Gemini Content Generation

Proxy Gemini API requests, supporting text chat and media recognition.

Path format: /v1beta/models/{model_name}:generateContent

Supported features:

• Text conversation
• Multi-turn conversation
• Image recognition (via inlineData base64)
• PDF recognition
• Video recognition
• Audio recognition

⚠️Note: Only supports uploading media via inlineData in base64 format. fileData.fileUri and File API are not supported.

curl -X POST "https://docs.newapi.ai/v1beta/models/string:generateContent" \  -H "Content-Type: application/json" \  -d '{    "contents": [      {        "role": "user",        "parts": [          {            "text": "Hi"          }        ]      }    ]  }'

{
  "candidates": [
    {
      "content": {
        "role": "string",
        "parts": [
          {}
        ]
      },
      "finishReason": "string",
      "safetyRatings": [
        {}
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 0,
    "candidatesTokenCount": 0,
    "totalTokenCount": 0
  }
}