{ "openapi": "3.1.0", "info": { "title": "Mixen API", "description": "OpenAI-compatible API for [Mixen AI](https://mixen.ai). **Drop-in**: point any\nOpenAI client at this base URL and use your Mixen key — nothing else changes.\n\n```python\nfrom openai import OpenAI\n\nclient = OpenAI(base_url=\"https://api.mixen.ai/v1\", api_key=\"mxn-...\")\nresp = client.chat.completions.create(\n model=\"gpt-5.5\",\n messages=[{\"role\": \"user\", \"content\": \"Hello!\"}],\n)\n```\n\n* **Auth** — `Authorization: Bearer mxn-...`. Create keys in your\n [cabinet](https://mixen.ai/account/profile/api).\n* **Billing** — from your Mixen balance.\n* **Rate limit** — 60 requests/min per key by default (`429` + `Retry-After`).\n* **Endpoints** — `chat/completions`, `images/generations`, `audio/speech` (TTS),\n `audio/transcriptions` (STT), `embeddings`, `models`.\n* **Models** — `GET /models` returns the live catalog with display names, pricing\n (RUB + USD, identical to what is charged) and capabilities. Pass the `id` (or a\n common OpenAI/Claude/Gemini name, e.g. `gpt-4o`, `claude-opus`) in the `model` field.\n\n## Wire protocols\n\nThe same models and the same key are reachable over four request formats — pick the\none your client already speaks:\n\n| Protocol | Base URL | Auth header | Used by |\n| --- | --- | --- | --- |\n| OpenAI Chat Completions | `https://api.mixen.ai/v1` | `Authorization: Bearer` | OpenAI SDK, most tools |\n| OpenAI Responses | `https://api.mixen.ai/v1` | `Authorization: Bearer` | Codex CLI, OpenAI Agents SDK |\n| Anthropic Messages | `https://api.mixen.ai` | `Authorization: Bearer` | Claude Code, Anthropic SDK |\n| Google Gemini | `https://api.mixen.ai/v1beta` | `x-goog-api-key` | gemini-cli, google-genai SDK |\n\n`POST /responses`, `POST /messages` and `POST /messages/count_tokens` are listed below.\nThe Gemini surface is not part of this schema — its routes are addressed Google-style\n(`POST /v1beta/models/{model}:generateContent`, `:streamGenerateContent`, plus\n`GET /v1beta/models`), which OpenAPI paths cannot express; see the\n[gemini-cli guide](https://api.mixen.ai/docs/en/integrations/gemini-cli/).\n", "version": "1.0" }, "paths": { "/models": { "get": { "tags": [ "models" ], "summary": "List models", "description": "Live catalog of available models with display names, per-unit pricing (RUB + USD, identical to what is charged) and capabilities. Each entry has a `type` (text/search/image/video/music/tts/stt/embeddings) telling you which endpoint to call. For text models, `capabilities.reasoning_efforts` lists the valid `reasoning_effort` values and `can_disable_reasoning` whether `\"off\"` is accepted; image models expose `references` (image-to-image via /images/edits); `native_search` marks models with the provider's built-in web search (set `web_search: \"native\"` on chat completions). Pass an `id` in the `model` field of a request; common OpenAI/Anthropic/Google names (e.g. `gpt-4o`, `claude-opus`) are also accepted.", "operationId": "list_models", "responses": { "200": { "description": "Catalog entries", "content": { "application/json": { "schema": { "additionalProperties": true, "type": "object", "title": "Response List Models" }, "example": { "object": "list", "data": [ { "id": "openai/gpt-6-sol", "object": "model", "type": "text", "name": "GPT-6 Sol", "created": 1788000000, "description": "Balanced tier of the GPT-6 family.", "pricing": { "prompt_rub": "228.0", "completion_rub": "1139.9", "prompt_usd": "2.5", "completion_usd": "12.5", "currency_note": "per 1M tokens" }, "capabilities": { "reasoning": true, "reasoning_efforts": [ "low", "medium", "high", "xhigh", "max" ], "can_disable_reasoning": true, "vision": true, "file": true, "video": false, "audio": false, "native_search": true } }, { "id": "openai/gpt-image-2.5-flare", "object": "model", "type": "image", "name": "GPT Image 2.5 Flare", "created": 1785000000, "pricing": { "per_image_rub": "4.1038", "per_image_usd": "0.045" }, "capabilities": { "references": true } } ] } } } } } } }, "/balance": { "get": { "tags": [ "balance" ], "summary": "Get balance", "description": "Available balance of the account that owns this API key, in rubles. The same balance is shared by the Telegram bot, the web cabinet and the API. `balance_rub` is a string with two decimals — parse it as a decimal, not a float, to avoid losing sub-cent precision. Read-only: recharges go through the cabinet.", "operationId": "get_balance", "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } } } } }, "/history": { "get": { "tags": [ "history" ], "summary": "List balance transactions", "description": "Balance movements of the account that owns this API key: generation charges (negative), top-ups, bonuses and referrals (positive), newest first. `amount_rub` is a decimal string with up to 4 decimals — the exact charged value. `model` is the model id for generation charges and `null` for top-ups. Paginated with a cursor: pass `next_cursor` from the response as the `cursor` query parameter to get the next older page.", "operationId": "list_history", "parameters": [ { "name": "cursor", "in": "query", "required": false, "schema": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "Transaction id from a previous response's next_cursor; returns older items.", "title": "Cursor" }, "description": "Transaction id from a previous response's next_cursor; returns older items." }, { "name": "limit", "in": "query", "required": false, "schema": { "type": "integer", "maximum": 