Introduction

How developers use Xenodia's unified LLM token API, media APIs, agents, credits, and payments.

Intelligence, through one API.

Xenodia provides a unified LLM token API for developers and agents. Compare available models and public token pricing, make requests through one API, and track usage in your account. Image and video APIs extend the same account.

Use these docs when you need to:

Call leading language models through an OpenAI-compatible endpoint.
Discover available text, image, and video models before choosing a model ID.
Create asynchronous image and video tasks and poll for results.
Discover and invoke capabilities with agent-readable contracts.
Bind owner and agent wallets for controlled billing.
Install the Xenodia CLI and skill instructions for supported agent runtimes.

Who this is for

Product backends that need one integration for text and media models.
Agent platforms that need API keys, wallet boundaries, and live model discovery.
Skill and MCP builders that need a stable action layer for billing and capability calls.

Core concepts

Concept	Meaning
LLM tokens	Units of text input and output consumed or generated by a model. Token counts are usage measurements, not an account balance.
Credits	Fund your account and use the balance to pay for supported model, media, and capability requests.
Model APIs	OpenAI-compatible text calls plus shared image and video generation endpoints.
Model discovery	`GET /v1/models` returns current model IDs, modalities, public capability metadata, pricing, and availability.
Capabilities	`GET /v1/capabilities` returns agent-ready tools with operations, pricing, availability, and instructions.
Wallet-aware billing	Runtime calls use a Xenodia credential; billing can resolve through owner, agent, or controlled fallback rules.
Task resource	Long-running media and capability work returns `task_id`, `state`, `poll_url`, and normalized `result` or `error` fields.

Public surfaces

Surface	Purpose
`https://www.xenodia.xyz`	Model catalog, public pricing, account, and console.
`https://docs.xenodia.xyz`	Developer documentation and API reference.
`https://api.xenodia.xyz`	Runtime API.

Start building

Start with Quickstart for a working request. Read Authentication before connecting a server. Use Model Discovery before shipping model-specific behavior. Use Capabilities when an agent needs to discover and call tools through Xenodia.

For an OpenAI-compatible client:

Set the base URL to https://api.xenodia.xyz.
Use a Xenodia API key as the Bearer token.
Query /v1/models and select a currently enabled, available model ID.
Send POST /v1/chat/completions with that model ID.

Source of truth

For model IDs, availability, capabilities, and API pricing, use the live API and generated reference. Use your signed-in account for current credit balance, payment options, and usage records. Do not copy changing values from examples into production logic.