> ## Documentation Index > Fetch the complete documentation index at: https://platform.minimax.io/docs/llms.txt > Use this file to discover all available pages before exploring further. # Image Edit > Generate new images from 1 to 16 reference images and a text description with MiniMax-H3-Image. Supported models: `MiniMax-H3-Image`, `MiniMax-H3-Image-Highspeed`; both take the same parameters and limits. Image edits always apply prompt enhancement; see `data[].revised_prompt` for the enhanced prompt. > [!WARNING] > > The server waits up to 600 seconds; set the client timeout to at least 600 seconds. This endpoint is not idempotent: once a request is sent, the server finishes generation and charges for successful images even if the client times out or disconnects, and a retry generates and charges again. With the OpenAI SDK, set `max_retries=0` to turn off its default automatic retries. ## OpenAPI ````yaml api-reference/image/generation/api/h3-image-edits.json POST /v1/images/edits openapi: 3.1.0 info: title: MiniMax H3-Image Edits API description: MiniMax H3-Image API license: name: MIT version: 1.0.0 servers: - url: https://api.minimax.io security: - bearerAuth: [] paths: /v1/images/edits: post: tags: - Image summary: Image Edit description: >- Generate images from 1 to 16 reference images and a text description. Synchronous, with optional streaming. Supported models: `MiniMax-H3-Image`, `MiniMax-H3-Image-Highspeed`; both take the same parameters and limits. Image edits always apply prompt enhancement; see `data[].revised_prompt` for the enhanced prompt. The server waits up to 600 seconds; set the client timeout to at least 600 seconds. This endpoint is not idempotent: once a request is sent, the server finishes generation and charges for successful images even if the client times out or disconnects, and a retry generates and charges again. operationId: h3ImageEdits requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/H3ImageEditReq' multipart/form-data: schema: $ref: '#/components/schemas/H3ImageEditMultipartReq' description: >- Two formats are supported: `application/json`, or `multipart/form-data` compatible with the OpenAI SDK `images.edit`. responses: '200': description: >- Returns `application/json` when `stream` is `false` (default). When `stream` is `true`, returns `text/event-stream` (SSE); the `data` of each event is JSON, defined under the `text/event-stream` response. See [Streaming Events](/api-reference/image-generation-h3-streaming) for event details and a full example. content: application/json: schema: $ref: '#/components/schemas/ImagesResponse' text/event-stream: schema: $ref: '#/components/schemas/ImageStreamEvent' examples: Single image succeeded: summary: Single image succeeded value: type: image_edit.partial_succeeded created: 1792308690 model: MiniMax-H3-Image image_index: 1 url: https://example.com/h3-image/output-1.jpg size: 5440x3072 output_format: jpeg revised_prompt: >- Replace the orange cat in image 1 with the Shiba Inu from image 2, sitting on the windowsill looking out, keeping the original lighting and background Single image failed: summary: Single image failed value: type: image_edit.partial_failed created: 1792308691 model: MiniMax-H3-Image image_index: 2 code: '1027' message: output image failed content safety check All done: summary: All done value: type: image_edit.completed created: 1792308695 model: MiniMax-H3-Image usage: generated_images: 2 total_tokens: 80450 input_tokens: 47810 output_tokens: 32640 input_tokens_details: text_tokens: 24186 image_tokens: 23624 output_tokens_details: image_tokens: 32640 request_id: 021792308678142a2c883cf675b9804d Request failed: summary: Request failed value: type: error error: type: server_error message: internal error (1000) http_code: '500' usage: generated_images: 0 total_tokens: 0 input_tokens: 0 output_tokens: 0 input_tokens_details: text_tokens: 0 image_tokens: 0 output_tokens_details: image_tokens: 0 request_id: 021792308678142a2c883cf675b9804d '400': $ref: '#/components/responses/Err400' '401': $ref: '#/components/responses/Err401' '402': $ref: '#/components/responses/Err402' description: >- Insufficient balance or plan quota. The error code is in the parentheses at the end of `error.message`: - `1008`: insufficient balance - `2053`: insufficient