200, "minimum": 1, "description": "Page size, max 200.", "default": 50, "title": "Limit" }, "description": "Page size, max 200." } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/generations": { "get": { "tags": [ "generations" ], "summary": "List generations", "description": "Previously generated artifacts of the account that owns this API key: images, videos and music from the bot, the web cabinet and the API alike — newest first. Pass `next_cursor` as `cursor` for the next older page. Fetch the artifact bytes from /v1/generations/{type}/{id}/content. Prompts are returned as stored; `charged_rub` is a decimal string.", "operationId": "list_generations", "parameters": [ { "name": "type", "in": "query", "required": true, "schema": { "enum": [ "image", "video", "music" ], "type": "string", "description": "Artifact kind — histories live in separate tables with separate ids.", "title": "Type" }, "description": "Artifact kind — histories live in separate tables with separate ids." }, { "name": "cursor", "in": "query", "required": false, "schema": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "Item id from a previous response's next_cursor.", "title": "Cursor" }, "description": "Item id from a previous response's next_cursor." }, { "name": "limit", "in": "query", "required": false, "schema": { "type": "integer", "maximum": 200, "minimum": 1, "description": "Page size, max 200.", "default": 50, "title": "Limit" }, "description": "Page size, max 200." } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/generations/{gen_type}/{gen_id}/content": { "get": { "tags": [ "generations" ], "summary": "Download generation content", "description": "Artifact bytes (image, video or audio) of a generation from GET /v1/generations. Supports HTTP Range for video/audio playback.", "operationId": "generation_content", "parameters": [ { "name": "gen_type", "in": "path", "required": true, "schema": { "enum": [ "image", "video", "music" ], "type": "string", "title": "Gen Type" } }, { "name": "gen_id", "in": "path", "required": true, "schema": { "type": "integer", "title": "Gen Id" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/files": { "post": { "tags": [ "files" ], "summary": "Upload file", "description": "Upload a file to your storage. `policy=temp` keeps it for 7 days (then it is deleted automatically), `policy=permanent` — indefinitely, counted against the 1 GB permanent quota. Max size 25 MB. Use stored files as `file_data`/`image_url` inputs (fetch /v1/files/{id}/content) or just to keep results.", "operationId": "upload_file", "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Body_upload_file" } } } }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } }, "get": { "tags": [ "files" ], "summary": "List files", "description": "Your stored files, newest first. Cursor pagination like the other history endpoints: pass `next_cursor` as `cursor`.", "operationId": "list_files", "parameters": [ { "name": "cursor", "in": "query", "required": false, "schema": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "description": "File id from next_cursor.", "title": "Cursor" }, "description": "File id from next_cursor." }, { "name": "limit", "in": "query", "required": false, "schema": { "type": "integer", "maximum": 200, "minimum": 1, "default": 50, "title": "Limit" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/files/stats": { "get": { "tags": [ "files" ], "summary": "Storage stats", "description": "Counts and volumes of your storage: temp and permanent separately, the permanent quota and how much of it is used.", "operationId": "files_stats", "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } } } } }, "/files/{file_id}": { "get": { "tags": [ "files" ], "summary": "Retrieve file", "description": "Metadata of one stored file.", "operationId": "get_file", "parameters": [ { "name": "file_id", "in": "path", "required": true, "schema": { "type": "integer", "title": "File Id" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } }, "delete": { "tags": [ "files" ], "summary": "Delete file", "description": "Deletes the file and its metadata permanently.", "operationId": "delete_file", "parameters": [ { "name": "file_id", "in": "path", "required": true, "schema": { "type": "integer", "title": "File Id" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/files/{file_id}/content": { "get": { "tags": [ "files" ], "summary": "Download file content", "description": "File bytes with the original mime type. Supports HTTP Range.", "operationId": "file_content", "parameters": [ { "name": "file_id", "in": "path", "required": true, "schema": { "type": "integer", "title": "File Id" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/files/{file_id}/keep": { "patch": { "tags": [ "files" ], "summary": "Keep file forever", "description": "Switches a temp file to permanent storage: no expiry, counted against the 1 GB permanent quota.", "operationId": "keep_file", "parameters": [ { "name": "file_id", "in": "path", "required": true, "schema": { "type": "integer", "title": "File Id" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/chat/completions": { "post": { "tags": [ "chat" ], "summary": "Create chat completion", "description": "OpenAI-compatible chat completion. Set `stream=true` for SSE token streaming; otherwise returns a single `chat.completion` object. Charged per-token from balance. Supports vision (image_url data: parts on vision models) and Perplexity Sonar (category=search models) — web results return