Token Hub documentation
One OpenAI-compatible API for every model in the catalog — metered per token, with automatic failover across upstream routes.
Quickstart
curl https://tokenhub-staging.coality.io/v1/chat/completions \
-H "Authorization: Bearer $TOKEN_HUB_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5-3",
"messages": [{"role": "user", "content": "Explain vector databases in one paragraph"}]
}'Guides
Models & Inference
Text ModelsQuery chat models via the OpenAI-compatible APIVision ModelsSend images alongside text promptsEmbeddings & RerankingVector representations and relevance scoringTool CallingLet models call your functionsReasoningModels that think before they answerReliability and Error HandlingFailover, retries, and error semanticsBatch APIHigh-throughput asynchronous workloadsModel Quality and PrecisionCompare models and understand quality signals