# Xailon Token Factory Docs

> One OpenAI-compatible endpoint for every LLM provider, with metering, credits, and enforcement you own end-to-end.

This file lists every documentation page so AI coding agents (Claude Code,
Cursor, Codex, …) can consume the docs directly. A concatenated version of all
pages is at https://www.tokenfactory.iamsaif.ai/docs/llms-full.txt.

## Guides

- [Authentication](https://www.tokenfactory.iamsaif.ai/docs/authentication): API keys, auth headers, key hierarchy, request ids, and how auth failures are reported.
- [Billing](https://www.tokenfactory.iamsaif.ai/docs/billing): The prepaid wallet, request-time credit reservations, metered usage, and video billing.
- [Errors](https://www.tokenfactory.iamsaif.ai/docs/errors): The uniform error envelope, status rules, and the full error-code table.
- [Models & Aliases](https://www.tokenfactory.iamsaif.ai/docs/models-and-aliases): Curated aliases, listing models, the alias echo guarantee, and the deprecation lifecycle.
- [OpenAI & Anthropic Compatibility](https://www.tokenfactory.iamsaif.ai/docs/openai-anthropic-compatibility): The gateway's two wire dialects — same underlying contract, different shapes.
- [Overview](https://www.tokenfactory.iamsaif.ai/docs/overview): One OpenAI-compatible endpoint for every LLM provider, with metering, credits, and enforcement you own end-to-end.
- [Provider Routing & Failover](https://www.tokenfactory.iamsaif.ai/docs/provider-routing): How the gateway picks the provider behind a model alias, and what happens when one fails.
- [Quickstart](https://www.tokenfactory.iamsaif.ai/docs/quickstart): Make your first API call in five minutes — curl, Python, Node.js, or the OpenAI/Anthropic SDKs.
- [Rate Limits & Quotas](https://www.tokenfactory.iamsaif.ai/docs/rate-limits): RPM windows, token quotas, the response headers, and how 429s behave.
- [SDKs & Tools](https://www.tokenfactory.iamsaif.ai/docs/sdks): Which client SDKs and tools work with the gateway — what is tested vs what should work.
- [Single sign-on (SSO)](https://www.tokenfactory.iamsaif.ai/docs/single-sign-on): Connect your organization's identity provider, and the exact redirect URIs to register on the IdP side for Microsoft Entra ID, Google Workspace, Okta, generic OIDC and SAML.
- [Streaming](https://www.tokenfactory.iamsaif.ai/docs/streaming): SSE shapes, the always-present final usage chunk, side-channel headers, and in-band error handling.
- [API Versioning](https://www.tokenfactory.iamsaif.ai/docs/versioning): Contract v1, what counts as a breaking change, and how deprecations are communicated.

## API Reference

- [Text to Speech](https://www.tokenfactory.iamsaif.ai/docs/api-reference/audio-speech): Synthesize audio from input text.
- [Transcriptions](https://www.tokenfactory.iamsaif.ai/docs/api-reference/audio-transcriptions): Transcribe audio into text.
- [Chat Completions](https://www.tokenfactory.iamsaif.ai/docs/api-reference/chat-completions): Create a model response for a chat conversation — OpenAI dialect, with tools and vision.
- [Text Completions](https://www.tokenfactory.iamsaif.ai/docs/api-reference/completions): Legacy OpenAI text completion endpoint.
- [Embeddings](https://www.tokenfactory.iamsaif.ai/docs/api-reference/embeddings): Create a vector embedding for input text.
- [Image Generation](https://www.tokenfactory.iamsaif.ai/docs/api-reference/images-generations): Generate images from a text prompt.
- [Anthropic Messages](https://www.tokenfactory.iamsaif.ai/docs/api-reference/messages): Anthropic Messages dialect for Claude SDKs — translated and routed to the serving provider.
- [List Models](https://www.tokenfactory.iamsaif.ai/docs/api-reference/models-list): List the model aliases this API key can request.
- [Overview](https://www.tokenfactory.iamsaif.ai/docs/api-reference/overview): The complete Token Factory inference surface — every endpoint across chat, completions, messages, embeddings, images, audio, rerank, video, and the model catalogue.
- [Rerank](https://www.tokenfactory.iamsaif.ai/docs/api-reference/rerank): Rerank documents against a query by relevance.
- [Videos — Cancel Job](https://www.tokenfactory.iamsaif.ai/docs/api-reference/videos-cancel): Cancel a video job that has not yet completed.
- [Videos — Create Job](https://www.tokenfactory.iamsaif.ai/docs/api-reference/videos-create): Submit an async video-generation job.
- [Videos — Poll Job](https://www.tokenfactory.iamsaif.ai/docs/api-reference/videos-poll): Retrieve the current state of a video job.