as message.annotations (url_citation).", "operationId": "chat_completions", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ChatCompletionRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/images/generations": { "post": { "tags": [ "images" ], "summary": "Create image", "description": "OpenAI-compatible text-to-image. Returns base64 images (`b64_json`); `url` is not supported. Models: see GET /models (image), or `dall-e-3`/`gpt-image-1`. Charged per image.", "operationId": "create_image", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ImageGenRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/images/price": { "post": { "tags": [ "images" ], "summary": "Quote an image", "description": "Price of POST /images/generations for the same body, without generating or charging. Computed with the same formula as the actual charge (per image × n).", "operationId": "price_image", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ImageGenRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/images/edits": { "post": { "tags": [ "images" ], "summary": "Edit image (image-to-image)", "description": "OpenAI-compatible image-to-image: multipart `image` (one or more reference images) + `prompt` + `model`. Returns base64 (`b64_json`). Only models that accept image input (GET /models → image with `references: true`): Nano Banana / GPT Image 2 / Seedream / Flux. `aspect_ratio`+`resolution` (or `size`) optional. Charged per image.", "operationId": "create_image_edit", "requestBody": { "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Body_create_image_edit" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/images/upscale": { "post": { "tags": [ "images" ], "summary": "Upscale image", "description": "Upscales an image 2× or 4× (Real-ESRGAN, face enhance on). Multipart: `image` file + `scale` (2 or 4, default 4). Input cap: the side is reduced so the output stays within 4K. Returns base64 (`b64_json`); the result is also saved to your generations history (GET /v1/generations?type=image). Charged per image.", "operationId": "upscale_image", "requestBody": { "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Body_upscale_image" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/audio/speech": { "post": { "tags": [ "audio" ], "summary": "Text to speech", "description": "OpenAI-compatible TTS. Returns mp3 audio. Served by gpt-4o-mini-tts; OpenAI voices (alloy, echo, fable, nova, shimmer, ...) are accepted. Charged per input characters (most models) or per second of generated audio (seed-audio, gemini TTS).", "operationId": "create_speech", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/SpeechRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/audio/transcriptions": { "post": { "tags": [ "audio" ], "summary": "Transcribe audio", "description": "OpenAI-compatible STT (multipart: file + model). Served by whisper-large-v3-turbo. Returns `{\"text\": ..., \"usage\": {\"cost\", \"cost_rub\", \"billing_source\"}}` (or plain text if response_format=text). Charged per minute of audio. Max file size 25 MB.", "operationId": "create_transcription", "requestBody": { "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Body_create_transcription" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/embeddings": { "post": { "tags": [ "embeddings" ], "summary": "Create embeddings", "description": "OpenAI-compatible embeddings. `input` is a string or array of strings. Models: text-embedding-3-small (1536-dim) / -large (3072-dim), qwen/qwen3-embedding-8b, qwen/qwen3-embedding-4b, google/gemini-embedding-2. Charged per input token.", "operationId": "create_embeddings_ep", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/EmbeddingsRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/decisions": { "post": { "tags": [ "decisions" ], "summary": "Submit a Decisions request", "description": "Structured decisions (e.g. `typesafe/jev-1.13`, `openai/gpt-6-luna-decisions`): send `state` and typed `questions` (noul / choice / score), get back typed answers with probabilities instead of generated text. Charged per input token; output tokens are free. See the Decisions guide in API docs.", "operationId": "create_decision_ep", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/DecisionsApiRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/videos": { "post": { "tags": [ "videos" ], "summary": "Create video", "description": "OpenAI-compatible async video job. Returns a Video object (status=queued). Poll GET /videos/{id} until status=completed, then GET /videos/{id}/content for the mp4. Models: see GET /models (video), e.g. veo-3.1-fast, kling-v3-pro, seedance-2.5, happyhorse-1.1.", "operationId": "create_video", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/VideoCreateRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/videos/price": { "post": { "tags": [ "videos" ], "summary": "Quote a video", "description": "Price of POST /videos for the same body, without creating a job or charging. Computed with the same formula as the actual charge (resolution, duration, references).", "operationId": "price_video", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/VideoCreateRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/videos/{video_id}": { "get": { "tags": [ "videos" ], "summary": "Retrieve video", "description": "Poll the video job. status: queued | in_progress | completed | failed.", "operationId": "get_video", "parameters": [ { "name": "video_id", "in": "path", "required": true, "schema": { "type": "string", "title": "Video