> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tracelm.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Authentication

> How to authenticate TraceLM proxy and API endpoints

## 1. Proxy Calls (`/v1/...`)

For `POST /v1/chat/completions` and `POST /v1/completions`:

* `X-API-Key: lt_...` (TraceLM project key)
* `Authorization: Bearer <provider_key>`
* Optional `X-Provider: openai | anthropic | google` (defaults to `openai`)

```bash theme={null}
curl -X POST "https://api.tracelm.ai/v1/chat/completions" \
  -H "X-API-Key: $TRACELM_API_KEY" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "X-Provider: openai" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"Hello"}]}'
```

## 2. Product APIs (`/api/v1/...`)

Most management/reporting endpoints use JWT auth:

* `Authorization: Bearer <access_token>`

Some task/conversation endpoints accept either JWT or `X-API-Key`.

## Agent Context Headers (Optional)

Send these on proxy requests for execution grouping:

* `X-Task-ID`
* `X-Task-Name`
* `X-Conversation-ID`
* `X-User-ID`

These headers drive timeline assembly, loop/failure/context detection, and conversation grouping.