Submit an image generation task
Hub（优质 AI 网关）
提交图像任务
Generates images using the selected model.
Text-to-image models: nano-banana, nano-banana-2, nano-banana-pro, gpt-image-2
Image-to-image edit models: nano-banana-edit, nano-banana-2-edit, nano-banana-pro-edit, gpt-image-2-edit
Workflow
GET /hub/v1/models?capability=image— browse available modelsGET /hub/v1/models/:model— copy theexampleas yourinputPOST /hub/v1/image← you are hereGET /hub/v1/tasks/:task_id— poll untilready=true
Model Reference
Tip: Click Try it out → select a model from the dropdown below → the parameter schema auto-populates with an example.
nano-banana — Nano Banana (Google) · text-to-image
Gemini 2.5 Flash Image: fast and affordable text-to-image generation.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
seed | integer | – | – | The seed for the random number generator. | |
prompt | string | ✓ | – | – | The text prompt to generate an image from. |
sync_mode | boolean | – | – | If True, the media will be returned as a data URI and the output data won’t be available in the request history. | |
num_images | integer | 1 | – | The number of images to generate. | |
aspect_ratio | string | 1:1 | 21:9 16:9 3:2 4:3 5:4 1:1 4:5 3:4 2:3 9:16 | The aspect ratio of the generated image. | |
output_format | string | png | jpeg png webp | The format of the generated image. | |
safety_tolerance | string | 4 | 1 2 3 4 5 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. | |
limit_generations | boolean | – | – | Experimental parameter to limit the number of generations from each round of prompting to 1. Set to True to disregard any instructions in the prompt regarding the number of images to generate. |
Example request body
{
"model": "nano-banana",
"input": {
"prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half, revealing both the dogs head above water holding a tennis ball in it's mouth, and it's paws paddling underwater.",
"num_images": 1,
"aspect_ratio": "1:1",
"output_format": "png",
"safety_tolerance": "4"
}
}
nano-banana-edit — Nano Banana Image Edit (Google) · image-to-image
Gemini 2.5 Flash Image: image editing with instruction-following.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
seed | integer | – | – | The seed for the random number generator. | |
prompt | string | ✓ | – | – | The text prompt to generate an image from. |
image_urls | array | ✓ | – | – | The URLs of the images to use as a reference for the generation. |
num_images | integer | 1 | – | The number of images to generate. | |
aspect_ratio | string | 1:1 | 21:9 16:9 3:2 4:3 5:4 1:1 4:5 3:4 2:3 9:16 | The aspect ratio of the generated image. | |
output_format | string | png | jpeg png webp | The format of the generated image. | |
safety_tolerance | string | 4 | 1 2 3 4 5 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
{
"model": "nano-banana-edit",
"input": {
"prompt": "Make the character drive along the California coastline",
"image_urls": [
"https://example.com/sample-image.jpg"
],
"num_images": 1
}
}
nano-banana-2 — Nano Banana 2 (Google) · text-to-image
Nano Banana 2 (Gemini 3.1 Flash Image) ??fast text-to-image with resolution tiers.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
seed | integer | – | – | The seed for the random number generator. | |
prompt | string | ✓ | – | – | The text prompt to generate an image from. |
sync_mode | boolean | – | – | If True, the media will be returned as a data URI and the output data won’t be available in the request history. | |
num_images | integer | 1 | – | The number of images to generate. | |
resolution | string | 1K | 0.5K 1K 2K 4K | The resolution of the image to generate. | |
aspect_ratio | string | auto | auto 21:9 16:9 3:2 4:3 5:4 1:1 4:5 3:4 2:3 9:16 4:1 1:4 8:1 1:8 | The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. Use ‘auto’ to let the model decide based on the prompt. | |
output_format | string | png | jpeg png webp | The format of the generated image. | |
system_prompt | string | “ | – | Optional system instruction that steers the model’s persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers). | |
thinking_level | string | – | minimal high | When set, enables model thinking with the given level (‘minimal’ or ‘high’) and includes thoughts in the generation. Omit to disable. | |
safety_tolerance | string | 4 | 1 2 3 4 5 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. | |