Id" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/videos/upscale": { "post": { "tags": [ "videos" ], "summary": "Upscale a video", "description": "Video upscaling (FLUX Video Upscale). Multipart: a `video` file (mp4), optional `prompt`, `upscale_factor` (1.5–3.0, default 1.5) and `creativity` (0.0–1.0, default 0.0). Billed per megapixel-second of the output: the amount depends on the source resolution and duration, so it is settled once the job completes. Returns a Video object; poll GET /videos/{id}.", "operationId": "create_video_upscale", "requestBody": { "content": { "multipart/form-data": { "schema": { "$ref": "#/components/schemas/Body_create_video_upscale" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/videos/{video_id}/content": { "get": { "tags": [ "videos" ], "summary": "Download video content", "description": "Returns the mp4 (Range supported) once status=completed.", "operationId": "get_video_content", "parameters": [ { "name": "video_id", "in": "path", "required": true, "schema": { "type": "string", "title": "Video Id" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/audio/music": { "post": { "tags": [ "music" ], "summary": "Create music", "description": "Async music generation (job+poll). Suno (model \"suno\") returns 2 tracks; Lyria (\"lyria\"/\"lyria-pro\") returns 1 instrumental track. Poll GET /audio/music/{id} until status=completed, then GET .../content?index=N for the mp3.", "operationId": "create_music", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/MusicCreateRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/audio/music/price": { "post": { "tags": [ "music" ], "summary": "Quote a music generation", "description": "Price of POST /audio/music for the same body, without creating a job or charging (flat per generation: Suno — 2 tracks, Lyria — 1).", "operationId": "price_music", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/MusicCreateRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/audio/music/{music_id}": { "get": { "tags": [ "music" ], "summary": "Retrieve music", "description": "Poll the music job. status: queued | in_progress | completed | failed.", "operationId": "get_music", "parameters": [ { "name": "music_id", "in": "path", "required": true, "schema": { "type": "string", "title": "Music Id" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/audio/music/{music_id}/content": { "get": { "tags": [ "music" ], "summary": "Download music content", "description": "Returns an mp3 track (Range supported) once status=completed. Use ?index=N to select a track (Suno yields 2, Lyria 1; default 0).", "operationId": "get_music_content", "parameters": [ { "name": "music_id", "in": "path", "required": true, "schema": { "type": "string", "title": "Music Id" } }, { "name": "index", "in": "query", "required": false, "schema": { "type": "integer", "default": 0, "title": "Index" } } ], "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/messages": { "post": { "tags": [ "chat" ], "summary": "Create a message (Anthropic-compatible)", "description": "Anthropic Messages API compatible endpoint for Claude Code / Anthropic SDK. Streaming: SSE events message_start/content_block_*/message_delta/message_stop.", "operationId": "create_message", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AnthropicMessagesRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/messages/count_tokens": { "post": { "tags": [ "chat" ], "summary": "Count tokens (Anthropic-compatible)", "description": "Cheap ~chars/4 estimate without an upstream call. Used by Claude Code for context/compact decisions.", "operationId": "count_tokens", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/CountTokensRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } }, "/responses": { "post": { "tags": [ "chat" ], "summary": "Create a response (OpenAI Responses-compatible)", "description": "OpenAI Responses API compatible endpoint for Codex CLI / OpenAI Agents SDK. Stateless: send the full input on every request (previous_response_id/store are not supported). Streaming: SSE events response.created / response.output_item.* / response.output_text.* / response.completed.", "operationId": "create_response", "requestBody": { "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ResponsesRequest" } } }, "required": true }, "responses": { "200": { "description": "Successful Response", "content": { "application/json": { "schema": {} } } }, "422": { "description": "Validation Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/HTTPValidationError" } } } } } } } }, "components": { "schemas": { "AnthropicMessagesRequest": { "properties": { "model": { "type": "string", "title": "Model" }, "max_tokens": { "type": "integer", "minimum": 1.0, "title": "Max Tokens" }, "messages": { "items": { "additionalProperties": true, "type": "object" }, "type": "array", "title": "Messages" }, "system": { "anyOf": [ { "type": "string" }, { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "System" }, "tools": { "anyOf": [ { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "Tools" }, "tool_choice": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Tool Choice" }, "temperature": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "title": "Temperature" }, "top_p": { "anyOf": [ { "type": "number", "maximum": 1.0, "minimum": 0.0 }, { "type": "null" } ], "title": "Top P" }, "top_k": { "anyOf": [ { "type": "integer", "minimum": 0.0 }, { "type": "null" } ], "title": "Top