Documentation
Start with the quickstart, then dive into the reference pages for rate limits, error codes, and SDK integration.
Guides
-
Quickstart
Go from zero to your first token-hub API call in under five minutes. Sign up, create a key, send a cURL request, and connect OpenAI-compatible or Anthropic Messages-compatible clients.
-
FAQ
Answers to common questions about token-hub - current routes, CLI compatibility, billing, data handling, rate limits, and refunds.
-
Troubleshooting
Diagnose and fix common token-hub errors - 401 invalid token, 402 insufficient balance, 429 rate limit, 502 upstream down, 504 timeout.
Scenarios
View all →-
Batch classification with token-hub
Run large-volume classification jobs through token-hub with aiohttp, bounded concurrency, retries, and the verified moonshot-v1-8k route.
-
Chat app with streaming responses
Build a server-side chat route that streams OpenAI-compatible output through token-hub using the currently verified moonshot-v1-8k route.
-
RAG answer synthesis through token-hub
Use token-hub as the generation step in a retrieval pipeline while keeping embeddings and vector storage in your own stack.