enable_web_search | boolean | – | – | Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image. | |
limit_generations | boolean | true | – | Experimental parameter to limit the number of generations from each round of prompting to 1. Set to True to disregard any instructions in the prompt regarding the number of images to generate and ignore any intermediate images generated by the model. This may affect generation quality. |
Example request body
{
"model": "nano-banana-2",
"input": {
"prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half, revealing both the dogs head above water holding a tennis ball in it's mouth, and it's paws paddling underwater.",
"num_images": 1,
"resolution": "1K",
"aspect_ratio": "auto",
"output_format": "png",
"safety_tolerance": "4",
"limit_generations": true
}
}
nano-banana-2-edit — Nano Banana 2 Image Edit (Google) · image-to-image
Nano Banana 2 image editing with resolution tiers.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
seed | integer | – | – | The seed for the random number generator. | |
prompt | string | ✓ | – | – | The text prompt to generate an image from. |
image_urls | array | ✓ | – | – | The URLs of the images to use as a reference for the generation. |
num_images | integer | 1 | – | The number of images to generate. | |
resolution | string | 1K | 0.5K 1K 2K 4K | The resolution of the image to generate. | |
aspect_ratio | string | auto | auto 21:9 16:9 3:2 4:3 5:4 1:1 4:5 3:4 2:3 9:16 4:1 1:4 8:1 1:8 | The aspect ratio of the generated image. Supports extreme ratios: 4:1, 1:4, 8:1, 1:8. Use ‘auto’ to let the model decide based on the prompt. | |
output_format | string | png | jpeg png webp | The format of the generated image. | |
safety_tolerance | string | 4 | 1 2 3 4 5 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
{
"model": "nano-banana-2-edit",
"input": {
"prompt": "Add falling snow and a warm golden glow to the scene",
"image_urls": [
"https://example.com/sample-image.jpg"
],
"resolution": "1K"
}
}
nano-banana-pro — Nano Banana Pro (Google) · text-to-image
Nano Banana Pro (Gemini 3 Pro Image) ??studio-quality text-to-image generation.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
seed | integer | – | – | The seed for the random number generator. | |
prompt | string | ✓ | – | – | The text prompt to generate an image from. |
sync_mode | boolean | – | – | If True, the media will be returned as a data URI and the output data won’t be available in the request history. | |
num_images | integer | 1 | – | The number of images to generate. | |
resolution | string | 1K | 1K 2K 4K | The resolution of the image to generate. | |
aspect_ratio | string | 1:1 | auto 21:9 16:9 3:2 4:3 5:4 1:1 4:5 3:4 2:3 9:16 | The aspect ratio of the generated image. | |
output_format | string | png | jpeg png webp | The format of the generated image. | |
system_prompt | string | “ | – | Optional system instruction that steers the model’s persona and output style across the request. Leave blank to omit; when provided, it is sent as the system instruction to Gemini (or as a system message on OpenAI-compatible providers). | |
safety_tolerance | string | 4 | 1 2 3 4 5 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. | |
enable_web_search | boolean | – | – | Enable web search for the image generation task. This will allow the model to use the latest information from the web to generate the image. Note: disabled on this platform. | |
limit_generations | boolean | – | – | Experimental parameter to limit the number of generations from each round of prompting to 1. Set to True to disregard any instructions in the prompt regarding the number of images to generate. |
Example request body
{
"model": "nano-banana-pro",
"input": {
"prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half, revealing both the dogs head above water holding a tennis ball in it's mouth, and it's paws paddling underwater.",
"num_images": 1,
"resolution": "1K",
"aspect_ratio": "1:1",
"output_format": "png",
"safety_tolerance": "4"
}
}
nano-banana-pro-edit — Nano Banana Pro Image Edit (Google) · image-to-image
Nano Banana Pro studio-quality image editing.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
seed | integer | – | – | The seed for the random number generator. | |
prompt | string | ✓ | – | – | The text prompt to generate an image from. |
image_urls | array | ✓ | – | – | The URLs of the images to use as a reference for the generation. |
num_images | integer | 1 | – | The number of images to generate. | |
