> ## Documentation Index > Fetch the complete documentation index at: https://docs.budgetpixel.com/llms.txt > Use this file to discover all available pages before exploring further. # Add an outfit > Add clothes to your wardrobe so a character can wear them, from one source: - `image_url`: any picture's own address, one of your BudgetPixel pictures, or a shop's **product page**. A page is read once for the product picture and name it publishes for link previews. Many shops don't allow automatic reading, or show no product picture; then the answer is `422` with `code: link_unreadable`, a `link_problem` (`blocked`, `login`, `not_found`, `no_image`, `not_clothes`, `bad_url`, `failed`) and a message that says what to do instead: use the product picture's own address (right-click it, *Copy image address*), or send the picture itself. - `image_data`: the picture as base64 or a data URL. - `description`: the clothes in words, designed for you (a link inside is read like `image_url`). `mode` (optional): `photo` (someone wears it: the clothes are taken out onto an invisible mannequin), `clean` (the picture shows only the clothes: used as it is) or `text` (from the description). A picture from a link that shows the clothes on their own is used as it is, whatever the mode: there is nobody to take them off. **Price:** a clean picture is free; `photo` and `text` run an image model at its usual price (`model`, default `nano-banana-2.1`), charged on success. Limited to 60 calls per day and 10 a minute per account. **Answer:** `201` with the outfit when it is ready at once (a clean picture), else `202` with its `id` and `status: processing`: the picture usually takes about a minute. `GET /v1/wardrobe/{id}` returns it when `status` is `ready`, with its final handle. ## OpenAPI ````yaml /openapi.yaml post /wardrobe openapi: 3.1.0 info: contact: email: support@budgetpixel.com name: BudgetPixel Support description: > The BudgetPixel developer API for programmatic image, video, music and sound-effect generation. Generation is **asynchronous**: you create a job, then poll its status until it reaches a terminal state (`succeeded` / `failed`). You are charged in credits only on success — never for failures, timeouts, or content blocked before generation. **Authentication.** All requests require an API key sent as a bearer token: Authorization: Bearer bpx_live_xxx Create and manage keys from your BudgetPixel account dashboard. The developer API is available on **every paid plan**. On the **Free** plan, API keys can call the free library searches only: `GET /v1/stock/images`, `GET /v1/stock/sound-effects` and `GET /v1/stock/music`. **Pricing.** API usage is metered in credits at each model's published price (see `GET /v1/models`), and your plan's model discounts and active promotions apply to API charges exactly as they do on the web — `POST /v1/cost` quotes your discounted price. Pro and Ultra plans include a daily free-models allowance (a shared pool of free generations per day across qualified image models such as FLUX 2 Klein and Qwen-Image) that covers API requests too — the standard price applies once the day's pool is used. Other promotional free daily generations remain web/app-only. Failed generations are never charged. **Rate limits.** Requests are limited per minute: **600 requests/min per API key** and **1200 requests/min per source IP** (defaults; subject to tuning). Every response carries `X-RateLimit-Limit`, `X-RateLimit-Remaining`, and `X-RateLimit-Reset` (seconds until the window resets). Exceeding a limit returns HTTP `429` with a `Retry-After` header — wait that long before retrying. Rejected requests still count against the window, so a tight retry loop keeps you limited; back off instead. Generation jobs additionally have a per-plan concurrency cap (the same one as the web workshop), independent of these request limits. `POST /v1/uploads` also has a dedicated **60 uploads/min per account** cap (it's free/unmetered) on top of these limits. Every `429` this API returns carries `Retry-After`, including a full concurrency queue (a suggested wait) and the monthly spend limit (seconds until the month resets). **Characters.** Write `@handle` in the prompt of an image or video generation to cast a character: one of the free BudgetPixel AI influencers (`@barry`, `@rosa`, ...) or a character of your own. Its picture and look go with the mention, so the same face appears in every post. `GET /v1/characters` lists the ones you can cast, `GET /v1/characters/{handle}` gives one in full with every picture, and `POST /v1/characters/recommend` picks influencers for a brief. **Wardrobe.** Dress a character by writing an outfit's `@handle` next to theirs: `@barry wearing @camel_belted_overcoat_outfit`. The outfit's picture goes with the mention and the character wears it in place of their own clothes. `GET /v1/wardrobe` lists the outfits you can use (your own, the ones you saved and the free library) and `GET /v1/wardrobe/{handle}` gives one in full. **Output retention.