K" }, "stream": { "type": "boolean", "title": "Stream", "default": false }, "stop_sequences": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "title": "Stop Sequences" }, "thinking": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Thinking" }, "provider": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Provider" }, "service_tier": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Service Tier" }, "metadata": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Metadata" } }, "type": "object", "required": [ "model", "max_tokens", "messages" ], "title": "AnthropicMessagesRequest" }, "Body_create_image_edit": { "properties": { "image": { "items": { "type": "string", "contentMediaType": "application/octet-stream" }, "type": "array", "title": "Image", "description": "Reference image(s) for image-to-image." }, "model": { "type": "string", "title": "Model" }, "prompt": { "type": "string", "title": "Prompt" }, "n": { "type": "integer", "title": "N", "default": 1 }, "size": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Size" }, "aspect_ratio": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Aspect Ratio" }, "resolution": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Resolution" }, "quality": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Quality" }, "background": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Background" }, "output_format": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Output Format" }, "response_format": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Response Format" } }, "type": "object", "required": [ "image", "model", "prompt" ], "title": "Body_create_image_edit" }, "Body_create_transcription": { "properties": { "file": { "type": "string", "contentMediaType": "application/octet-stream", "title": "File" }, "model": { "type": "string", "title": "Model", "default": "whisper-1" }, "language": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Language" }, "response_format": { "type": "string", "title": "Response Format", "default": "json" } }, "type": "object", "required": [ "file" ], "title": "Body_create_transcription" }, "Body_create_video_upscale": { "properties": { "video": { "type": "string", "contentMediaType": "application/octet-stream", "title": "Video", "description": "Source mp4 to enlarge" }, "prompt": { "type": "string", "title": "Prompt", "default": "Upscale this video, keep every detail sharp" }, "upscale_factor": { "type": "number", "title": "Upscale Factor", "default": 1.5 }, "creativity": { "type": "number", "title": "Creativity", "default": 0.0 } }, "type": "object", "required": [ "video" ], "title": "Body_create_video_upscale" }, "Body_upload_file": { "properties": { "file": { "type": "string", "contentMediaType": "application/octet-stream", "title": "File" }, "policy": { "type": "string", "enum": [ "temp", "permanent" ], "title": "Policy", "default": "temp" } }, "type": "object", "required": [ "file" ], "title": "Body_upload_file" }, "Body_upscale_image": { "properties": { "image": { "type": "string", "contentMediaType": "application/octet-stream", "title": "Image" }, "scale": { "type": "integer", "title": "Scale", "default": 4 } }, "type": "object", "required": [ "image" ], "title": "Body_upscale_image" }, "ChatCompletionRequest": { "properties": { "model": { "type": "string", "title": "Model", "description": "Model id from GET /models, or a common OpenAI/Claude/Gemini alias." }, "messages": { "items": { "$ref": "#/components/schemas/_Msg" }, "type": "array", "title": "Messages", "description": "Conversation so far; the last user message is the prompt." }, "stream": { "type": "boolean", "title": "Stream", "description": "If true, stream tokens as SSE (text/event-stream).", "default": false }, "stream_options": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Stream Options", "description": "e.g. {\"include_usage\": true} to append a usage chunk." }, "temperature": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "title": "Temperature" }, "max_tokens": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Max Tokens" }, "max_completion_tokens": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Max Completion Tokens" }, "reasoning_effort": { "anyOf": [ { "type": "string", "enum": [ "off", "low", "medium", "high", "xhigh", "max" ] }, { "type": "null" } ], "title": "Reasoning Effort" }, "tools": { "anyOf": [ { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "Tools" }, "tool_choice": { "anyOf": [ {}, { "type": "null" } ], "title": "Tool Choice" }, "response_format": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Response Format" }, "web_search": { "anyOf": [ { "type": "boolean" }, { "type": "string", "enum": [ "auto", "native", "exa" ] }, { "type": "null" } ], "title": "Web Search" }, "provider": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Provider", "description": "OpenRouter provider routing, passed through as-is: order, only, ignore, sort, allow_fallbacks, data_collection, zdr, quantizations, max_price." }, "service_tier": { "anyOf": [ { "type": "string", "enum": [ "flex", "priority" ] }, { "type": "null" } ], "title": "Service Tier", "description": "Service tier of the same provider: \"flex\" (cheaper, best-effort) or \"priority\" (faster, dearer). Ignored by models that have no such tier." }, "stop": { "anyOf": [ { "items": { "type": "string" }, "type": "array", "maxItems": 4 }, { "type": "null" } ], "title": "Stop", "description": "Up to 4 sequences where the model stops generating further