Gemma 4 26B API in India

Gemma 4 26B is Google's open-weights, instruction-tuned model in the Gemma 4 line, and it's callable from India through unoblox's single ₹-billed, OpenAI-compatible endpoint — the same key and base URL as every other model in the catalogue, with one monthly GST invoice instead of a foreign-currency charge.

Why open weights matter for this model

Gemma ships as an open-weights model, meaning the underlying weights are published rather than served only from behind a closed API. On unoblox this doesn't change how you call it — it's still google/gemma-4-26b-a4b-it on the same chat/completions endpoint — but it does mean the model isn't tied to a single vendor's roadmap or pricing decisions the way some closed frontier models are, which some teams weigh when picking a model for a long-lived product.

₹ pricing for Gemma 4 26B

Gemma 4 26B doesn't have a fixed indicative rate published here — see the live number on its model page. Its larger sibling in the same family is priced as follows:

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
Gemma 4 31B	13.10	38.30
Llama 4 Scout	10.08	30.24

As the smaller model in the Gemma 4 line, expect 26B to be priced at or below its 31B sibling — confirm the live figure before estimating cost.

Calling Gemma 4 26B from unoblox

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer ub-gw-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-26b-a4b-it",
    "messages": [{"role": "user", "content": "Rewrite this paragraph in plain, simple English."}]
  }'

The request and response format match the OpenAI chat completions shape, so an existing integration only needs the model field pointed at this id to try it.

When to reach for Gemma 4 26B

• General-purpose chat and writing tasks where an open-weights model is preferred over a closed alternative.
• Cost-sensitive workloads where the smaller Gemma tier is expected to be priced below its 31B sibling and below most closed frontier models.
• Teams that want the option to self-host the same weights elsewhere later, while using unoblox's ₹-billed endpoint for production traffic today.
• For tasks that need the largest possible quality ceiling regardless of cost, compare against a flagship model on the models page instead.

Frequently asked questions

Is Gemma 4 26B available in India through unoblox? Yes, google/gemma-4-26b-a4b-it is callable on https://api.unoblox.ai/v1 right after signup, billed in rupees.

What does Gemma 4 26B cost compared to Gemma 4 31B? It isn't in our fixed indicative list, but as the smaller model in the family it's expected to sit at or below 31B's ₹13.10 / ₹38.30 per 1M tokens — check the live rate on its model page.

Is Gemma 4 26B an open-weights model? Yes, it's part of Google's open-weights Gemma line, callable here on the same rupee-billed endpoint as every other model.

Does using Gemma 4 26B through unoblox mean data stays in India? No, it runs on the upstream provider's infrastructure. The India-specific part is ₹ billing, a GST invoice and one endpoint, not data residency.

Can I switch between Gemma 4 26B and Gemma 4 31B with the same integration? Yes, only the model field changes; both sit behind the same key and endpoint.

Is GST input tax credit available on Gemma 4 26B usage? Yes, it's included in the same monthly GST invoice as every other model, and is claimable as input tax credit.

Get started in rupees → https://unoblox.ai/sign-in