# Telnyx AI: LLM Token Gateway — Documentation Index
> LLM Token Gateway documentation within the AI section of the Telnyx developer docs (https://developers.telnyx.com).
> This file: https://developers.telnyx.com/docs/development/llms/ai-llm-token-gateway-llms-txt · Root index: https://developers.telnyx.com/llms.txt

## LLM Token Gateway

- [Overview](https://developers.telnyx.com/docs/inference/llm-token-gateway.md): Give applications scoped, budgeted access to language models through OpenAI- and Anthropic-compatible APIs, with Telnyx-hosted models or your own provider keys. Create groups, users and token keys, a…
- [Quickstart](https://developers.telnyx.com/docs/inference/llm-token-gateway/quickstart.md): Create a token group, issue a scoped token key, call a model with the OpenAI SDK, inspect usage and revoke the key.

## API

- [Inference API](https://developers.telnyx.com/docs/inference/llm-token-gateway/inference-api.md): Call models through LLM Token Gateway with the official OpenAI and Anthropic SDKs: Telnyx-hosted and bring-your-own-key models, base URL, authentication, streaming, request limits and the supported r…
- [Management API](https://developers.telnyx.com/docs/inference/llm-token-gateway/management-api.md): Provision token groups, users, keys, end-user caps and provider keys through the LLM Token Gateway management API, with idempotency, ETag preconditions and snapshot pagination.

## Concepts

- [Budgets & rate limits](https://developers.telnyx.com/docs/inference/llm-token-gateway/controls.md): How LLM Token Gateway enforces budgets, rate limits and end-user identity, and what an application observes at each limit.
- [Bring your own key](https://developers.telnyx.com/docs/inference/llm-token-gateway/byok.md): Attach your own OpenAI or Anthropic key to LLM Token Gateway groups so your provider bills inference directly, while Telnyx keeps enforcing budgets, rate limits and attribution.
- [Usage reporting](https://developers.telnyx.com/docs/inference/llm-token-gateway/usage.md): Query LLM Token Gateway spend events and dimensional summaries by group, user, key or end user, and interpret cost and unknown-usage fields correctly.
- [Errors](https://developers.telnyx.com/docs/inference/llm-token-gateway/errors.md): HTTP status codes, structured error codes and error envelopes returned by the LLM Token Gateway management and inference planes, with handling guidance.