OpenAI has introduced API inference residency in India, allowing businesses and developers to process supported GPT-6 Luna workloads within the country.
The move addresses data localisation requirements, particularly in regulated sectors such as financial services, where the location of data processing can determine whether organisations deploy AI applications.
The offering allows eligible customers to process API requests and run model computations in India. Supported customer content is also stored within the country.
“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, 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.
The offering currently supports GPT-6 Luna input and output through OpenAI's Responses and Chat Completions APIs. It covers direct API usage and allows organisations to use the model for text-based applications, including document summarisation, drafting responses, and analysing information.
Customers can enable the feature by creating a new API project and selecting India as the region for both data storage and processing. They must also use the corresponding India regional endpoint.
The launch extends OpenAI's existing data residency options in India, which previously covered where customer data is stored. With inference residency, both API request processing and model computation take place within the country for supported workloads.
The move builds on OpenAI’s broader India strategy. Earlier this year, the company introduced OpenAI for India, an initiative covering AI infrastructure, enterprise adoption, skills development, and local partnerships. It also announced a partnership with Tata Group to develop domestic AI data centre capacity.
OpenAI recently introduced a similar residency capability for certain models through Amazon Web Services' Bedrock platform.
The company has also expanded API inference residency to other markets, with India, Australia, and Japan among its latest additions.
- HCLTech, PTC Launch Pre-Configured PLM Solution for Semiconductor Firms
- IBM, Microsoft Launch Agentic AI Platform With Over 6,000 AI Agents
- NHA Selects EkaCare for AI Voice Scribe in Public Health Facilities
- SoftBank Takes $7 Billion Hit on US AI Data Centre Investments
- Anthropic Seeks Up to $64.4 Bn at $1.4 Tn Valuation With IPO
- IBM Ends H-1B, Green Card Sponsorship for Most Roles in Consulting Division