credit - `2067`: usage limit reached and credit auto consumption is off - `2068`: the current plan tier does not support this model '422': $ref: '#/components/responses/Err422' '429': $ref: '#/components/responses/Err429' description: >- Rate limited. The error code is in the parentheses at the end of `error.message`: - `1002`: the images-per-minute (IPM) limit is exceeded; each request counts as `n` images - `2056`: the M Plan usage limit is reached '500': $ref: '#/components/responses/Err500' x-codeSamples: - lang: cURL label: cURL (JSON) source: |- curl --request POST \ --url https://api.minimax.io/v1/images/edits \ --header 'Authorization: Bearer ' \ --header 'Content-Type: application/json' \ --data '{ "model": "MiniMax-H3-Image", "prompt": "Replace the cat in image 1 with the Shiba Inu in image 2, keep the background unchanged", "images": [ {"image_url": "https://example.com/cat.jpg"}, {"image_url": "https://example.com/dog.png"} ], "size": "auto", "response_format": "url" }' - lang: cURL label: cURL (multipart) source: |- curl --request POST \ --url https://api.minimax.io/v1/images/edits \ --header 'Authorization: Bearer ' \ --form model=MiniMax-H3-Image \ --form 'prompt=Replace the cat in image 1 with the Shiba Inu in image 2, keep the background unchanged' \ --form 'image[]=@cat.jpg' \ --form 'image[]=@dog.png' \ --form size=auto \ --form response_format=url - lang: Python label: Python (requests) source: >- import os import requests url = "https://api.minimax.io/v1/images/edits" headers = {"Authorization": f"Bearer {os.environ.get('MINIMAX_API_KEY')}"} payload = { "model": "MiniMax-H3-Image", "prompt": "Replace the cat in image 1 with the Shiba Inu in image 2, keep the background unchanged", "images": [ {"image_url": "https://example.com/cat.jpg"}, {"image_url": "https://example.com/dog.png"}, ], "size": "auto", "response_format": "url", } response = requests.post(url, headers=headers, json=payload, timeout=600) print(response.json()) - lang: Python label: Python (OpenAI SDK) source: |- import os from openai import OpenAI client = OpenAI( base_url="https://api.minimax.io/v1", api_key=os.environ.get("MINIMAX_API_KEY"), ) # Upload reference images as files; list order is the Picture number result = client.images.edit( model="MiniMax-H3-Image", image=[open("cat.jpg", "rb"), open("dog.png", "rb")], prompt="Replace the cat in image 1 with the Shiba Inu in image 2, keep the background unchanged", size="auto", response_format="url", ) for i, item in enumerate(result.data): print(i, item.url) # url is None for images that failed components: schemas: H3ImageEditReq: type: object required: - model - prompt - images properties: model: type: string description: >- Model name. Supported values: `MiniMax-H3-Image`, `MiniMax-H3-Image-Highspeed`; both take the same parameters and limits enum: - MiniMax-H3-Image - MiniMax-H3-Image-Highspeed prompt: type: string maxLength: 32000 description: >- Text description of the edit, up to 32000 characters (counted as Unicode characters, excluding leading and trailing whitespace); an empty or whitespace-only prompt returns 400. images: type: array minItems: 1 maxItems: 16 description: >- Reference images, 1 to 16. **Reference image limits** (total request body ≤ 64 MiB; Base64-encoded data is about 4/3 of the original file size; if the request body would exceed the limit, use public URLs or `mm_file://`) | Item | Limit | | :--- | :--- | | Format | JPG, JPEG, PNG, WEBP, HEIC, HEIF | | Single file size | ≤ 64 MiB | | Width/height range | [128, 8192] px | | Aspect ratio (long/short side) | ≤ 4:1 | | Count | 1 to 16 | items: $ref: '#/components/schemas/ImageInput' 'n': type: integer default: 1 minimum: 1 maximum: 10 description: Number of images, range [1, 10], default 1. size: type: string default: auto description: >- Output image size, default `auto`; see [Output Size](/guides/image-generation#output-size). Use one of two forms: - `WIDTHxHEIGHT`: set the width and height directly, e.g. `2720x1536`; both are positive integers. The area (width × height) must be between 655,360 and 20,000,000 pixels and the aspect ratio between 1:3 and 3:1, bounds inclusive; otherwise 400 is returned, and the size is never scaled or rounded. In this form, do not set `aspect_ratio` or `area` (not even to `auto`); otherwise 