E2E Networks launches pay-per-token AI inference service in India
E2E Networks introduced Blaze, an inference service enabling developers and enterprises to access open AI models through a single OpenAI-compatible API. The service supports models including NVIDIA Nemotron, Sarvam, DeepSeek, Qwen, GLM, and Gemma, using a pay-per-token pricing model. This represents E2E Networks' entry into the growing AI inference market.
Key points
- New pay-per-token inference service for open-source AI models
- OpenAI-compatible API supporting multiple models
- Targets developers and enterprises in India
Summary and key points written by AI from the headline and a short excerpt, so they can be incomplete or wrong. Express Computer did the reporting; read the original for the full story.
Read the full story at Express Computer