tokens." }, "seed": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Seed", "description": "Sampling seed for best-effort reproducibility." }, "top_p": { "anyOf": [ { "type": "number", "maximum": 1.0, "minimum": 0.0 }, { "type": "null" } ], "title": "Top P", "description": "Nucleus sampling: consider tokens covering this probability mass." }, "top_k": { "anyOf": [ { "type": "integer", "minimum": 0.0 }, { "type": "null" } ], "title": "Top K", "description": "Consider only the K most likely tokens. Open-weight models only." }, "min_p": { "anyOf": [ { "type": "number", "maximum": 1.0, "minimum": 0.0 }, { "type": "null" } ], "title": "Min P", "description": "Drop tokens below this share of the top token probability." }, "frequency_penalty": { "anyOf": [ { "type": "number", "maximum": 2.0, "minimum": -2.0 }, { "type": "null" } ], "title": "Frequency Penalty", "description": "Penalise tokens by how often they already appeared." }, "presence_penalty": { "anyOf": [ { "type": "number", "maximum": 2.0, "minimum": -2.0 }, { "type": "null" } ], "title": "Presence Penalty", "description": "Penalise tokens that appeared at all." }, "repetition_penalty": { "anyOf": [ { "type": "number", "maximum": 2.0, "minimum": 0.0 }, { "type": "null" } ], "title": "Repetition Penalty", "description": "Penalise repetition of the prompt and the answer so far." }, "logprobs": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "title": "Logprobs", "description": "Return log probabilities of the output tokens." }, "top_logprobs": { "anyOf": [ { "type": "integer", "maximum": 20.0, "minimum": 0.0 }, { "type": "null" } ], "title": "Top Logprobs", "description": "How many alternatives per position to return; requires logprobs." }, "plugins": { "anyOf": [ { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "Plugins", "description": "Upstream plugins, passed through as-is: e.g. [{\"id\": \"jev-router\", \"models\": [\"anthropic/*\", \"openai/gpt-6*\"]}] to constrain the Jev Router model pool (also allowed_models, excluded_models, cost_tier)." } }, "type": "object", "required": [ "model", "messages" ], "title": "ChatCompletionRequest", "example": { "messages": [ { "content": "Hello!", "role": "user" } ], "model": "gpt-5.5", "stream": false } }, "CountTokensRequest": { "properties": { "model": { "type": "string", "title": "Model" }, "max_tokens": { "anyOf": [ { "type": "integer", "minimum": 1.0 }, { "type": "null" } ], "title": "Max Tokens" }, "messages": { "items": { "additionalProperties": true, "type": "object" }, "type": "array", "title": "Messages" }, "system": { "anyOf": [ { "type": "string" }, { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "System" }, "tools": { "anyOf": [ { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "Tools" }, "tool_choice": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Tool Choice" }, "temperature": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "title": "Temperature" }, "top_p": { "anyOf": [ { "type": "number", "maximum": 1.0, "minimum": 0.0 }, { "type": "null" } ], "title": "Top P" }, "top_k": { "anyOf": [ { "type": "integer", "minimum": 0.0 }, { "type": "null" } ], "title": "Top K" }, "stream": { "type": "boolean", "title": "Stream", "default": false }, "stop_sequences": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "title": "Stop Sequences" }, "thinking": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Thinking" }, "provider": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Provider" }, "service_tier": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Service Tier" }, "metadata": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Metadata" } }, "type": "object", "required": [ "model", "messages" ], "title": "CountTokensRequest" }, "DecisionsApiRequest": { "properties": { "model": { "type": "string", "title": "Model" }, "state": { "anyOf": [ {}, { "type": "string" }, { "items": {}, "type": "array" } ], "title": "State" }, "questions": { "additionalProperties": { "additionalProperties": true, "type": "object" }, "type": "object", "title": "Questions" }, "session_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Session Id" }, "user": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "User" } }, "type": "object", "required": [ "model", "state", "questions" ], "title": "DecisionsApiRequest", "description": "OR Decisions API-форма (System One: typesafe/jev-*).\n\nstate — string | object | array; questions — map имя→{type: noul|choice|\nscore, instructions, criteria}. Детальная семантика критериев валидирует\nOR — наш слой резолвит модель, биллит по usage.cost и логирует." }, "EmbeddingsRequest": { "properties": { "model": { "type": "string", "title": "Model", "description": "text-embedding-3-small | text-embedding-3-large (or text-embedding-ada-002) | qwen/qwen3-embedding-8b | qwen/qwen3-embedding-4b | google/gemini-embedding-2." }, "input": { "anyOf": [ { "type": "string" }, { "items": { "type": "string" }, "type": "array" } ], "title": "Input", "description": "A string or array of strings to embed." }, "encoding_format": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Encoding Format" } }, "type": "object", "required": [ "model", "input" ], "title": "EmbeddingsRequest", "example": { "input": "hello world", "model": "text-embedding-3-small" } }, "HTTPValidationError": { "properties": { "detail": { "items": { "$ref": "#/components/schemas/ValidationError" }, "type": "array", "title": "Detail" } }, "type": "object", "title": "HTTPValidationError" }, "ImageGenRequest": { "properties": { "model": { "type": "string", "title": "Model", "description": "Image