API Reference
OpenAI-compatible REST API for ORGN Gateway.
Base URL
https://api.gateway.orgn.comAuthentication
Authorization: Bearer sk-ollm-…Pass your API key as a bearer token. Model selection determines TEE or ZDR execution path. See authentication for key format and environments.
Generate a model response for a conversation. Set `stream: true` to receive Server-Sent Events. Only `model` and `messages` are required. `n` must be `1` (or omitted); other values are rejected. `stop` accepts an array of strings only (a bare string is not supported).
/v1/chat/completions
Generate embedding vectors for input text. Model names should be prefixed with `ollm::embedding_model_name::` (an unprefixed name is accepted but emits a deprecation warning).
/v1/embeddings
Rank a list of documents by relevance to a query (Cohere-compatible shape). The gateway proxies the request to the model's first provider, which must be an OpenAI-type provider exposing a `/rerank` endpoint.
/v1/rerank
Transcribe an audio file (OpenAI-compatible `multipart/form-data`). The gateway re-streams the form to the model's first provider, which must be an OpenAI-type provider exposing an `/audio/transcriptions` endpoint. Maximum request body size is 100 MB.
/v1/audio/transcriptions
List the active model catalog. Only models marked active are returned. Tier filters subtract models: `allow_tee=false` excludes TEE-tagged models, `allow_zdr=false` excludes ZDR-tagged models. Models without a tier tag are always returned.
/v1/models
Returns the gateway status, version, and config hash. Never requires authentication.
/status
Returns the availability of backing services (Postgres, ClickHouse, Valkey). Returns 200 when healthy, otherwise a non-2xx status with per-service detail. Never requires authentication.
/health
Prometheus text-format metrics exposition.
/metrics