GPT-5.2 API in India
Access GPT-5.2 from India through unoblox's ₹-billed endpoint — GST invoice, no international card, live pricing on the model page.
GPT-5.2 is OpenAI's latest point release on the GPT-5 line, and it's available from India today on unoblox's single OpenAI-compatible, ₹-billed endpoint — the same key and base URL you'd use for every other model in the catalogue, with one monthly GST invoice instead of a foreign-currency charge.
₹ pricing for GPT-5.2
GPT-5.2 doesn't carry a fixed indicative rate in this note — its live price is on the model page, and it's worth checking before committing a workload, since point releases can be priced differently from the models they extend. For context, two of its stablemates:
| Model | Input (₹ / 1M tokens) | Output (₹ / 1M tokens) |
|---|---|---|
| GPT-5 | 126 | 1008 |
| GPT-5 mini | 25.2 | 201.6 |
What a point release like GPT-5.2 changes
Point releases in a model family typically refine behaviour and capability within the same general position in the lineup, rather than introducing a new tier. Practically, that means GPT-5.2 is a like-for-like swap for GPT-5 in most integrations — same request shape, same chat/completions endpoint, same tool-calling and JSON-mode support — with the model string as the only change.
Calling GPT-5.2 on unoblox
curl https://api.unoblox.ai/v1/chat/completions \
-H "Authorization: Bearer ub-gw-xxxxxxxxxxxxxxxx" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.2",
"messages": [{"role": "user", "content": "Summarise this support ticket in two sentences."}],
"stream": true
}'
Set stream to false (or omit it) for a single JSON response instead of server-sent events — both work unchanged from calling OpenAI directly.
Deciding whether to move to GPT-5.2
- If you're starting a new integration,
openai/gpt-5.2is a reasonable default to evaluate first, alongside GPT-5 and GPT-5 mini. - If you're already running GPT-5 in production, test GPT-5.2 against your own prompts before switching — check the live ₹ price and your own output quality rather than assuming a newer point release automatically fits every task.
- For high-volume, low-complexity calls, GPT-5 mini at ₹25.2 / ₹201.6 per 1M tokens remains the cheaper option regardless of which flagship point release you standardise on.
Frequently asked questions
Is GPT-5.2 available in India through unoblox?
Yes, openai/gpt-5.2 is callable on https://api.unoblox.ai/v1 immediately after signup, billed in rupees.
What is GPT-5.2's ₹ price on unoblox? It isn't in our fixed indicative list; check the live rate on its model page before estimating cost for a workload.
Is GPT-5.2 a separate tier from GPT-5, like the mini model? No, it sits in the same flagship position as GPT-5 as a point release, not as a smaller or cheaper tier.
Does GPT-5.2 support streaming and tool calling? Yes, both work exactly as documented for the OpenAI API — only the base URL and key differ on unoblox.
Does calling GPT-5.2 through unoblox mean data is processed in India? No, it runs on OpenAI's infrastructure; the India-specific benefit is ₹ billing, a GST invoice and one endpoint, not data residency.
Is GPT-5.2 usage included in the same GST invoice as other models? Yes, all usage across every model is combined into one monthly GST invoice, with input tax credit claimable.
Get started in rupees → https://unoblox.ai/sign-in
Start building in rupees
Call every major model through one OpenAI-compatible endpoint, billed in ₹ on a GST invoice.