India, Nov. 3 -- E2E Networks Ltd has launched Blaze, a pay-per-token inference service designed to provide developers and enterprises with access to open-weight artificial intelligence (AI) models through a single application programming interface (API).

The service runs on Nvidia GPU infrastructure hosted in India and incorporates open-source components from the Nvidia DSX OS software stack. It provides an OpenAI-compatible endpoint for models including Nvidia Nemotron, Sarvam, DeepSeek, Qwen, GLM and Gemma, with customers paying according to the number of tokens consumed.

The launch comes as Indian enterprises and AI developers move from pilot projects to production deployments, increasing the importance of inference costs, latency a...