Together AI
Together AI's OpenAI-compatible chat-completions endpoint, selected with LLM_PROVIDER=together, used to extract facts from conversations.
Enable it
bash
LLM_PROVIDER=together
OPENAI_API_KEY=<together-api-key>
OPENAI_BASE_URL=https://api.together.xyz/v1
OPENAI_LLM_MODEL=meta-llama/Llama-3.3-70B-Instruct-TurboConfiguration
| Variable | Default | Description |
|---|---|---|
LLM_PROVIDER | openai | Set to together. |
OPENAI_API_KEY | (none) | Together API key, sent as a bearer token. |
OPENAI_BASE_URL | https://api.openai.com/v1 | Point at Together's endpoint: https://api.together.xyz/v1. |
OPENAI_LLM_MODEL | gpt-4.1-nano | A Together-hosted model, e.g. meta-llama/Llama-3.3-70B-Instruct-Turbo. |
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 Together's endpoint; its default points at OpenAI.