400 is returned - `auto` or omitted: width and height are determined by `aspect_ratio` (default `auto`) and `area` (default `4K`); either can be set on its own aspect_ratio: type: string default: auto example: '16:9' description: >- Output aspect ratio, default `auto`. Can only be set when `size` is omitted or `auto`; setting it while `size` is `WIDTHxHEIGHT` returns 400. - `auto`: decided by prompt enhancement based on the reference images and content - `X:Y`: X and Y are integers from 1 to 300 and the ratio is between 1:3 and 3:1 (bounds inclusive), e.g. `16:9`, `3:4`, `21:9`, `3:1` area: type: string enum: - 1K - 2K - 4K default: 4K description: >- Output area level, default `4K`. Can only be set when `size` is omitted or `auto`; setting it while `size` is `WIDTHxHEIGHT` returns 400. `1K`, `2K` and `4K` target areas of 1024 × 1024, 2048 × 2048 and 4096 × 4096 pixels. The server calculates width and height from the aspect ratio; for example, `2K` with `16:9` outputs 2720 × 1536. See `data[].size` for each image's actual width and height. output_format: type: string enum: - png - jpeg - jpg - webp default: jpeg description: >- Output image format, default `jpeg`. Available values: `png`, `jpeg`, `jpg`, `webp`. `jpg` is equivalent to `jpeg`; `output_format` in the response is returned as `jpeg`. response_format: type: string enum: - url - b64_json default: url description: >- Return format, default `url`. - `url`: image URL. Download the image and store it yourself; the URL is not guaranteed to remain available - `b64_json`: Base64-encoded image data, not supported with streaming Total output area (`n` × width × height) limits for `b64_json`; exceeding returns 400 (with `size` = `auto`, each image counts as its `area` level, e.g. 4096 × 4096 for `4K`): | `output_format` | Total area limit | Example | | :--- | :--- | :--- | | `png` | 20,000,000 px | 1 image of any size | | `jpeg` / `webp` | 80,000,000 px | Up to 4 images at `4K`, or 10 at `2K` | stream: type: boolean default: false description: >- Whether to stream results, default `false`. When enabled, the response is `text/event-stream` (SSE), and only `response_format` = `url` is supported: - One event is pushed as each image finishes: `image_edit.partial_succeeded` on success, `image_edit.partial_failed` on failure. Events are pushed in completion order; use `image_index` to match images - `image_edit.completed` is pushed after all images finish, with `usage` and `request_id` - After the response headers are sent, an `error` event is pushed if all images fail or the request fails before generation is submitted - Errors before the response headers are sent (invalid parameters, authentication, rate limiting, insufficient balance, etc.) are returned as regular HTTP errors, the same as non-streaming calls; check the HTTP status code before parsing SSE See [Streaming Events](/api-reference/image-generation-h3-streaming) for event structures. output_compression: type: integer minimum: 0 maximum: 100 default: 95 description: >- Compression quality, range [0, 100], default 95; higher values give better quality and larger files. Only applies to `jpeg` / `webp` and is ignored for `png`; values outside the range return 400. example: model: MiniMax-H3-Image prompt: >- Replace the cat in image 1 with the Shiba Inu in image 2, keep the background unchanged images: - image_url: https://example.com/cat.jpg - image_url: https://example.com/dog.png size: auto response_format: url H3ImageEditMultipartReq: type: object description: >- The `multipart/form-data` format, compatible with the OpenAI SDK `images.edit`: upload reference images as files and pass the other parameters as form fields, with the same values as the `application/json` format. required: - model - prompt - image properties: model: type: string description: >- Model name. Supported values: `MiniMax-H3-Image`, `MiniMax-H3-Image-Highspeed`; both take the same parameters and limits enum: - MiniMax-H3-Image - MiniMax-H3-Image-Highspeed prompt: type: string maxLength: 32000 description: >- Text description of the edit, up to 32000 characters (counted as Unicode characters, excluding leading and trailing whitespace); an empty or whitespace-only prompt returns 400. image: type: array minItems: 1 maxItems: 16 description: >- Reference image