model id from GET /models, or dall-e-3 / gpt-image-1." }, "prompt": { "type": "string", "title": "Prompt" }, "n": { "type": "integer", "maximum": 4.0, "minimum": 1.0, "title": "N", "description": "Number of images (1-4).", "default": 1 }, "size": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Size", "description": "WxH; allowed values are per-model (see GET /models). Alternative to aspect_ratio+resolution." }, "aspect_ratio": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Aspect Ratio", "description": "E.g. 16:9; allowed values are per-model (see GET /models). Defaults to 1:1." }, "resolution": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Resolution", "description": "1k | 2k | 4k; allowed values are per-model (see GET /models). Defaults to 1k." }, "background": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Background", "description": "transparent | opaque | auto — GPT Image 2.5 only; transparent requires png/webp output_format." }, "output_format": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Output Format", "description": "png | jpeg | webp — GPT Image 2.5 only; default png." }, "quality": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Quality", "description": "low | medium — only on models exposing a quality knob (e.g. grok-imagine-image-2)." }, "response_format": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Response Format" } }, "type": "object", "required": [ "model", "prompt" ], "title": "ImageGenRequest", "example": { "model": "gpt-image-1", "prompt": "a red cat", "size": "1024x1024" } }, "MusicCreateRequest": { "properties": { "idempotency_key": { "anyOf": [ { "type": "string", "maxLength": 128, "minLength": 1 }, { "type": "null" } ], "title": "Idempotency Key", "description": "Client idempotency key: a repeated request with the same key (per API key owner) returns the already created job instead of creating and charging a new one." }, "webhook_url": { "anyOf": [ { "type": "string", "maxLength": 2048 }, { "type": "null" } ], "title": "Webhook Url", "description": "Public https URL; when the job reaches completed/failed we POST the same job object that GET returns. Signed with X-Mixen-Signature (t=,v1=): HMAC-SHA256 over \".\", secret = sha256 hex of your API key. Retries at 5/20/60/180 s on non-2xx." }, "wait": { "type": "boolean", "title": "Wait", "description": "Hold the request until the job is terminal (or wait_timeout) and return the final job object. Default false — return the queued job immediately and poll.", "default": false }, "wait_timeout": { "type": "integer", "maximum": 300.0, "minimum": 1.0, "title": "Wait Timeout", "description": "Seconds to wait when wait=true; on timeout the job is returned as is (still running).", "default": 60 }, "model": { "type": "string", "title": "Model", "description": "suno / suno-v6 (song with vocals, 2 tracks) or lyria / lyria-pro (instrumental, 1 track).", "default": "suno" }, "prompt": { "anyOf": [ { "type": "string", "maxLength": 5000 }, { "type": "null" } ], "title": "Prompt", "description": "Track description (Suno simple / Lyria). Unused in Suno custom mode." }, "mode": { "type": "string", "title": "Mode", "description": "Suno: simple (from prompt) | custom (from lyrics+style+title). Ignored by Lyria.", "default": "simple" }, "lyrics": { "anyOf": [ { "type": "string", "maxLength": 5000 }, { "type": "null" } ], "title": "Lyrics", "description": "Suno custom: song lyrics." }, "style": { "type": "string", "maxLength": 500, "title": "Style", "description": "Suno custom: genre, style, tags.", "default": "" }, "title": { "type": "string", "maxLength": 200, "title": "Title", "description": "Suno custom: track title.", "default": "" } }, "type": "object", "title": "MusicCreateRequest", "example": { "model": "suno", "prompt": "lo-fi hip-hop, rain outside the window, calm" } }, "ResponsesRequest": { "properties": { "model": { "type": "string", "title": "Model" }, "input": { "anyOf": [ { "type": "string" }, { "items": { "additionalProperties": true, "type": "object" }, "type": "array" } ], "title": "Input" }, "instructions": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Instructions" }, "tools": { "anyOf": [ { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "Tools" }, "tool_choice": { "anyOf": [ {}, { "type": "null" } ], "title": "Tool Choice" }, "max_output_tokens": { "anyOf": [ { "type": "integer" }, { "type": "null" } ], "title": "Max Output Tokens" }, "temperature": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "title": "Temperature" }, "reasoning": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Reasoning" }, "stream": { "type": "boolean", "title": "Stream", "default": false }, "top_p": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "title": "Top P" }, "provider": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Provider" }, "service_tier": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Service Tier" }, "previous_response_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Previous Response Id" }, "store": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "title": "Store" }, "background": { "anyOf": [ { "type": "boolean" }, { "type": "null" } ], "title": "Background" }, "metadata": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Metadata" }, "text": { "anyOf": [ {}, { "type": "null" } ], "title": "Text" } }, "type": "object", "required": [ "model", "input" ], "title": "ResponsesRequest", "description": "Запрос /v1/responses. extra='ignore': drop-in клиенты шлют много\nне-MVP полей (parallel_tool_calls, truncation, user…) — молча терпим." }, "SpeechRequest": { "properties": { "model": { "type": "string", "title": "Model", "description": "Accepted for compatibility; served by gpt-4o-mini-tts.", "default": "tts-1" }, "input": { "type": "string", "title": "Input", "description": "Text to synthesize." }, "voice": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Voice", "description": "alloy, echo, fable, nova, shimmer, ... (unknown → default)." }, "response_format": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Response Format" }, "speed": { "anyOf": [ { "type": "number" }, { "type": "null" } ], "title": "Speed" } }, "type": "object", "required": [ "input" ], "title": "SpeechRequest", "example": { "input": "Hello there!", "model": "tts-1", "voice": "alloy" } }, "ValidationError": { "properties": { "loc": { "items": { "anyOf": [ { "type": "string" }, { "type": "integer" } ] }, "type": "array", "title": "Location" }, "msg": { "type": "string", "title": "Message" }, "type": { "type": "string", "title": "Error Type" }, "input": { "title": "Input" }, "ctx": { "type": "object", "title": "Context" } }, "type": "object", "required": [ "loc", "msg", "type" ], "title": "ValidationError" }, "VideoCreateRequest": { "properties": { "idempotency_key": { "anyOf": [ { "type": "string", "maxLength": 128, "minLength": 1 }, { "type": "null" } ], "title": "Idempotency Key", "description": "Client idempotency key: a repeated request with the same key (per API key owner) returns the already created job instead of creating and charging a new one." }, "webhook_url": { "anyOf": [ { "type": "string", "maxLength": 2048 }, { "type": "null" } ], "title": "Webhook Url", "description": "Public https URL; when the job reaches completed/failed we POST the same job object that GET returns. Signed with X-Mixen-Signature (t=,v1=): HMAC-SHA256 over \".\", secret = sha256 hex of your API key. Retries at 5/20/60/180 s on non-2xx." }, "wait": { "type": "boolean", "title": "Wait", "description": "Hold the request until the job is terminal (or wait_timeout) and return the final job object. Default false — return the queued job immediately and poll.", "default": false }, "wait_timeout": { "type": "integer", "maximum": 300.0, "minimum": 1.0, "title": "Wait Timeout", "description": "Seconds to wait when wait=true; on timeout the job is returned as is (still running).", "default": 60 }, "model": { "type": "string", "title": "Model", "description": "A catalog video model (veo-3.1-fast, kling-v3-pro, seedance-2.5, happyhorse-1.1, gemini-omni-1.1-flash). The sora-2 aliases are deprecated and redirect to veo-3.1-fast.", "default": "veo-3.1-fast" }, "prompt": { "type": "string", "maxLength": 30000, "minLength": 1, "title": "Prompt" }, "seconds": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Seconds", "description": "Duration in seconds; allowed values are per-model (see GET /models); defaults to the model minimum." }, "size": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Size", "description": "Size WxH; allowed values are per-model (see GET /models); defaults to the model 16:9 720p." }, "input_reference": { "anyOf": [ { "additionalProperties": true, "type": "object" }, { "type": "null" } ], "title": "Input Reference", "description": "Image-to-video: {\"image_url\": \"data:image/...;base64,...\"} (data: URLs only)." }, "input_references": { "anyOf": [ { "items": { "type": "string" }, "type": "array" }, { "type": "null" } ], "title": "Input References", "description": "Reference-to-video (models with \"references\": true in GET /models): data: image URLs. Gemini Omni 1.1 Flash accepts 0 to 7 images (0/empty = generate without references); other models accept from 1 image up to the per-model \"max_references\" from GET /models." }, "seed": { "anyOf": [ { "type": "integer", "maximum": 2147483647.0, "minimum": 0.0 }, { "type": "null" } ], "title": "Seed", "description": "Reproducibility seed (models with \"seed\": true in GET /models). The same prompt with the same seed yields the same clip." } }, "type": "object", "required": [ "prompt" ], "title": "VideoCreateRequest", "example": { "model": "veo-3.1-fast", "prompt": "an astronaut cat riding a motorcycle at night", "seconds": "4", "size": "720x1280" } }, "_Msg": { "properties": { "role": { "type": "string", "title": "Role" }, "content": { "title": "Content" }, "tool_calls": { "anyOf": [ { "items": { "additionalProperties": true, "type": "object" }, "type": "array" }, { "type": "null" } ], "title": "Tool Calls" }, "tool_call_id": { "anyOf": [ { "type": "string" }, { "type": "null" } ], "title": "Tool Call Id" } }, "type": "object", "required": [ "role" ], "title": "_Msg" } }, "securitySchemes": { "ApiKeyAuth": { "type": "http", "scheme": "bearer", "bearerFormat": "mxn-..." } } }, "security": [ { "ApiKeyAuth": [] } ], "tags": [ { "name": "models", "description": "List available models" }, { "name": "chat", "description": "Chat completions (text, vision). Web search via Perplexity Sonar models." }, { "name": "images", "description": "Image generation" }, { "name": "videos", "description": "Video generation (async job + poll)" }, { "name": "music", "description": "Music generation (async job + poll)" }, { "name": "audio", "description": "Text-to-speech and transcription" }, { "name": "embeddings", "description": "Text embeddings" } ], "servers": [ { "url": "https://api.mixen.ai/v1" } ] }