AnyPath Docs

AnyPath is a shared supply network for official AI API capacity. Suppliers connect official provider credentials; callers reach that capacity with one API key at a published discount to the official list price; both sides settle in USDT.

Two ways to use AnyPath

You want to	You are a	Start with
Call official models for less	Caller	API Access
Turn spare official capacity into USDT	Supplier	Supplier guide

Start here

Goal	Page
Create a key and send a first request	API Access
Learn the few terms these docs use	Concepts
See how the price is set	Pricing and billing
Check that you got the model you asked for	Verify what served your request
Know your request and token limits	Rate limits and tiers
Handle failures and retries safely	Error Handling
Connect a credential and start earning	Supplier guide

What is public

• Live supply and price: the current multiplier for each provider, its supply, demand, success rate, and latency.
• Every request you send keeps its own record: which provider served it, the upstream model, metered usage, the price applied, and how it settled.
• Failed requests are not charged, and suppliers are not paid for them.

Public API

API type	Endpoint
Model discovery	GET /v1/models
OpenAI Chat Completions	POST /v1/chat/completions
OpenAI Responses	POST /v1/responses
Anthropic Messages	POST /v1/messages, POST /v1/messages/count_tokens
Images	POST /v1/images/generations, POST /v1/images/edits
Gemini /v1beta	GET /v1beta/models, GET /v1beta/models/{model}, POST /v1beta/models/{model}:generateContent, POST /v1beta/models/{model}:streamGenerateContent, POST /v1beta/models/{model}:countTokens