Should you use gemma-4-31B-it (Preview)?
gemma-4-31B-it (Preview) is listed for chat workloads and supports a 128K context window.
Use it when SambaNova's free tier is enough for evaluation, demos, or light production traffic.
gemma-4-31B-it (Preview) — free model from SambaNova.
https://api.sambanova.ai/v1 gemma-4-31b-it-preview gemma-4-31B-it (Preview) is listed for chat workloads and supports a 128K context window.
Use it when SambaNova's free tier is enough for evaluation, demos, or light production traffic.
We found 2 provider listings for gemma. Check model ID, quota, pricing, and API format before switching providers.
| Provider | Model listing | Access | Context | API | Limits |
|---|---|---|---|---|---|
| | gemma-4-31B-it (Preview) | Free tier | 128K | Native | 20 RPM, 20 RPD, 200K TPD |
| | gemma-4-31b | Free tier | 131K | OpenAI-style | 15 RPM, 30K TPM, 1M TPD |
| Model | Provider | Context | Access |
|---|---|---|---|
| gemma-4-31b | Cerebras | 131K | Free tier |
| DeepSeek-V3.1 | SambaNova | 128K | Free tier |
| DeepSeek-V3.2 (Preview) | SambaNova | 128K | Free tier |
| MiniMax-M2.7 | SambaNova | 128K | Free tier |
gemma-4-31B-it (Preview) is tagged for chat in this catalog and works with OpenAI-compatible client libraries.
gemma-4-31B-it (Preview) is listed with free API access on SambaNova, subject to the provider's quota and account policy.
The model ID shown in this catalog is gemma-4-31b-it-preview.
The listed free tier limit is 20 RPM, 20 RPD, 200K TPD. Limits can change per account tier, so confirm against the provider dashboard.
The listed context window is 128K tokens with up to 128K output tokens.
gemma-4-31B-it (Preview) — free model from SambaNova.
For API keys, setup steps, and provider-level limits, see the SambaNova provider page.