E2E Networks launches pay-per-token Blaze inference service
AI · First reported 3 Nov, 11:19 · Updated 11:37
E2E Networks says Blaze will give developers and enterprises a single OpenAI-compatible API for open-weight AI models, running on NVIDIA GPU infrastructure hosted in India. The company says its AI factory capacity is expanding to about 14.6 MW.
- Blaze offers access to multiple open-weight models through one OpenAI-compatible API, with customers paying for the tokens they use.
- The service runs on NVIDIA GPU infrastructure in India and is aimed at production inference workloads, including voice, coding agents, document AI and image or video generation.
- E2E says its AI factory capacity is expanding to about 14.6 MW, including a 1,024-GPU Blackwell cluster and additional Blackwell capacity.
Summary written by Lux AI from 2 articles
Key facts
- Service
- Blaze, a pay-per-token AI inference service.
- API
- Single OpenAI-compatible endpoint for open-weight models.
- Infrastructure
- NVIDIA GPU infrastructure hosted in India.
- Capacity
- E2E says its AI factory capacity is expanding to about 14.6 MW.
Source spectrum
Far left
Left
Lean left
Centre
Lean right
Right
Far right
Left 0 · Centre 2 · Right 0 of 2 rated sources
Images from the coverage
Background
All coverage
Coverage over time
LeftCentreRight
Articles per hour since first reported, by side.
Ownership
- Unknown 50% (1)
- Corporation 50% (1)
Share of the 2 sources by owner type.