## Management API

- [Audit log](https://www.tokenfactory.iamsaif.ai/docs/management-api/audit): Read and export the audit trail of administrative actions in your organization.
- [Authentication](https://www.tokenfactory.iamsaif.ai/docs/management-api/authentication): How Management API requests are authenticated with a personal access token.
- [Billing](https://www.tokenfactory.iamsaif.ai/docs/management-api/billing): Read your balance, credit grants, and invoices. Reads only — no money moves through this API.
- [Catalog](https://www.tokenfactory.iamsaif.ai/docs/management-api/catalog): List the models and regions available to your organization — the vocabulary allowlists are written in.
- [Automate from a CI pipeline](https://www.tokenfactory.iamsaif.ai/docs/management-api/ci-pipeline): Use a scoped personal access token to create and rotate a project's keys from CI.
- [Errors](https://www.tokenfactory.iamsaif.ai/docs/management-api/errors): The error envelope, HTTP status codes, and error codes returned by the Management API.
- [Idempotency](https://www.tokenfactory.iamsaif.ai/docs/management-api/idempotency): Safely retry mutating Management API requests with idempotency keys.
- [Incident response](https://www.tokenfactory.iamsaif.ai/docs/management-api/incident-response): Use the Management API to contain a leaked key, a runaway workload, or a compromised account quickly.
- [Invites](https://www.tokenfactory.iamsaif.ai/docs/management-api/invites): List your organization's pending invitations and revoke the ones you no longer want.
- [API keys](https://www.tokenfactory.iamsaif.ai/docs/management-api/keys): Create, list, rotate, disable, and delete a project's inference API keys.
- [Members](https://www.tokenfactory.iamsaif.ai/docs/management-api/members): List organization members and change their role, project access, and state.
- [Organization](https://www.tokenfactory.iamsaif.ai/docs/management-api/org): Read your organization, and read and update its settings.
- [Overview](https://www.tokenfactory.iamsaif.ai/docs/management-api/overview): What the Management API is — a programmatic, token-authenticated interface for administering your organization.
- [Pagination](https://www.tokenfactory.iamsaif.ai/docs/management-api/pagination): How list endpoints page through results.
- [Personal access tokens](https://www.tokenfactory.iamsaif.ai/docs/management-api/personal-access-tokens): Create, scope, rotate, and revoke the personal access tokens that authenticate Management API calls.
- [Projects](https://www.tokenfactory.iamsaif.ai/docs/management-api/projects): Create, list, update, disable, and delete projects and their guardrails.
- [Quickstart](https://www.tokenfactory.iamsaif.ai/docs/management-api/quickstart): Create a personal access token and make your first Management API call.
- [Rate limits](https://www.tokenfactory.iamsaif.ai/docs/management-api/rate-limits): Request limits for the Management API and how to handle 429 responses.
- [Scopes](https://www.tokenfactory.iamsaif.ai/docs/management-api/scopes): The permission scopes a personal access token can carry and which operations each scope allows.
- [Tokens](https://www.tokenfactory.iamsaif.ai/docs/management-api/tokens): List and revoke your own personal access tokens from the API.
- [Usage](https://www.tokenfactory.iamsaif.ai/docs/management-api/usage): Query token usage and spend across your organization and projects.
- [Versioning](https://www.tokenfactory.iamsaif.ai/docs/management-api/versioning): How the Management API is versioned, what can change within v1, and how deprecations are announced.

## Terms and Policy

- [Data Processing Agreement](https://www.tokenfactory.iamsaif.ai/docs/legal/data-processing-agreement): How Infinia Technologies processes personal data on your behalf, its sub-processors, and the standard contractual clauses.
- [Privacy Policy](https://www.tokenfactory.iamsaif.ai/docs/legal/privacy-policy): How Infinia Technologies processes personal data as a controller in connection with Xailon Token Factory.
- [Terms of Use](https://www.tokenfactory.iamsaif.ai/docs/legal/terms-of-use): The terms governing your use of Xailon Token Factory, including service modes, acceptable use, and data retention.

## Links

- [Support](mailto:support@iamsaif.ai)