OpenAI has announced local processing and inference for its API in India, allowing eligible businesses and developers to have supported AI requests processed within the country, The Hindu BusinessLine reported on November 12, 2026. The offering, called API inference residency, is available initially for the GPT-6 Luna model.

The launch extends OpenAI's existing data residency options in India. Earlier, residency covered where supported customer content is stored; now, for supported workloads, both the processing of an API request and the model computation that generates its response also take place in India, with supported customer content stored in the country as well.

At launch, local processing covers direct API usage only, supporting GPT-6 Luna input and output through the Responses API and the Chat Completions API. OpenAI said customers can access it by creating a new API project with India selected for both storage and processing and routing requests through the India regional endpoint. According to Dataquest India, eligible organisations must have approved, active Zero Data Retention status, and India supports Standard pay-as-you-go processing for the rollout.

Nitin Bawankule, Head of Enterprise for India at OpenAI, said some Indian businesses had not fully deployed AI for important work because they needed the information involved to be processed within the country. OpenAI said the in-country option will help businesses use AI for tasks such as summarising documents, drafting responses and analysing information.

The announcement follows the OpenAI for India initiative introduced earlier this year, spanning AI infrastructure, enterprise adoption, skills and local partnerships, including plans with the Tata Group to develop domestic AI data centre capacity. India joins Australia and Japan in the latest expansion of API inference residency, which OpenAI already offers in the United States, Europe and the UAE. Sources: The Hindu BusinessLine; Dataquest India; FoneArena.