E2E : LAUNCHES BLAZE PAY-PER-TOKEN AI INFERENCE SERVICE

• Blaze is a pay-per-token inference service for open AI models, launched globally on 02-11-2026 • Offers a single OpenAI-compatible API for models including NVIDIA Nemotron, Sarvam, DeepSeek, Qwen, GLM and Gemma • Built on NVIDIA DSX OS with NVIDIA Dynamo serving and CUDA kernels; runs on NVIDIA GPU infrastructure hosted in India • Targets latency-sensitive use cases such as voice, coding agents, document AI, image and video generation • Works with E2E's TIR platform, giving labs and enterprises an India-hosted path from training to production inference • AI factory capacity expanding to about 14.6 MW, including a 1,024-GPU NVIDIA Blackwell cluster live since May 2026 and additional 5.4 MW of Blackwell capacity

E2E Networks Limited

Open attachment

← Back to feed