Google

Los modelos de Google se llaman a través de una API de trabajos asíncrona y unificada. Inicia una tarea con POST /api/generate y luego sondea GET /api/generate/{taskId} hasta que termine. Esta familia expone 9 endpoints.

Resumen

Todos los endpoints comparten la misma envoltura — solo cambian model y los campos input. Ejecuta cualquiera desde el playground del Mercado de modelos.

Autenticación

Crea una API key en /api-keys y luego envíala como token Bearer. Las solicitudes desde el navegador con sesión iniciada también funcionan mediante la cookie de sesión.

Authorization: Bearer <YOUR_API_KEY>

Crear tarea

POST

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

Cuerpo: { "model": "<slug>", "input": { … } }

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

Consultar resultado

GET

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

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

Asíncrono

Un 200 de Crear tarea solo significa que la tarea fue aceptada — no que haya terminado. Sondea este endpoint hasta que state sea success o fail. Las tareas fallidas no se facturan.

Endpoints

Modelo	Tarea	model slug
Imagen 4 Fast	Text to Image	google/imagen4-fast
Imagen 4 Ultra	Text to Image	google/imagen4-ultra
Imagen 4	Text to Image	google/imagen4
Nano Banana Edit	Image to Image	google/nano-banana-edit
Nano Banana	Text to Image	google/nano-banana
Pro	Image to Image	google/pro-image-to-image
Nano Banana 2	Text to Image	google/nanobanana2
Nano Banana 2 Lite	Text to Image	google/nano-banana-2-lite
Gemini 3.1 Flash TTS	Text to Speech	google/gemini-3-1-flash-tts

Imagen 4 Fast · Text to Image

POSTText to Imagegoogle/imagen4-fast

campos input

promptstringobligatorio

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

negative_promptstringopcional

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

aspect_ratioenum<string>opcional

The aspect ratio of the generated image

seedintegeropcional

Random seed for reproducible generation

Ejemplo

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

campos input

promptstringobligatorio

Text description of desired image (max 5000 chars)

negative_promptstringopcional

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

aspect_ratioenum<string>opcional

Output image aspect ratio

seedstringopcional

Random seed for reproducible results (max 500 chars)

Ejemplo

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

campos input

promptstringobligatorio

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

negative_promptstringopcional

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

aspect_ratioenum<string>opcional

The aspect ratio of the generated image

seedstringopcional

Random seed for reproducible generation (max 500 characters)

Ejemplo

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

campos input

promptstringobligatorio

The prompt for image editing (max 5000 characters)

image_urlsarray<string>obligatorio

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

output_formatenum<string>opcional

Output format for the generated images

aspect_ratioenum<string>opcional

Aspect ratio for the generated image

Ejemplo

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

campos input

promptstringobligatorio

The prompt for image generation (max 5000 characters)

output_formatenum<string>opcional

Output format for the images

aspect_ratioenum<string>opcional

Image aspect ratio configuration

image_sizeenum<string>opcional

Deprecated parameter; use aspect_ratio instead

nsfw_checkerbooleanopcional

Disables content filtering when false

Ejemplo

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

campos input

promptstringobligatorio

Text description of image to generate (max 10000 characters)

image_inputarray<string>opcional

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

aspect_ratioenum<string>opcional

Aspect ratio of generated image

resolutionenum<string>opcional

Resolution of generated image

output_formatenum<string>opcional

Format of output image

Ejemplo

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

campos input

promptstringobligatorio

Text description of image to generate (max 20000 chars)

image_inputarray<string>opcional

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

aspect_ratiostringopcional

Aspect ratio of generated image

resolutionstringopcional

Output image resolution

output_formatstringopcional

Output image file format

Ejemplo

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

campos input

image_urlsarray<string>opcional

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

promptstringobligatorio

Text prompt for image generation; max 20000 characters

aspect_ratioenum<string>obligatorio

Output image aspect ratio

Ejemplo

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

campos input

promptstringobligatorio

Text prompt describing the desired output.

Ejemplo

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"
  }
}'