files, 1 to 16; upload order is the Picture number. Use the field name `image` or `image[]`, one field per file (the OpenAI SDK uses `image[]` for multiple images). Format, single file size, width/height, and aspect ratio limits are the same as `images` in the `application/json` format; total request body ≤ 64 MiB. `mask` is not supported and returns 400. items: type: string format: binary 'n': type: integer default: 1 minimum: 1 maximum: 10 description: Number of images, range [1, 10], default 1. size: type: string default: auto description: >- Output image size, default `auto`; see [Output Size](/guides/image-generation#output-size). Use one of two forms: - `WIDTHxHEIGHT`: set the width and height directly, e.g. `2720x1536`; both are positive integers. The area (width × height) must be between 655,360 and 20,000,000 pixels and the aspect ratio between 1:3 and 3:1, bounds inclusive; otherwise 400 is returned, and the size is never scaled or rounded. In this form, do not set `aspect_ratio` or `area` (not even to `auto`); otherwise 400 is returned - `auto` or omitted: width and height are determined by `aspect_ratio` (default `auto`) and `area` (default `4K`); either can be set on its own aspect_ratio: type: string default: auto example: '16:9' description: >- Output aspect ratio, default `auto`. Can only be set when `size` is omitted or `auto`; setting it while `size` is `WIDTHxHEIGHT` returns 400. - `auto`: decided by prompt enhancement based on the reference images and content - `X:Y`: X and Y are integers from 1 to 300 and the ratio is between 1:3 and 3:1 (bounds inclusive), e.g. `16:9`, `3:4`, `21:9`, `3:1` area: type: string enum: - 1K - 2K - 4K default: 4K description: >- Output area level, default `4K`. Can only be set when `size` is omitted or `auto`; setting it while `size` is `WIDTHxHEIGHT` returns 400. `1K`, `2K` and `4K` target areas of 1024 × 1024, 2048 × 2048 and 4096 × 4096 pixels. The server calculates width and height from the aspect ratio; for example, `2K` with `16:9` outputs 2720 × 1536. See `data[].size` for each image's actual width and height. output_format: type: string enum: - png - jpeg - jpg - webp default: jpeg description: >- Output image format, default `jpeg`. Available values: `png`, `jpeg`, `jpg`, `webp`. `jpg` is equivalent to `jpeg`; `output_format` in the response is returned as `jpeg`. response_format: type: string enum: - url - b64_json default: url description: >- Return format, default `url`. - `url`: image URL. Download the image and store it yourself; the URL is not guaranteed to remain available - `b64_json`: Base64-encoded image data, not supported with streaming Total output area (`n` × width × height) limits for `b64_json`; exceeding returns 400 (with `size` = `auto`, each image counts as its `area` level, e.g. 4096 × 4096 for `4K`): | `output_format` | Total area limit | Example | | :--- | :--- | :--- | | `png` | 20,000,000 px | 1 image of any size | | `jpeg` / `webp` | 80,000,000 px | Up to 4 images at `4K`, or 10 at `2K` | stream: type: boolean default: false description: >- Whether to stream results, default `false`. When enabled, the response is `text/event-stream` (SSE), and only `response_format` = `url` is supported: - One event is pushed as each image finishes: `image_edit.partial_succeeded` on success, `image_edit.partial_failed` on failure. Events are pushed in completion order; use `image_index` to match images - `image_edit.completed` is pushed after all images finish, with `usage` and `request_id` - After the response headers are sent, an `error` event is pushed if all images fail or the request fails before generation is submitted - Errors before the response headers are sent (invalid parameters, authentication, rate limiting, insufficient balance, etc.) are returned as regular HTTP errors, the same as non-streaming calls; check the HTTP status code before parsing SSE See [Streaming Events](/api-reference/image-generation-h3-streaming) for event structures. output_compression: type: integer minimum: 0 maximum: 100 default: 95 description: >- Compression quality, range [0, 100], default 95; higher values give better quality and larger files. Only applies to `jpeg` / `webp` and is ignored for `png`; values outside the range return 400. ImagesResponse: type: object properties: created: type: integer description: Time the response was generated, as a Unix timestamp in seconds. data: type: array description: >- Images, always `n` items in image order (matching `image_index` in streaming events). Successful items contain `url` (or `b64_json`), `size` and `revised_prompt`; failed items, including those withheld by the content safety check, contain only `error`. If at least one image succeeds, the HTTP status is 200, so check `data[].error` for every item; if all images fail, a 402, 422 or 500 error response is returned. Only successful images are charged. items: $ref: '#/components/schemas/ImageObject' output_format: type: string enum: - png - jpeg - webp description: Format of the generated images. usage: $ref: '#/components/schemas/ImageUsage' request_id: type: string description: Request ID (the trace ID). Provide it when reporting an issue. example: created: 1792308678 data: - url: https://example.com/h3-image/output-0.jpg size: 5440x3072 revised_prompt: >- Replace the orange cat lying on the windowsill in image 1 with the Shiba Inu from image 2, keeping the dog's coat color and facial features, lying down, with the windowsill, lighting and background unchanged output_format: jpeg usage: generated_images: 1 total_tokens: 40225 input_tokens: 23905 output_tokens: 16320 input_tokens_details: text_tokens: 12093 image_tokens: 11812 output_tokens_details: image_tokens: 16320 request_id: 021792308678142a2c883cf675b9804d ImageStreamEvent: description: >- JSON in the `data` field of each SSE event: one of the four events below, distinguished by `type`. Each event consists of an `event:` line and a `data:` line, and events are separated by a blank line. While waiting, a comment line `: keepalive` is sent every 15 seconds and can be ignored. oneOf: - $ref: '#/components/schemas/ImageStreamPartialSucceeded' - $ref: '#/components/schemas/ImageStreamPartialFailed' - $ref: '#/components/schemas/ImageStreamCompleted' - $ref: '#/components/schemas/ImageStreamError' ImageInput: type: object description: A single reference image. required: - image_url properties: image_url: type: string description: >- Image location. Supported: a public URL; `mm_file://{file_id}` (reference an uploaded file, obtained by calling [File Upload](/api-reference/file-management-upload) with `purpose` set to `image_generation_input`); a `data:image/;base64,` data URI (`` lowercase). ImageObject: type: object properties: url: type: string description: Image URL, returned when `response_format` is `url`. b64_json: type: string description: >- Base64-encoded image data. Returned when `response_format` is `b64_json`. size: type: string description: Actual image size, formatted as `WIDTHxHEIGHT`. revised_prompt: type: string description: >- The prompt actually used to generate this image, i.e. the enhanced prompt. error: type: object description: Error for this image, returned only when it fails. properties: code: type: string description: >- Error code for this image. Common values: `1000` generation failed, `1001` timed out, `1008` insufficient balance, `1026` enhanced prompt failed the content safety check, `1027` generated image failed the content safety check. See [Error Codes](/api-reference/errorcode) for the full list. message: type: string description: Error detail. ImageUsage: type: object description: >- Token usage of this request, counting successful images only; billing is based on it. `total_tokens` is the sum of `input_tokens` and `output_tokens`. properties: generated_images: type: integer description: Number of images generated successfully; may be less than `n`. total_tokens: type: integer description: Total tokens. input_tokens: type: integer description: Input tokens (text and reference images). output_tokens: type: integer description: Output tokens (generated images). input_tokens_details: type: object properties: text_tokens: type: integer description: >- Input text tokens, including tokens converted from the prompt enhancement cost. image_tokens: type: integer description: Input reference image tokens; 0 for text-to-image. output_tokens_details: type: object properties: image_tokens: type: integer description: Tokens of the output images. ImageStreamPartialSucceeded: type: object title: partial_succeeded description: >- A single