Skip to main content
GoModel exposes OpenAI-compatible and Anthropic-compatible APIs, provider-native passthrough, and a set of operations endpoints. Admin and dashboard routes are documented separately in Admin Endpoints. For request and response details, see the dedicated guides: Responses API, Conversations API, Anthropic Messages API, and Audio API.

OpenAI-Compatible API

EndpointMethodDescription
/v1/chat/completionsPOSTChat completions (streaming supported)
/v1/responsesPOSTCreate an OpenAI Responses API response
/v1/responses/{id}GETRetrieve a stored response
/v1/responses/{id}DELETEDelete a stored response (forwards native deletion where supported)
/v1/responses/{id}/cancelPOSTCancel an in-progress response (provider-native where supported)
/v1/responses/{id}/input_itemsGETList the input items of a stored response
/v1/responses/input_tokensPOSTCount input tokens for a Responses request
/v1/responses/compactPOSTCompact a Responses conversation (provider-native where supported)
/v1/conversationsPOSTCreate a conversation (gateway-managed)
/v1/conversations/{id}GETRetrieve a conversation
/v1/conversations/{id}POSTReplace conversation metadata in full
/v1/conversations/{id}DELETEDelete a conversation
/v1/embeddingsPOSTText embeddings
/v1/modelsGETList available models
/v1/audio/speechPOSTText-to-speech, returning binary audio
/v1/audio/transcriptionsPOSTSpeech-to-text from a multipart upload
/v1/realtimeGETRealtime speech-to-speech websocket upgrade (when REALTIME_ENABLED)
/v1/filesPOSTUpload a file (OpenAI-compatible multipart)
/v1/filesGETList files
/v1/files/{id}GETRetrieve file metadata
/v1/files/{id}DELETEDelete a file
/v1/files/{id}/contentGETRetrieve raw file content
/v1/batchesPOSTCreate a native provider batch (OpenAI-compatible schema; inline requests supported where provider-native)
/v1/batchesGETList stored batches
/v1/batches/{id}GETRetrieve one stored batch
/v1/batches/{id}/cancelPOSTCancel a pending batch
/v1/batches/{id}/resultsGETRetrieve native batch results when available

Anthropic-Compatible API

EndpointMethodDescription
/v1/messagesPOSTAnthropic Messages API through translated model routing (streaming supported)
/v1/messages/count_tokensPOSTHeuristic Anthropic Messages input token estimate

Provider Passthrough

EndpointMethodDescription
/p/{provider}/...GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONSProvider-native passthrough with opaque upstream responses

Admin Endpoints

Admin REST and dashboard routes (/admin/*) are covered in Admin Endpoints.

Operations Endpoints

EndpointMethodDescription
/healthGETLiveness check (always 200 while the process serves)
/health/readyGETReadiness check: pings storage (503 if down) and Redis cache (degraded, still 200)
/metricsGETPrometheus metrics (experimental, when enabled)
/swagger/index.htmlGETSwagger UI (when enabled)