resolution | string | 1K | 1K 2K 4K | The resolution of the image to generate. | |
aspect_ratio | string | 1:1 | auto 21:9 16:9 3:2 4:3 5:4 1:1 4:5 3:4 2:3 9:16 | The aspect ratio of the generated image. | |
output_format | string | png | jpeg png webp | The format of the generated image. | |
safety_tolerance | string | 4 | 1 2 3 4 5 6 | The safety tolerance level for content moderation. 1 is the most strict (blocks most content), 6 is the least strict. Note: API-only parameter. |
Example request body
{
"model": "nano-banana-pro-edit",
"input": {
"prompt": "Remove the background and replace with a dramatic sunset beach scene",
"image_urls": [
"https://example.com/sample-image.jpg"
],
"resolution": "1K"
}
}
gpt-image-2 — GPT Image 2 (OpenAI) · text-to-image
GPT Image 2, OpenAI’s latest image model, is capable of creating extremely detailed images with fine typography.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
prompt | string | ✓ | – | – | The prompt for image generation |
quality | string | high | auto low medium high | Quality for the generated image. Use ‘auto’ to let the model pick the best quality for the prompt. | |
sync_mode | boolean | – | – | If True, the media will be returned as a data URI and the output data won’t be available in the request history. | |
image_size | oneOf | landscape_4_3 | Preset / Custom | The size of the generated image. Use a preset name or a custom object. Concrete sizes: both dimensions must be multiples of 16, max edge 3840px, aspect ratio ??3:1, total pixels 655,360??,294,400. | |
num_images | integer | 1 | – | Number of images to generate | |
output_format | string | png | jpeg png webp | Output format for the images |
Example request body
{
"model": "gpt-image-2",
"input": {
"prompt": "create a realistic image taken with iphone at these coordinates 41°43′32″N 49°56′49″W 15 April 1912",
"quality": "high",
"image_size": "landscape_4_3",
"num_images": 1,
"output_format": "png"
}
}
gpt-image-2-edit — GPT Image 2 Edit (OpenAI) · image-to-image
GPT Image 2 instruction-following image editing with reasoning.
| Parameter | Type | Req | Default | Values / Range | Description |
|---|---|---|---|---|---|
prompt | string | ✓ | – | – | The prompt for image generation |
quality | string | high | auto low medium high | Quality for the generated image. Use ‘auto’ to let the model pick the best quality for the prompt. | |
mask_url | string | – | – | The URL of the mask image to use for the generation. This indicates what part of the image to edit. | |
sync_mode | boolean | – | – | If True, the media will be returned as a data URI and the output data won’t be available in the request history. | |
image_size | oneOf | auto | Preset / Custom | The size of the generated image. Use ‘auto’ to infer from input images, a preset name, or a custom object. | |
image_urls | array | ✓ | – | – | The URLs of the images to use as a reference for the generation. |
num_images | integer | 1 | – | Number of images to generate | |
output_format | string | png | jpeg png webp | Output format for the images |
Example request body
{
"model": "gpt-image-2-edit",
"input": {
"prompt": "Add a dramatic rainbow arching across the sky",
"quality": "high",
"image_size": "auto",
"image_urls": [
"https://example.com/sample-image.jpg"
]
}
}
POST
Submit an image generation task
Documentation Index
Fetch the complete documentation index at: https://docs.mountsea.ai/llms.txt
Use this file to discover all available pages before exploring further.
授权
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
请求体
application/json
- Nano Banana (Google) [text-to-image]
- Nano Banana Image Edit (Google) [image-to-image]
- Nano Banana 2 (Google) [text-to-image]
- Nano Banana 2 Image Edit (Google) [image-to-image]
- Nano Banana Pro (Google) [text-to-image]
- Nano Banana Pro Image Edit (Google) [image-to-image]
- GPT Image 2 (OpenAI) [text-to-image]
- GPT Image 2 Edit (OpenAI) [image-to-image]
响应
200 - application/json
Unique task ID — use this to poll GET /hub/v1/tasks/:task_id
示例:
"hub-xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx"
Task status at creation time (usually pending)
示例:
"pending"
Capability: image | video | audio | transcribe
示例:
"video"
Model ID
示例:
"veo-3.1-fast"
Model vendor
示例:
"Google"
Generation mode (e.g. text-to-video, image-to-image)
示例:
"text-to-video"
ISO 8601 creation timestamp
示例:
"2026-05-18T09:00:00.000Z"