Gemma 4 26B A4B on OpenRouter
OpenRouter Free API tier
The catch: Only 50 requests a day until you buy 10 credits, and many free endpoints keep or train on prompts: OpenRouter marks the NVIDIA, Poolside, Liquid, Thinking Machines and Inception free endpoints 'Trains', and Google AI Studio (55 days) and Cohere (30 days) as retaining prompts.
| Access | Free API tier |
|---|---|
| Free limits | Free variant: 20 requests per minute and 50 requests per day, or 1,000 per day once you have bought at least 10 credits. Google AI Studio serves it; OpenRouter marks it 'Privacy: Logs' (prompts retained 55 days, not used for training). |
| Modality | text, image, video |
| Credit card | Not required |
| Commercial use | – |
| Trains on your data | No |
| Licence or terms | OpenRouter Terms of Service (last updated 31 Aug 2026) + each provider's Model Terms |
| Context window | 262,144 tokens |
| Model id | google/gemma-4-26b-a4b-it:free |
| Base URL | https://openrouter.ai/api/v1 |
| Last checked | 8 Oct 2026 |
How to use Gemma 4 26B A4B
It speaks the OpenAI API at https://openrouter.ai/api/v1, so the OpenAI SDK you already use works once you change the base URL and key.
curl https://openrouter.ai/api/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer $OPENROUTER_API_KEY" -d '{"model":"google/gemma-4-26b-a4b-it:free","messages":[{"role":"user","content":"Hello"}]}'I want to use the free AI model "Gemma 4 26B A4B" from OpenRouter (model id: google/gemma-4-26b-a4b-it:free) 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: 20 RPM · 50 RPD (1,000 after buying 10 credits). 4. If the same provider has a more generous free option, mention it.
Before you ship on it
- Only 50 requests a day until you buy 10 credits, and many free endpoints keep or train on prompts: OpenRouter marks the NVIDIA, Poolside, Liquid, Thinking Machines and Inception free endpoints 'Trains', and Google AI Studio (55 days) and Cohere (30 days) as retaining prompts.
- OpenRouter Terms (last updated 31 Aug 2026) allow incorporating the Service into your own products and services, but you must follow each model's Model Terms; the FAQ says free models 'are usually not suitable for…
- Free tiers are shared capacity: treat the limits as a ceiling, not a promise, and keep a paid fallback.
Questions
Is Gemma 4 26B A4B on OpenRouter free?
Yes. OpenRouter offers it as free api tier, with these limits: 20 RPM · 50 RPD (1,000 after buying 10 credits). No credit card is needed.
Can I use Gemma 4 26B A4B on OpenRouter commercially?
The provider’s terms do not say. Ask them before you build a product on it.
How do I start with Gemma 4 26B A4B on OpenRouter?
It speaks the OpenAI API at https://openrouter.ai/api/v1, so the OpenAI SDK you already use works once you change the base URL and key.
Source: openrouter.ai/google/gemma-4-26b-a4b-it:free, checked 8 Oct 2026.