Gemma 4 31B IT is free on 9 providers today. Permanent free tiers come first, then one-time trials.
| Provider | API model ID | Context | Free limits | Sign-up |
|---|---|---|---|---|
| OpenRouter | google/gemma-4-31b-it:free |
262K | 20 requests/minute | No card |
| Google AI Studio | gemma-4-31b-it |
256K | Varies by model (per-model limits are now shown only inside AI Studio) | No card |
| Requesty | google/gemma-4-31b-it |
262K | 20 RPM on free models (60 RPM for paying orgs) | No card |
| Inferbase | google-gemma-4-31b-it |
256K | 100 managed requests per day | No card |
| NVIDIA NIM | google/gemma-4-31b-it |
262K | ~40 RPM (varies per model, not published) | Phone |
| AIHubMix (free models) | gemma-4-31b-it-free |
262K | 5 RPM per account on most *-free routes | Free account |
| Regolo.ai Trial | gemma4-31b |
— | Not published (trial) | No card |
| Friendli AI Trial | google/gemma-4-31B-it |
262K | Tier 0: adaptive (60 RPM from Tier 1) | Free account |
| Sail Research Trial | google/gemma-4-31B-it |
— | 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.