LaunchDevelopersNovember 17, 2026

Sarvam opens Token Factory, India-hosted inference for 8 models

Read original source →marktechpost.com

Sarvam Token Factory serves 8 models — including Sarvam 105B (105B total, 9B active, 128K context), GLM 5.3, DeepSeek V4.1 Flash 1017, Kimi K3.1 Pro and Gemma 4 31B — via one OpenAI-compatible API on NVIDIA B200 clusters in India. Sarvam claims Kimi K3.1 Pro hits 6,177 tokens/s per GPU vs 3,213 for InferenceX.

1 source

More stories today

Open the live feed