Gemma 4 31B on LLM7
LLM7.io Free API tier
The catch: The Terms call it an educational and research service that is 'not for ... production' use and ban reselling, proxying or embedding it in another product without written approval; free quotas 'may be reduced without notice'.
| Access | Free API tier |
|---|---|
| Free limits | Turbo-tier model, so it is open to free tokens; LLM7 publishes no per-model limits, so the free-token caps apply (100,000 tokens per 24 h, 1 req/s, 60 req/min, 250 req/hour). |
| Modality | text |
| Credit card | Not required |
| Commercial use | Not allowed |
| Trains on your data | – |
| Licence or terms | LLM7.io Terms of Service (last updated 30 Sep 2026) + Privacy Policy (7 Oct 2026) |
| Context window | 262,000 tokens |
| Model id | gemma4:31b |
| Base URL | https://api.llm7.io/v1 |
| Last checked | 8 Oct 2026 |
How to use Gemma 4 31B
It speaks the OpenAI API at https://api.llm7.io/v1, so the OpenAI SDK you already use works once you change the base URL and key.
curl https://api.llm7.io/v1/chat/completions -H "Authorization: Bearer $LLM7_TOKEN" -H "Content-Type: application/json" -d '{"model":"gemma4:31b","messages":[{"role":"user","content":"Hello"}]}'I want to use the free AI model "Gemma 4 31B" from LLM7 (model id: gemma4:31b) in my project. Please: 1. Check the provider docs and give me the exact steps to get a free API key. 2. Give me a minimal working example that reads the key from an environment variable. 3. Tell me the real free limits and any catch (commercial use, card, data use). Listed limits: 100K tokens/day · 60 RPM · 250 requests/hour. 4. If the same provider has a more generous free option, mention it.
Before you ship on it
- The Terms call it an educational and research service that is 'not for ... production' use and ban reselling, proxying or embedding it in another product without written approval; free quotas 'may be reduced without notice'.
- Terms (30 Sep 2026) s.2: 'intended for education, experimentation, development, and research. It is not for ... production'; s.3A bars making the Service available to third parties 'as part of another product' without…
- Free tiers are shared capacity: treat the limits as a ceiling, not a promise, and keep a paid fallback.
Questions
Is Gemma 4 31B on LLM7 free?
Yes. LLM7 offers it as free api tier, with these limits: 100K tokens/day · 60 RPM · 250 requests/hour. No credit card is needed.
Can I use Gemma 4 31B on LLM7 commercially?
No: the free access is for testing or non-commercial use. A paid plan is needed for production.
How do I start with Gemma 4 31B on LLM7?
It speaks the OpenAI API at https://api.llm7.io/v1, so the OpenAI SDK you already use works once you change the base URL and key.
Source: api.llm7.io/v1/models, checked 8 Oct 2026.