OpenAI Starts Local API Processing in India With GPT-6 Luna
OpenAI now processes and stores supported GPT-6 Luna API requests inside India for eligible customers.
Key Takeaways
- OpenAI launched API inference residency in India on November 12, 2026.
- GPT-6 Luna is the only model supported at launch, via the Responses and Chat Completions APIs.
- Request processing, model computation and supported content storage stay in India.
- Customers must create a new API project with India selected for both storage and processing.
- India joins Australia and Japan as OpenAI's latest inference residency regions.
Table of Contents 6 sections
OpenAI has started local processing and inference for its API in India, so eligible businesses and developers can run supported AI requests inside the country. The company announced the launch on November 12, 2026, and it is available first for the GPT-6 Luna model.
For supported workloads, both the handling of an API request and the model computation that produces the answer take place in India, and supported customer content is also stored in the country. The launch covers direct API usage through the Responses and Chat Completions APIs. India joins Australia and Japan as the latest places where OpenAI offers API inference residency.
OpenAI India inference residency at a glance
| Detail | Value |
|---|---|
| Company | OpenAI |
| What launched | Local processing and inference for the OpenAI API in India |
| Announced | November 12, 2026 |
| Model at launch | GPT-6 Luna |
| Supported APIs | Responses API and Chat Completions API |
| India endpoint | in.api.openai.com |
| Data covered | Request processing, model computation and storage of supported customer content |
| Other recent regions | Australia and Japan |
OpenAI's India residency now covers processing, not just storage
OpenAI already let customers keep data stored in India. The new launch extends that residency to where information is processed. OpenAI said where AI handles information can decide whether an application moves into production for Indian organisations, especially financial services firms with specific localisation rules. The company listed text tasks such as summarising documents, drafting responses and helping employees analyse information.
To use it, a customer creates a new API project with India selected for both storage and processing, and sends requests to the India regional endpoint. OpenAI had recently made a similar residency option available on certain models through Amazon Web Services' Bedrock.
| When | What happened |
|---|---|
| February 2026 | OpenAI launched OpenAI for India, including a partnership with Tata Group to build AI data centre capacity in India |
| February 2026 | OpenAI said it would become the first customer of TCS's HyperVault data centre business, starting with 100 megawatts |
| November 12, 2026 | OpenAI launched API inference residency in India for GPT-6 Luna |
Nitin Bawankule on why some Indian firms held back AI work
"Some Indian businesses have not fully deployed AI for important work because they need the information involved to be processed within the country. Local inference gives them more control over where supported workloads run and helps address a practical barrier to adoption. It gives more businesses a way to put OpenAI’s tools to work, and gives Indian developers and startups more scope to build for their own, and enterprise needs."
OpenAI's price uplift for India processing
OpenAI's API documentation says data residency endpoints carry a 10% price uplift for eligible models released on or after March 5, 2026.
Where OpenAI's India offer stands at launch
Eligible OpenAI API customers in India can now have GPT-6 Luna requests processed and answered inside the country, on top of storing supported content there. The option works through the Responses and Chat Completions APIs and the in.api.openai.com endpoint. It follows OpenAI for India, under which OpenAI and Tata Group agreed in February 2026 to build AI data centre capacity in the country.
More news
Frequently Asked Questions
What is OpenAI's API inference residency in India?
When did OpenAI launch local processing in India?
Which model does OpenAI support for processing in India?
Which APIs does OpenAI's India processing work with?
How do customers turn on OpenAI's India processing?
What is OpenAI's India regional endpoint?
How is this different from OpenAI's earlier India data residency?
Does OpenAI offer a similar residency option through AWS Bedrock?
How does OpenAI price data residency endpoints?
Who at OpenAI spoke about the India launch?
Which other regions recently got OpenAI API inference residency?
What is OpenAI for India?
More in AI
Chariot Launches Text-to-Speech Model for 11 Indian Languages
Chariot has launched a text-to-speech model for 11 Indian languages and English with 50+ voices.
IntellectAI Launches AI Portfolio Tool for Insurers
IntellectAI has launched Xponent Portfolio Navigator, an AI portfolio steering tool for insurers.
Wipro Partners With Labelbox to Take AI Agents to Production
Wipro and Labelbox will help enterprises move AI agents from pilot projects into production.