flash |
— | 10 RPM (no payment method) / up to 6,000 RPM (with card + credits) | Free account |
| Hyperbolic Trial | glm-5.3-flash |
— | 300 requests/minute per API key | Phone |
| Friendli AI Trial | zai-org/GLM-5.3-Flash |
1M | Tier 0: adaptive (60 RPM from Tier 1) | Free account |
| Dahl Inference Trial | zai-org/GLM-5.3-Flash |
Unknown | Not published | Free account |
| Sail Research Trial | zai-org/GLM-5.3-Flash |
— | Not published for Free plan (most relaxed on flex window) | Card required |
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.