Gemini Media Recognition (Native Format)

Beyond text chat, the Gemini native API supports uploading images, PDFs, audio, and video to the same generateContent endpoint for recognition and understanding, using the same Base URL and authentication as Gemini Text Chat.

inlineData Base64 uploads only

YouQi AI only supports inlining media as Base64 via inlineData. It does not support fileData.fileUri or the Gemini File API (upload-then-reference). Encode your file as Base64 and embed it directly in the request body.

Endpoint

POST /v1beta/models/{model}:generateContent

Base URL and auth are the same as Gemini Text Chat: https://ai.youqi.tech/v1beta, authenticated via the ?key= query parameter or the x-goog-api-key header.

Request parameters

Parameter	Type	Required	Description
contents	array	Yes	Conversation contents, each with role and parts
parts[].text	string	No	Text prompt
parts[].inlineData	object	No	Inline media data with mimeType and data (Base64 string)

Request examples

Image recognition

curl "https://ai.youqi.tech/v1beta/models/gemini-2.5-pro:generateContent?key=sk-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          { "text": "What is in this image?" },
          {
            "inlineData": {
              "mimeType": "image/jpeg",
              "data": "BASE64_ENCODED_IMAGE_DATA"
            }
          }
        ]
      }
    ]
  }'

PDF / audio / video recognition

Replace mimeType with the matching type (e.g. application/pdf, audio/mp3, video/mp4) and data with that file's Base64 encoding; the rest of the structure is the same:

{
  "contents": [
    {
      "role": "user",
      "parts": [
        { "text": "Summarize the key points of this PDF." },
        {
          "inlineData": {
            "mimeType": "application/pdf",
            "data": "BASE64_ENCODED_PDF_DATA"
          }
        }
      ]
    }
  ]
}

Response example

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [{ "text": "The image shows a golden retriever running on grass." }]
      },
      "finishReason": "STOP"
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 258,
    "candidatesTokenCount": 18,
    "totalTokenCount": 276
  }
}

TIP

Base64 encoding significantly increases the request body size — watch client and gateway request size limits for large files. For text-only chat, use Gemini Text Chat instead.