** Generated files are kept for 24 hours after the job is created. Job status responses give the exact time as `expires_at`; after it, `expired` is `true` and no download URLs are returned. title: BudgetPixel API version: '2026-06-20' servers: - description: Production url: https://api.budgetpixel.com/v1 security: - ApiKeyAuth: [] tags: - description: Account and credit balance name: Account - description: Discover available models and pricing name: Models - description: Upload input media for image/video generation name: Uploads - description: Image job status name: Images - description: FLUX image models name: Black Forest Labs - description: SeeDream image models name: Bytedance - description: Video job status name: Videos - description: Kuaishou Kling video models name: Kling - description: SeeDance video models name: ByteDance (SeeDance) - description: Music and sound-effect job status name: Audios - description: Music generation models name: Music - description: Text-to-sound-effect models (priced per second) name: Sound Effects - description: >- Image-to-3D models — a picture in, a textured 3D model (GLB, plus FBX/USDZ/STL on Meshy) out name: 3D Models - description: Format conversion for images, video, and audio name: Conversions - description: Publish posts to your BudgetPixel feed and enter clan themes name: Social - description: Cast BudgetPixel AI influencers and your own characters with @mentions name: Characters - description: >- Outfits your characters can wear, called with an @mention next to the character name: Wardrobe - description: >- Body poses your characters can take, called with an @mention after the character name: Poses - description: Content moderation — NSFW rating and CSAM detection name: Moderation - description: Content classification — music genre detection name: Classification - description: >- Search the free stock image library — available on every plan, including Free name: Stock Images - description: >- Search the free sound effect library — available on every plan, including Free name: Stock Sound Effects - description: >- Search the free background music library — available on every plan, including Free name: Stock Music - description: >- Turn a video into a depth map video to guide other video models with its structure and motion name: Depth Maps paths: /wardrobe: post: tags: - Wardrobe summary: Add an outfit description: > Add clothes to your wardrobe so a character can wear them, from one source: - `image_url`: any picture's own address, one of your BudgetPixel pictures, or a shop's **product page**. A page is read once for the product picture and name it publishes for link previews. Many shops don't allow automatic reading, or show no product picture; then the answer is `422` with `code: link_unreadable`, a `link_problem` (`blocked`, `login`, `not_found`, `no_image`, `not_clothes`, `bad_url`, `failed`) and a message that says what to do instead: use the product picture's own address (right-click it, *Copy image address*), or send the picture itself. - `image_data`: the picture as base64 or a data URL. - `description`: the clothes in words, designed for you (a link inside is read like `image_url`). `mode` (optional): `photo` (someone wears it: the clothes are taken out onto an invisible mannequin), `clean` (the picture shows only the clothes: used as it is) or `text` (from the description). A picture from a link that shows the clothes on their own is used as it is, whatever the mode: there is nobody to take them off. **Price:** a clean picture is free; `photo` and `text` run an image model at its usual price (`model`, default `nano-banana-2.1`), charged on success. Limited to 60 calls per day and 10 a minute per account. **Answer:** `201` with the outfit when it is ready at once (a clean picture), else `202` with its `id` and `status: processing`: the picture usually takes about a minute. `GET /v1/wardrobe/{id}` returns it when `status` is `ready`, with its final handle. operationId: addWardrobeItem requestBody: content: application/json: example: image_url: https://shop.example.com/products/linen-shirt schema: properties: category: enum: - everyday - work - formal - party - sport - swim - outerwear - sleepwear - underwear - costume - traditional - seasonal type: string description: description: The clothes in words. type: string fit: enum: - women - men - unisex type: string handle: type: string image_data: description: The picture as base64 or a data URL. type: string image_url: description: >- A picture's own address, one of your BudgetPixel pictures, or a shop's product page. type: string mode: enum: - photo - clean - text type: string model: enum: - nano-banana-2.1 - seedream-5.0-pro - gpt-image-2.5-sunburst type: string name: type: string note: description: >- With a photo: what to take when it shows more ("only the leather jacket"). type: string type: object required: true responses: '201': content: application/json: schema: $ref: '#/components/schemas/WardrobeItemDetail' description: The outfit, ready. '202': content: application/json: schema: $ref: '#/components/schemas/WardrobeItemDetail' description: The outfit is being made; poll `GET /v1/wardrobe/{id}`. '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '403': $ref: '#/components/responses/Forbidden' '422': content: application/json: schema: properties: error: properties: code: example: link_unreadable type: string link_problem: enum: - blocked - login - not_found - no_image - not_clothes - bad_url - failed type: string message: type: string type: example: invalid_request_error type: string type: object type: object description: >- The link can't be used. `link_problem` says why and the message what to do instead. '429': $ref: '#/components/responses/TooManyRequests' components: schemas: WardrobeItemDetail: allOf: - $ref: '#/components/schemas/WardrobeItem' - properties: error: type: string how_to_use: type: string picture_url: description: >- The full-size picture a mention sends: 896x1200 for an outfit made from