image was generated successfully. Pushed once for each successful image, in completion order; use `image_index` to identify the image. required: - type - image_index - url properties: type: type: string enum: - image_edit.partial_succeeded description: Event type, always `image_edit.partial_succeeded`. created: type: integer description: Unix timestamp (seconds) when the event was produced. model: type: string description: Model name. image_index: type: integer description: >- Image index, starting from 0, range [0, n-1]; matches the position in `data` of the non-streaming response. url: type: string description: Image URL. Download the image and store it yourself. size: type: string description: Actual image size, formatted as `WIDTHxHEIGHT`. output_format: type: string enum: - png - jpeg - webp description: 'Image format: `png`, `jpeg`, or `webp`.' revised_prompt: type: string description: >- The prompt actually used to generate this image, i.e. the enhanced prompt. ImageStreamPartialFailed: type: object title: partial_failed description: >- A single image failed to generate or failed the content safety check. Other images are not affected and continue to be pushed. required: - type - image_index - code - message properties: type: type: string enum: - image_edit.partial_failed description: Event type, always `image_edit.partial_failed`. created: type: integer description: Unix timestamp (seconds) when the event was produced. model: type: string description: Model name. image_index: type: integer description: >- Image index, starting from 0, range [0, n-1]; matches the position in `data` of the non-streaming response. code: type: string description: >- Error code for this image. Common values: `1000` generation failed, `1001` timed out, `1008` insufficient balance, `1026` enhanced prompt failed the content safety check, `1027` generated image failed the content safety check. See [Error Codes](/api-reference/errorcode) for the full list. message: type: string description: Error details. ImageStreamCompleted: type: object title: completed description: >- Pushed when all images are done and at least one succeeded. This is the last event in the stream. required: - type properties: type: type: string enum: - image_edit.completed description: Event type, always `image_edit.completed`. created: type: integer description: Unix timestamp (seconds) when the event was produced. model: type: string description: Model name. usage: $ref: '#/components/schemas/ImageUsage' request_id: type: string description: Request ID (the trace ID). Provide it when reporting an issue. ImageStreamError: type: object title: error description: >- Pushed when no image was generated, or when the request fails as a whole after the response headers were sent but before generation was submitted. The stream ends after this event. Not billed.Does not include `created` or `data`; the failure reason of each image is in the `partial_failed` events pushed before it. required: - type - error properties: type: type: string enum: - error description: Always `error`. error: $ref: '#/components/schemas/OaiErrorDetail' description: >- Error details, the same as the `error` field of the HTTP error response of a non-streaming request. When all images fail, `http_code` is `422` (all failed the content safety check), `402` (all failed due to insufficient balance), or `500` (otherwise). usage: $ref: '#/components/schemas/ImageUsage' description: All values are 0. request_id: type: string description: Request ID (the trace ID). Provide it when reporting an issue. OaiError: type: object description: >- Error response. The HTTP status code is the error code. If all images fail, `created`, `data` (per-image failure reasons), and `usage` are also returned: 422 if all failed the content safety check, 402 if all failed due to insufficient balance, otherwise 500. properties: type: type: string description: Always `error`. example: error error: $ref: '#/components/schemas/OaiErrorDetail' created: type: integer description: Unix timestamp (seconds). Returned only when all images fail. data: type: array description: Per-image failure reasons. Returned only when all images fail. items: $ref: '#/components/schemas/ImageObject' usage: $ref: '#/components/schemas/ImageUsage' description: Returned only