Jiniu AIJiniu AI
Docs
ImagesNative Gemini format

Native Gemini format

Gemini image generation

POST
/v1beta/models/{model}:generateContent

Path Parameters

model*string

Model name, such as gemini-3-pro-image-preview

Request Body

application/json

contents*

Conversation contents. For text-to-image, text only; for image-to-image, put the reference image as inlineData alongside the text in the same parts array

generationConfig?

Generation settings. For image output, responseModalities must include IMAGE

safetySettings?

Safety settings, with a blocking threshold per harm category

systemInstruction?

System instruction, used to constrain style or output requirements

Response Body

application/json

curl -X POST "https://jiniu.ai/v1beta/models/string:generateContent" \  -H "Content-Type: application/json" \  -d '{    "contents": [      {        "role": "user",        "parts": [          {            "text": "一只戴宇航头盔的柴犬，等距视角"          }        ]      }    ],    "generationConfig": {      "responseModalities": [        "TEXT",        "IMAGE"      ],      "imageConfig": {        "aspectRatio": "16:9",        "imageSize": "2K"      }    }  }'
{
  "candidates": [
    {
      "content": {
        "role": "string",
        "parts": [
          {}
        ]
      },
      "finishReason": "string",
      "safetyRatings": [
        {}
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 0,
    "candidatesTokenCount": 0,
    "totalTokenCount": 0
  }
}