Guides
Task-oriented walkthroughs for calling Faucet — authentication, a first request, streaming, chat, embeddings, images and transcription.
Guides explain how to do something end to end. Read Getting started first; the rest can be read in any order as you need them.
Getting started
What Faucet is, how to get an organization and a key, and your first request.
SDKs and clients
The Vercel AI SDK, the official OpenAI SDKs, and Claude Code.
Choosing a model
How slugs and aliases work, and how to ask what your key can reach.
Streaming and usage
SSE on both dialects, and how every request is metered.
Chat
Multi-turn conversations, prompt caching, tools, JSON and image inputs.
Embeddings
Vectors, widths, and telling Voyage what the text is for.
Images
Generating and editing pictures across three providers.
Transcription
Audio in, a transcript out, and which formats are served.
Management keys
Minting and revoking inference keys from your own backend.
Errors and limits
What each status means, your allowance, and prepaid credit.
The shape of it
One HTTPS endpoint that speaks the OpenAI wire format across every provider
and the native Anthropic Messages format for Anthropic models. You send a
request with a Faucet key, name a model as provider/model, and Faucet routes
it, streams the response back, and records what it cost.
Base URL https://api.intfaucet.com/v1
Auth Authorization: Bearer fct_live_…
Endpoints /messages, /chat/completions, /embeddings, /images/generations,
/images/edits, /audio/transcriptions, /models, /credits, /keyEvery slug Faucet carries is in the Models reference.