Skip to content

Sarvam AI (BYOK)BYOK

1 modelOpenAI-compatible

About Sarvam AI (BYOK)

Base URL

Models

131K

Sarvam's flagship 105B-parameter sparse Mixture-of-Experts model with 10.3B active parameters, built for reasoning, tool use and the ten most-spoken Indian languages. The 1711 weights run behind the stable sarvam-105b API id with a 128K context window.