a photo or a description, a clean picture at its own size (a signed link that expires after a few hours). format: uri type: string status: description: >- On an outfit you are adding: `processing` while its picture is made (its handle is final once `ready`), or `failed` with `error`. enum: - processing - ready - failed type: string type: object WardrobeItem: description: >- An outfit a character can wear, called by writing its `mention` next to the character in a prompt. properties: category: example: outerwear type: string colors: example: - camel - black items: type: string type: array costume_character: description: >- On a famous character's outfit (anime, game, film), the character. Absent otherwise. It is in the tags too, so `q` finds it. example: Ada Wong type: string costume_franchise: description: >- On a famous character's outfit, where the character is from. Absent otherwise. example: Resident Evil type: string description: description: >- What the outfit is, word for word as it is added to the prompt with the mention. example: >- Camel mid-length wool blend overcoat with waist belt, black turtleneck, black tailored trousers, black leather dress shoes. type: string handle: example: camel_belted_overcoat_outfit type: string id: format: uuid type: string kind: example: outfit type: string mention: description: Write this next to a character in an image or video prompt. example: '@camel_belted_overcoat_outfit' type: string name: example: Camel Belted Overcoat Outfit type: string preview_url: description: >- The picture at most 800 px on its long side, for a preview (a signed link that expires after a few hours). format: uri type: string source: description: >- `mine` = made by you; `saved` = kept from the free library or from another member; `house` = the free library. enum: - mine - saved - house type: string tags: example: - minimalist - autumn - smart items: type: string type: array thumbnail_url: description: >- The picture at most 350 px on its long side, for a list or a grid (a signed link that expires after a few hours). format: uri type: string type: object Error: properties: error: properties: code: description: Stable machine-readable code. example: model_not_available type: string message: type: string type: description: Error category. example: invalid_request_error type: string required: - type - code - message type: object required: - error type: object ModerationBlocked: description: >- Returned (with HTTP 400) when the input content moderation gate blocks a generation request. The block is a property of the request's prompt or input media — reword the prompt or change the input and retry. Branch on `restriction_reason`, which is stable and machine-readable. properties: error: description: Human-readable explanation of the block. type: string restriction_reason: description: Stable machine-readable block reason. enum: - input_csam - input_explicit_adult - input_upload_nudity - input_celebrity_likeness - strict_model_nsfw type: string required: - error - restriction_reason type: object QueueFull: description: | `429` body when your account already has as many jobs of this kind (image, video or audio) in flight as its concurrency cap allows. Submit the next job when one of your running jobs finishes. properties: active_jobs: description: Jobs of this kind in flight right now. type: integer code: enum: - queue_full type: string error: description: Human-readable message. type: string queue_full: enum: - true type: boolean queue_limit: description: Your concurrency cap for this kind of job. type: integer retry_after_seconds: description: Same value as the `Retry-After` header. type: integer required: - error - code - queue_full - queue_limit - active_jobs - retry_after_seconds type: object responses: BadRequest: content: application/json: schema: oneOf: - $ref: '#/components/schemas/Error' - $ref: '#/components/schemas/ModerationBlocked' description: >- The request was malformed, referenced an unavailable model, or was blocked by input content moderation (moderation blocks carry a `restriction_reason` — see ModerationBlocked). Unauthorized: content: application/json: schema: $ref: '#/components/schemas/Error' description: Missing or invalid API key. Forbidden: content: application/json: schema: $ref: '#/components/schemas/Error' description: >- Authenticated but not permitted (plan gate, ownership, account restriction). Content-moderation blocks are 400, not 403. TooManyRequests: content: application/json: schema: oneOf: - $ref: '#/components/schemas/Error' - $ref: '#/components/schemas/QueueFull' description: > A limit was reached. Every `429` carries `Retry-After` (seconds). The per-minute rate limit, the upload limit and the hourly API post cap answer with the `Error` envelope, code `rate_limited`. The monthly spend limit answers with code `monthly_spend_limit_reached`, and its `Retry-After` counts down to the start of next month (raising the limit in the console clears it sooner). A full concurrency queue answers with the flat `QueueFull` body (3D jobs: the `Error` envelope with code `queue_full`); its `Retry-After` is a suggested wait, because a slot frees as soon as one of your running jobs finishes. headers: Retry-After: description: Seconds to wait before retrying. schema: minimum: 1 type: integer securitySchemes: ApiKeyAuth: bearerFormat: bpx_live_* description: 'API key as a bearer token: Authorization: Bearer bpx_live_xxx' scheme: bearer type: http ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.