OpenAI brings local inference to India, starting with GPT-6 Luna

OpenAI on Thursday introduced local processing for its API in India, allowing eligible businesses and developers to run supported AI workloads within the country as it seeks to address a barrier to enterprise adoption.

The offering initially supports the GPT-6 Luna model and extends the company’s existing data residency options in India. Along with storing supported customer content locally, OpenAI will process API requests and run the model computation that generates responses within the country.

The distinction matters for businesses that need information to remain in India during processing, rather than only when stored. OpenAI said the capability would help organisations adopt AI for work that requires in-country processing.


“Some Indian businesses have not fully deployed AI for important work because they need the information involved to be processed within the country,” said Nitin Bawankule, head of enterprise, India, at OpenAI.

“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,” he added.

According to the company, businesses can use the offering for text-based tasks such as summarising documents, drafting responses and analysing information.

The capability currently supports GPT-6 Luna input and output through OpenAI’s Responses and Chat Completions APIs for direct API usage. Eligible customers can access it by creating a new API project, selecting India for both data storage and processing and using the India regional endpoint.

The launch builds on the company’s broader expansion in the country. Earlier this year, OpenAI introduced its OpenAI for India initiative, covering AI infrastructure, enterprise adoption, skills development and local partnerships. The initiative included a partnership with Tata Group to develop domestic AI data centre capacity.

The company said API inference residency is available in other regions as well, with India, Australia and Japan among the latest markets to receive the capability.