Search...
Menu

Gemini Media Understanding

Attach images, audio, video, or PDFs to text messages for understanding by a Gemini model that supports the corresponding modalities.

Request

Item Description
Method POST
Path /v1beta/models/{model}:generateContent
Gateway URL https://ailink.nativex.com
Authentication Authorization: Bearer sk-xxxx; replace the placeholder with your API Key
Request format application/json

Replace MODEL_ID with a model from the Model Marketplace that supports this endpoint. Available models, parameters, and permissions depend on your account.

Parameters

Parameter Location Type Required Description
model Path string Yes Gemini model name
contents Body object[] Yes Message array. Each message contains role and parts; common roles are user and model.
systemInstruction Body object No System instructions, supplied through parts
generationConfig Body object No Generation settings, such as temperature, topP, and maxOutputTokens
safetySettings Body object[] No Safety settings supported by the model
tools Body object[] No Tool definitions
contents[].parts[].inlineData Body object No mimeType and Base64-encoded data
contents[].parts[].fileData Body object No mimeType and an accessible fileUri; use this or inlineData as appropriate
Replace the example media URL. Prefer URLs publicly accessible to the upstream service. Private URIs uploaded through the Gemini File API are subject to upstream account permissions.

Example

curl -X POST 'https://ailink.nativex.com/v1beta/models/MODEL_ID:generateContent' \
  -H 'Authorization: Bearer sk-xxxx' \
  -H 'Content-Type: application/json' \
  -d '{
  "contents": [
    {
      "role": "user",
      "parts": [
        {
          "text": "Describe this image."
        },
        {
          "fileData": {
            "mimeType": "image/png",
            "fileUri": "https://example.com/input.png"
          }
        }
      ]
    }
  ]
}'

Response

The following is a simplified response for readability. IDs, URLs, text, and usage values are illustrative.

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {
            "text": "Hello! How can I help you?"
          }
        ]
      },
      "finishReason": "STOP"
    }
  ]
}
Field or result Description
candidates[].content.parts[].text The model's analysis of the media

Error handling

For unsuccessful responses, check the HTTP status and error body first. Verify the API Key, model name, account balance, and parameters. If rate limited, reduce concurrency and retry later.

Last modified: 2026-11-17