GPT-4o mini API in India

GPT-4o mini is OpenAI's compact multimodal model — text and vision in one call — and on unoblox it's reachable from India through the same ₹-billed, OpenAI-compatible endpoint as every other model in the catalogue, with a monthly GST invoice instead of a foreign-currency card charge.

Why GPT-4o mini still matters

GPT-4o mini keeps the multimodal ability of the GPT-4o line — accepting images alongside text in the same request — at a fraction of GPT-4o's per-token cost. That combination makes it a common choice for document and receipt parsing, image-captioning at volume, visual QA features, and general chat where vision is only needed occasionally but the SDK should stay identical whether or not an image is attached.

₹ pricing for GPT-4o mini

GPT-4o mini doesn't have a fixed indicative rate published here — see the live number on its model page. Its full-size sibling is priced as follows, for context:

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
GPT-4o	252	1008
GPT-4.1	201.6	806.4

As the "mini" tier of the GPT-4o family, it is priced well below full GPT-4o — confirm the current figure on the model page before estimating a workload's monthly run-rate.

Sending an image and text request

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer ub-gw-xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Summarise the key line items in this invoice image."}]
  }'

The request shape, streaming behaviour and tool-calling support are unchanged from calling OpenAI directly — only the base URL, the ub-gw- key and the ₹ billing are different.

GPT-4o mini vs GPT-4o vs GPT-4.1

• GPT-4o mini — cheapest way to get vision plus text in one call; best for high-volume multimodal features.
• GPT-4o — same multimodal ability, higher quality ceiling, higher per-token cost.
• GPT-4.1 — OpenAI's newer text-first line; check /models for whether a given task benefits more from GPT-4.1 or GPT-4o-class multimodal support.

If a feature doesn't need vision at all, it's worth comparing against GPT-5 mini too, since reasoning-family small models can outperform GPT-4o mini on pure-text tasks.

Frequently asked questions

Is GPT-4o mini available in India through unoblox? Yes. openai/gpt-4o-mini is callable on https://api.unoblox.ai/v1 right after signup, billed in rupees.

Does GPT-4o mini support image inputs on unoblox? Yes, it keeps the same multimodal request format as calling OpenAI directly.

What does GPT-4o mini cost in rupees? It isn't in our fixed indicative list; check the live ₹ rate on its model page, which sits below full GPT-4o's ₹252 / ₹1008 per 1M tokens.

Does choosing GPT-4o mini mean data stays in India? No — it runs on OpenAI's infrastructure. The India-specific part is ₹ billing, a GST invoice and one endpoint, not data residency.

Can I use GPT-4o mini and GPT-4o with the same account? Yes, both sit behind the same key; only the model field changes between calls.

Is a GST invoice issued for GPT-4o mini usage? Yes, combined with all other model usage into one monthly GST invoice from an Indian entity, input tax credit claimable.

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