Skip to content

Sarvam AI

Sarvam AI's OpenAI-compatible chat-completions endpoint, selected with LLM_PROVIDER=sarvam, used to extract facts from conversations.

Enable it

bash
LLM_PROVIDER=sarvam
OPENAI_API_KEY=<sarvam-api-key>
OPENAI_BASE_URL=https://api.sarvam.ai/v1
OPENAI_LLM_MODEL=sarvam-m

Configuration

VariableDefaultDescription
LLM_PROVIDERopenaiSet to sarvam.
OPENAI_API_KEY(none)Sarvam API key, sent as a bearer token.
OPENAI_BASE_URLhttps://api.openai.com/v1Point at Sarvam's endpoint: https://api.sarvam.ai/v1.
OPENAI_LLM_MODELgpt-4.1-nanoA Sarvam model, e.g. sarvam-m.

Notes

  • OpenAI-compatible: the provider reuses the OpenAI request handling and only differs by base URL, key, and model.
  • You must override OPENAI_BASE_URL to Sarvam's endpoint; its default points at OpenAI.

The memory layer for AI agents.