GPT88 / API Docs
ImageGoogle3 vendors

gemini-3-pro-image-preview

Google image generation model available through the GPT88 unified API.

Get API Key on gpt88.ccQuickstart

Overview

  • gemini-3-pro-image-preview is listed in the current GPT88 model catalog with model ID gemini-3-pro-image-preview.
  • This route uses a generic English integration profile because a model-specific editorial profile has not been published. Confirm current access and behavior before production use.

Best Use Cases

  • Evaluate it when you need a image generation model and want to keep an existing GPT88 integration.
  • Compare it with a model that already performs well on the same representative workload before changing a production default.

Integration Notes

  • Keep the exact model ID gemini-3-pro-image-preview in the request body and use the endpoint displayed on this page.
  • Call GET /v1/models or check the GPT88 console first to confirm that the current API key can access the model.

Usage Notes

  • Availability, pricing, context limits, rate limits, routes, permissions, and feature support are determined by the current GPT88 console configuration.
  • Generic catalog copy is not a model capability guarantee. Validate output quality, errors, latency, and usage on your own workload.

Capabilities

This model's Capabilities should be verified in the gpt88.cc console. This page focuses on protocol shape and request examples.gpt88.cc console for the real-time catalog.

Recommended Scenarios

This model's Recommended Scenarios should be verified in the gpt88.cc console. This page focuses on protocol shape and request examples.gpt88.cc console for the real-time catalog.

Endpoint Path

POSThttps://img.gpt88.cc/v1beta/models/gemini-3-pro-image-preview:generateContent

The endpoint path is determined by the model category. Chat, image, video, and audio models use different endpoints.

Send requests with Authorization: Bearer <API_KEY>. See Images API for the full parameter reference.

API Docs

Endpoint
POST /v1beta/models/gemini-3-pro-image-preview:generateContent
Model ID
gemini-3-pro-image-preview
Content-Type
application/json
Protocol
Gemini-native image generation. generateContent returns images in inlineData base64.
Base URL
Gemini-native image endpoints use the media Base URL https://img.gpt88.cc.

Headers / Auth

  • AuthorizationstringRequired
    Send Bearer <GPT88_API_KEY>. Create the API key in the gpt88.cc console.
  • Content-TypestringRequired
    Request body format. Audio transcription uploads use multipart/form-data.
    Default:application/json
  • Acceptstring
    Non-streaming requests return JSON; streaming chat requests return SSE chunks.
    Default:application/json
  • x-goog-api-keystring
    If the current route does not accept Authorization: Bearer, pass the API key with this header instead.

Request Parameters

The fields below are generated by model category. Pricing, context limits, rate limits, and available routes should be confirmed in the gpt88.cc console.

  • contentsarray<Content>Required
    Gemini generateContent input. Put the text prompt in contents[].parts[].text.
  • contents[].parts[].textstringRequired
    Image-generation prompt covering subject, style, aspect ratio, details, and constraints.
  • contents[].parts[].fileDataobject
    Reference image for image-to-image. Include mimeType and fileUri. The referenced file must be reachable by the server.
  • generationConfig.responseModalitiesstring[]Required
    Request both text and image outputs. Include IMAGE when generating images.
    Default:["TEXT", "IMAGE"]
  • generationConfig.responseFormat.image.aspectRatiostring
    Aspect ratio such as 1:1, 16:9, 9:16, 4:3, or 3:4.
    Default:1:1
  • generationConfig.responseFormat.image.imageSizestring
    Output size. Use uppercase values such as 1K, 2K, or 4K.
    Default:1K
  • modelpath parameterRequired
    The model ID is part of the path: /v1beta/models/gemini-3-pro-image-preview:generateContent.

Response Fields

Response bodies generally follow OpenAI-compatible shapes. Media models may return async task IDs or resource URLs.

  • candidatesarray<Candidate>Required
    Gemini candidate array.
  • candidates[].content.partsarray<Part>Required
    Contains text and image parts. Image bytes are usually in inlineData.data.
  • inlineData.datastring
    Base64 image payload. Decode it and write it to a PNG file.
  • usageMetadataobject
    Gemini-style usage metadata. Whether it is returned depends on the actual response.

Status Codes

  • 200OKRequired
    Request succeeded. See the response field table above for the response body shape.
  • 400Bad Request
    Invalid request fields, such as missing required fields, unsupported image size format, or unsupported file type.
  • 401Unauthorized
    API key is missing, invalid, or malformed.
  • 404Not Found
    Endpoint or model not found. Confirm the path is /v1beta/models/gemini-3-pro-image-preview:generateContent and the model ID is gemini-3-pro-image-preview.
  • 429Rate Limited
    Rate limit, concurrency cap, or insufficient balance. Check the console for the current allowance.
  • 5xxUpstream Error
    Upstream or request failure. Retry with the same Base URL and keep the request ID for debugging.

Errors and Troubleshooting

  • 401: verify Authorization is Bearer <API_KEY> and the key is still valid.
  • 404: confirm the endpoint is /v1beta/models/gemini-3-pro-image-preview:generateContent and the model ID gemini-3-pro-image-preview is available in the console.
  • 429: reduce concurrency, shorten requests, or check balance and quota in the console.
  • 5xx: retry with the same Base URL and keep the request ID for debugging.

Request Examples

export API_KEY="YOUR_GPT88_API_KEY"
export BASE_URL="https://img.gpt88.cc"
export MODEL="gemini-3-pro-image-preview"

curl -s -X POST \
  "$BASE_URL/v1/models/$MODEL:generateContent" \
  -H "x-goog-api-key: $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [{
        "text": "Create a cinematic 16:9 cyberpunk city at night with neon lights and rain."
      }]
    }],
    "generationConfig": {
      "responseModalities": ["IMAGE"],
      "responseFormat": {
        "image": {
          "aspectRatio": "16:9",
          "imageSize": "2K"
        }
      }
    }
  }' > response.json

jq -r '.. | objects | .inlineData?.data? | select(.)' response.json | head -n 1 | base64 -d > output.png

Expected response (trimmed example):

200 OKjson
{
  "candidates": [
    {
      "content": {
        "parts": [
          { "text": "Image generated." },
          {
            "inlineData": {
              "mimeType": "image/png",
              "data": "iVBORw0KGgoAAA..."
            }
          }
        ]
      }
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 24,
    "totalTokenCount": 88
  }
}