模型市场支持← 返回应用

Google

Google 模型通过一个统一的异步任务 API 调用。用 POST /api/generate 发起任务，再轮询 GET /api/generate/{taskId} 直到完成。本系列提供 9 个端点。

概览

每个端点共享相同的外层结构 —— 只有 model 和 input 字段不同。可在模型市场的 playground 中运行任意一个。

认证

在 /api-keys 创建 API 密钥，然后作为 Bearer token 发送。已登录时从浏览器发起的请求也可通过会话 cookie 生效。

Authorization: Bearer <YOUR_API_KEY>

创建任务

POST
POST https://api.lithovas.com/api/generate

请求体：{ "model": "<slug>", "input": { … } }

响应：{ "taskId": "<id>", "state": "waiting" }

查询结果

GET
GET https://api.lithovas.com/api/generate/<taskId>

响应：{ "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

异步
创建任务返回 200 只表示任务已被接受 —— 并非已完成。请轮询此端点，直到 state 变为 success 或 fail。失败任务不计费。

端点

模型任务model slug
Imagen 4 FastText to Imagegoogle/imagen4-fast
Imagen 4 UltraText to Imagegoogle/imagen4-ultra
Imagen 4Text to Imagegoogle/imagen4
Nano Banana EditImage to Imagegoogle/nano-banana-edit
Nano BananaText to Imagegoogle/nano-banana
ProImage to Imagegoogle/pro-image-to-image
Nano Banana 2Text to Imagegoogle/nanobanana2
Nano Banana 2 LiteText to Imagegoogle/nano-banana-2-lite
Gemini 3.1 Flash TTSText to Speechgoogle/gemini-3-1-flash-tts

Imagen 4 Fast · Text to Image

POSTText to Imagegoogle/imagen4-fast
input 字段
promptstring必填

Text prompt describing what you want to see (max 5000 characters)

negative_promptstring可选

Description of what to discourage in generated images (max 5000 chars)

aspect_ratioenum<string>可选

The aspect ratio of the generated image

seedinteger可选

Random seed for reproducible generation

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/imagen4-fast",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "negative_prompt": "example",
    "aspect_ratio": "16:9",
    "seed": 42
  }
}'

Imagen 4 Ultra · Text to Image

POSTText to Imagegoogle/imagen4-ultra
input 字段
promptstring必填

Text description of desired image (max 5000 chars)

negative_promptstring可选

Description of elements to exclude from generation (max 5000 chars)

aspect_ratioenum<string>可选

Output image aspect ratio

seedstring可选

Random seed for reproducible results (max 500 chars)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/imagen4-ultra",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "negative_prompt": "example",
    "aspect_ratio": "1:1",
    "seed": 42
  }
}'

Imagen 4 · Text to Image

POSTText to Imagegoogle/imagen4
input 字段
promptstring必填

The text prompt describing what you want to see (max 5000 characters)

negative_promptstring可选

A description of what to discourage in the generated images (max 5000 chars)

aspect_ratioenum<string>可选

The aspect ratio of the generated image

seedstring可选

Random seed for reproducible generation (max 500 characters)

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/imagen4",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "negative_prompt": "example",
    "aspect_ratio": "1:1",
    "seed": 42
  }
}'

Nano Banana Edit · Image to Image

POSTImage to Imagegoogle/nano-banana-edit
input 字段
promptstring必填

The prompt for image editing (max 5000 characters)

image_urlsarray<string>必填

List of URLs of input images for editing, up to 10 images

output_formatenum<string>可选

Output format for the generated images

aspect_ratioenum<string>可选

Aspect ratio for the generated image

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/nano-banana-edit",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "output_format": "png",
    "aspect_ratio": "1:1"
  }
}'

Nano Banana · Text to Image

POSTText to Imagegoogle/nano-banana
input 字段
promptstring必填

The prompt for image generation (max 5000 characters)

output_formatenum<string>可选

Output format for the images

aspect_ratioenum<string>可选

Image aspect ratio configuration

image_sizeenum<string>可选

Deprecated parameter; use aspect_ratio instead

nsfw_checkerboolean可选

Disables content filtering when false

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/nano-banana",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "output_format": "png",
    "aspect_ratio": "1:1",
    "image_size": "1:1",
    "nsfw_checker": false
  }
}'

Pro · Image to Image

POSTImage to Imagegoogle/pro-image-to-image
input 字段
promptstring必填

Text description of image to generate (max 10000 characters)

image_inputarray<string>可选

Input images as file URLs for transformation/reference (max 8 images, 30MB each)

aspect_ratioenum<string>可选

Aspect ratio of generated image

resolutionenum<string>可选

Resolution of generated image

output_formatenum<string>可选

Format of output image

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/pro-image-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_input": [
      "https://example.com/input.jpg"
    ],
    "aspect_ratio": "1:1",
    "resolution": "1K",
    "output_format": "png"
  }
}'

Nano Banana 2 · Text to Image

POSTText to Imagegoogle/nanobanana2
input 字段
promptstring必填

Text description of image to generate (max 20000 chars)

image_inputarray<string>可选

Input images as file URLs for transformation (max 14, up to 30MB)

aspect_ratiostring可选

Aspect ratio of generated image

resolutionstring可选

Output image resolution

output_formatstring可选

Output image file format

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/nanobanana2",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_input": [
      "https://example.com/input.jpg"
    ],
    "aspect_ratio": "auto",
    "resolution": "1K",
    "output_format": "jpg"
  }
}'

Nano Banana 2 Lite · Text to Image

POSTText to Imagegoogle/nano-banana-2-lite
input 字段
image_urlsarray<string>可选

Input image URL array for visual references; supports up to 10 images

promptstring必填

Text prompt for image generation; max 20000 characters

aspect_ratioenum<string>必填

Output image aspect ratio

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/nano-banana-2-lite",
  "input": {
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "aspect_ratio": "auto"
  }
}'

Gemini 3.1 Flash TTS · Text to Speech

POSTText to Speechgoogle/gemini-3-1-flash-tts
input 字段
promptstring必填

Text prompt describing the desired output.

示例
cURL
curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-3-1-flash-tts",
  "input": {
    "prompt": "a red panda surfing"
  }
}'