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-mConfiguration
| Variable | Default | Description |
|---|---|---|
LLM_PROVIDER | openai | Set to sarvam. |
OPENAI_API_KEY | (none) | Sarvam API key, sent as a bearer token. |
OPENAI_BASE_URL | https://api.openai.com/v1 | Point at Sarvam's endpoint: https://api.sarvam.ai/v1. |
OPENAI_LLM_MODEL | gpt-4.1-nano | A 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_URLto Sarvam's endpoint; its default points at OpenAI.