GPT-OSS 120B is free on 10 providers today. Permanent free tiers come first, then one-time trials.
| Provider | API model ID | Context | Free limits | Sign-up |
|---|---|---|---|---|
| Groq | openai/gpt-oss-120b |
131K | 30 RPM; 8K TPM on most chat models (varies by model) | No card |
| Cloudflare Workers AI | @cf/openai/gpt-oss-120b |
128K | Varies by model | No card |
| Inferbase | openai-gpt-oss-120b |
128K | 100 managed requests per day | No card |
| OVH AI Endpoints | gpt-oss-120b |
128K | 2 RPM per IP per model (anonymous, free); 400 RPM with a key (pay-as-you-go) | Free account |
| Vercel AI Gateway | openai/gpt-oss-120b |
128K | Lower per-model limits than the paid tier (429 on excess) | Free account |
| IBM watsonx.ai (Lite plan) | openai/gpt-oss-120b |
131K | About 2 requests/second (Lite) | Card required |
| Regolo.ai Trial | gpt-oss-120b |
128K | Not published (trial) | No card |
| Fireworks AI Trial | accounts/fireworks/models/gpt-oss-120b |
— | 10 RPM (no payment method) / up to 6,000 RPM (with card + credits) | Free account |
| Scaleway Generative APIs Trial | gpt-oss-120b |
128K | Organization quota in tokens/minute (see console) | Free account |
| Cerebras Trial | gpt-oss-120b |
128K | 5 RPM, 30K uncached / 90K total TPM, 1M tokens per hour and per day (Free Trial) | 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.