{ "opencollection": "1.0.0", "info": { "name": "0G Router Inference API", "version": "1.0" }, "items": [ { "info": { "name": "Inference", "type": "folder" }, "items": [ { "info": { "name": "Submit async image edit job", "type": "http" }, "http": { "method": "POST", "url": "/v1/async/images/edits", "headers": [ { "name": "X-0G-Provider-Address", "value": "" }, { "name": "X-0G-Provider-Sort", "value": "" }, { "name": "X-0G-Provider-Trust-Mode", "value": "" }, { "name": "X-0G-Provider-Allow-Fallbacks", "value": "" } ], "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Submit an image editing job to be processed asynchronously. The response includes `jobId` and `provider_address` — clients then poll `/v1/async/jobs/{jobId}` with `?provider_address=...` to retrieve the result.\nSupports provider routing preferences via `X-0G-Provider-*` request headers (`Address`, `Sort`, `Trust-Mode`, `Allow-Fallbacks`). Multipart endpoints have no body-side routing surface — headers only." }, { "info": { "name": "Submit async image generation job", "type": "http" }, "http": { "method": "POST", "url": "/v1/async/images/generations", "headers": [ { "name": "X-0G-Provider-Address", "value": "" }, { "name": "X-0G-Provider-Sort", "value": "" }, { "name": "X-0G-Provider-Trust-Mode", "value": "" }, { "name": "X-0G-Provider-Allow-Fallbacks", "value": "" } ], "body": { "type": "json", "data": "{}" }, "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Submit an image generation job to be processed asynchronously. The response includes `jobId` and `provider_address` — clients then poll `/v1/async/jobs/{jobId}` with `?provider_address=...` to retrieve the result.\n**Provider Routing**: Use `\"provider\": {...}` body field OR `X-0G-Provider-*` request headers. Header > body precedence resolves same-field conflicts." }, { "info": { "name": "Audio transcription", "type": "http" }, "http": { "method": "POST", "url": "/v1/audio/transcriptions", "headers": [ { "name": "X-0G-Provider-Address", "value": "" }, { "name": "X-0G-Provider-Sort", "value": "" }, { "name": "X-0G-Provider-Trust-Mode", "value": "" }, { "name": "X-0G-Provider-Allow-Fallbacks", "value": "" } ], "body": { "type": "json", "data": "{}" }, "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Transcribe audio file to text. Accepts **either** content type:\n- `application/json` (default, schema below): `AudioTranscriptionRequest` body with base64-encoded audio in `file_base64`.\n- `multipart/form-data` (OpenAI-style): `file` part with audio bytes + `model` form field (plus optional `language`, `response_format`). Schema not auto-documented here — matches the OpenAI `/v1/audio/transcriptions` shape.\nSupports provider routing preferences via `X-0G-Provider-*` request headers (`Address`, `" }, { "info": { "name": "Chat completion", "type": "http" }, "http": { "method": "POST", "url": "/v1/chat/completions", "headers": [ { "name": "X-0G-Provider-Address", "value": "" }, { "name": "X-0G-Provider-Sort", "value": "" }, { "name": "X-0G-Provider-Trust-Mode", "value": "" }, { "name": "X-0G-Provider-Allow-Fallbacks", "value": "" } ], "body": { "type": "json", "data": "{}" }, "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Send chat request to AI provider (OpenAI compatible API).\n\n**Web Search**: Add `\"plugins\": [{\"id\": \"web\"}]` to enable real-time web search.\nSearch results are injected into the prompt context and returned as `url_citation` annotations\nin the response. Works with any model. Multi-turn conversations automatically rewrite\nthe query for better search relevance. The injected search context tokens are billed\nas normal input tokens.\n\n**File Attachments**: Upload via `POST /v1/files`, then reference wit" }, { "info": { "name": "Image editing", "type": "http" }, "http": { "method": "POST", "url": "/v1/images/edits", "headers": [ { "name": "X-0G-Provider-Address", "value": "" }, { "name": "X-0G-Provider-Sort", "value": "" }, { "name": "X-0G-Provider-Trust-Mode", "value": "" }, { "name": "X-0G-Provider-Allow-Fallbacks", "value": "" } ], "body": { "type": "multipart-form", "data": [ { "name": "image", "type": "text", "value": "" }, { "name": "prompt", "type": "text", "value": "" }, { "name": "model", "type": "text", "value": "" } ] }, "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Edit an image using AI (inpainting, variations).