when all images fail. request_id: type: string description: Request ID (the trace ID). Provide it when reporting an issue. OaiErrorDetail: type: object properties: type: type: string description: >- Error type: `bad_request_error` (400) / `authorized_error` (401) / `insufficient_balance_error` (402) / `unprocessable_entity_error` (422) / `rate_limit_error` (429) / `server_error` (500), etc. message: type: string description: >- Error detail; the trailing parenthesis holds the internal error code (e.g. `... (2013)`). See [Error Codes](/api-reference/errorcode). http_code: type: string description: HTTP status code as a string, e.g. `400`. responses: Err400: description: Invalid parameters content: application/json: schema: $ref: '#/components/schemas/OaiError' examples: invalid_size: summary: Invalid parameters value: type: error error: type: bad_request_error message: invalid params, images must contain at most 16 items (2013) http_code: '400' request_id: 021792308678142a2c883cf675b9804d b64_json: summary: b64_json constraint not met value: type: error error: type: bad_request_error message: >- invalid params, b64_json total output area (n x width x height) 33554432 exceeds 20000000 for png, use url or jpeg/webp instead (2013) http_code: '400' request_id: 021792308678142a2c883cf675b9804d Err401: description: Authentication failed content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: authorized_error message: >- login fail: Please carry the API secret key in the 'Authorization' field of the request header (1004) http_code: '401' request_id: 021792308678142a2c883cf675b9804d Err402: description: Insufficient balance content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: insufficient_balance_error message: insufficient balance (1008) http_code: '402' request_id: 021792308678142a2c883cf675b9804d Err422: description: >- Input contains sensitive content / All images withheld by the content safety check content: application/json: schema: $ref: '#/components/schemas/OaiError' examples: input_sensitive: summary: Input contains sensitive content value: type: error error: type: unprocessable_entity_error message: 'input content failed safety check: prompt (1026)' http_code: '422' request_id: 021792308678142a2c883cf675b9804d all_images_failed: summary: All images withheld by the content safety check value: type: error error: type: unprocessable_entity_error message: >- no image generated: all 2 images failed content safety check (1027) http_code: '422' created: 1792308678 data: - error: code: '1027' message: output image failed content safety check - error: code: '1027' message: output image failed content safety check usage: generated_images: 0 total_tokens: 0 input_tokens: 0 output_tokens: 0 input_tokens_details: text_tokens: 0 image_tokens: 0 output_tokens_details: image_tokens: 0 request_id: 021792308678142a2c883cf675b9804d Err429: description: Rate limited content: application/json: schema: $ref: '#/components/schemas/OaiError' example: type: error error: type: rate_limit_error message: rate limit exceeded(IPM) (1002) http_code: '429' request_id: 021792308678142a2c883cf675b9804d Err500: description: Server error content: application/json: schema: $ref: '#/components/schemas/OaiError' examples: server_error: summary: Server error value: type: error error: type: server_error message: internal error (1000) http_code: '500' request_id: 021792308678142a2c883cf675b9804d all_images_failed: summary: No image generated (server error involved) value: type: error error: type: server_error message: 'no image generated: 1 x 1027, 1 x 1000 (1000)' http_code: '500' created: 1792308678 data: - error: code: '1027' message: output image failed content safety check - error: code: '1000' message: image generation failed usage: generated_images: 0 total_tokens: 0 input_tokens: 0 output_tokens: 0 input_tokens_details: text_tokens: 0 image_tokens: 0 output_tokens_details: image_tokens: 0 request_id: 021792308678142a2c883cf675b9804d securitySchemes: bearerAuth: type: http scheme: bearer description: >- `HTTP: Bearer Auth` - Security Scheme Type: http - HTTP Authorization Scheme: `Bearer API_key`, used to verify account information, can be found in [Account Management>API Keys](https://platform.minimax.io/user-center/basic-information/interface-key). ````