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

# Inference API Reference

> Concrete API reference for the Tensormesh serverless inference surface.

Use this section when you are calling Tensormesh inference directly over HTTP instead of through the Python SDK or the `tm` CLI.

Direct inference callers should expect `429` rate limits on busy surfaces, honor `Retry-After` when present, and avoid automatic retries around non-idempotent writes unless duplicate effects are acceptable.

## Surface

**Serverless**: OpenAI-compatible chat completions plus verified `models`, `completions`, `responses`, `tokenize`, `detokenize`, `health`, and `version` endpoints on the public serverless host.

Auth: `Authorization: Bearer <API_KEY>` for POST routes; `GET /v1/models`, `/health`, and `/version` also work on the public host without auth.

## Start Here

* [Serverless Chat Completions](/api-reference/serverless)
* [Serverless Models](/api-reference/serverless/models)
* [Serverless Responses](/api-reference/serverless/responses)
* [API Quickstart](/api-quickstart)
* [Choose A Serverless Model Name](/serverless-model-selection)

If you need management APIs for users, models, billing, support, logs, or metrics, use the **Control Plane API** tab instead of this section.