\nSupports provider routing preferences via `X-0G-Provider-*` request headers (`Address`, `Sort`, `Trust-Mode`, `Allow-Fallbacks`). Multipart endpoints have no body-side routing surface — headers only." }, { "info": { "name": "Image generation", "type": "http" }, "http": { "method": "POST", "url": "/v1/images/generations", "headers": [ { "name": "X-0G-Provider-Address", "value": "" }, { "name": "X-0G-Provider-Sort", "value": "" }, { "name": "X-0G-Provider-Trust-Mode", "value": "" }, { "name": "X-0G-Provider-Allow-Fallbacks", "value": "" } ], "body": { "type": "json", "data": "{}" }, "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Generate images using AI. Supports `provider` routing preferences (see /chat/completions)." }, { "info": { "name": "Anthropic Messages API", "type": "http" }, "http": { "method": "POST", "url": "/v1/messages", "headers": [ { "name": "X-0G-Provider-Address", "value": "" }, { "name": "X-0G-Provider-Sort", "value": "" }, { "name": "X-0G-Provider-Trust-Mode", "value": "" }, { "name": "X-0G-Provider-Allow-Fallbacks", "value": "" } ], "body": { "type": "json", "data": "{}" }, "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Send chat request using Anthropic Messages API format.\nRoutes to providers that support the Anthropic format.\nSupports web search plugins, file attachments, and provider routing preferences\n(same as `/chat/completions`)." }, { "info": { "name": "Preview provider selection (E2EE)", "type": "http" }, "http": { "method": "POST", "url": "/v1/routing/preview", "body": { "type": "json", "data": "{}" }, "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Return, in fallback order, the provider(s) the router WOULD select for a request — WITHOUT executing, billing, or mutating routing state. Built for end-to-end-encrypted (sealed) requests: a sealed request must be encrypted to a specific provider enclave before it can be sent, so a gateway calls this first (with the sensitive `messages` / prompt stripped out), seals to the head candidate, and pins the real request to it via `X-0G-Provider-Address` — falling back to the next candidate (re-sealing)" }, { "info": { "name": "Submit async video generation job", "type": "http" }, "http": { "method": "POST", "url": "/v1/videos", "headers": [ { "name": "X-0G-Provider-Address", "value": "" }, { "name": "X-0G-Provider-Sort", "value": "" }, { "name": "X-0G-Provider-Trust-Mode", "value": "" }, { "name": "X-0G-Provider-Allow-Fallbacks", "value": "" } ], "body": { "type": "json", "data": "{}" }, "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Submit a video generation job (OpenAI Video API shape). The response includes `id` and `provider_address` — clients poll `GET /videos/{id}?provider_address=...` and download the result from `GET /videos/{id}/content?provider_address=...`.\nAccepts `application/json` OR `multipart/form-data`. Use multipart to drive image-to-video: send the same fields as form values plus the reference image as a file part.\nSupports provider routing preferences via `X-0G-Provider-*` request headers (`Address`, `Sor" }, { "info": { "name": "Poll async video generation job", "type": "http" }, "http": { "method": "GET", "url": "/v1/videos/:id", "params": [ { "name": "id", "value": "", "type": "path", "description": "Video job id returned by POST /videos" }, { "name": "provider_address", "value": "", "type": "query", "description": "Pin the provider that owns this job; resolved from the job id when omitted" }, { "name": "verify_tee", "value": "", "type": "query", "description": "Verify the provider's TEE signature and include the trace" } ], "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Return a video job's current status. When the job has completed this is also what settles the charge. `provider_address` is optional — it is resolved from the job id when omitted, so an OpenAI-native client can call `GET /videos/{id}` with no query parameters." }, { "info": { "name": "Download a completed video", "type": "http" }, "http": { "method": "GET", "url": "/v1/videos/:id/content", "params": [ { "name": "id", "value": "", "type": "path", "description": "Video job id returned by POST /videos" }, { "name": "provider_address", "value": "", "type": "query", "description": "Pin the provider that owns this job; resolved from the job id when omitted" }, { "name": "verify_tee", "value": "", "type": "query", "description": "Verify the provider's TEE signature before billing" } ], "auth": { "type": "apikey", "key": "Authorization", "value": "{{Authorization}}", "placement": "header" } }, "docs": "Stream the finished video file. If the job has not been charged yet (the client never polled `GET /videos/{id}`) it is charged before any bytes are sent. A job that is still running returns 409; a job that failed at the provider returns 424. `provider_address` is optional — it is resolved from the job id when omitted." } ] } ], "bundled": true }