BeeBridge AIBeeBridge AI
API Reference
AI Model APIChatNative Gemini Format
⚠️Compliance notice: Use this project only for lawfully authorized API gateway, internal management, and private deployment scenarios. Follow upstream terms of service, platform rules, regulatory requirements, and content safety requirements.

Gemini Media Recognition

Gemini Image, PDF, Audio, Video Recognition Request

⚠️Note: Native Gemini format requests support passing media via inlineData (base64) or fileData.fileUri (a publicly accessible URL, YouTube links included). Accessibility of file URIs uploaded via the Gemini File API depends on the permissions of the upstream channel key, so the use of a publicly accessible URL is recommended. When an OpenAI format (chat/completions) request is converted to Gemini, media is uniformly downloaded and passed as inlineData (base64).

POST
/v1beta/models/{model}:generateContent
AuthorizationBearer <token>

Authenticate with a Bearer token. Format: Authorization: Bearer sk-xxxxxx

In: header

Path Parameters

modelstring

Model name

contents?
generationConfig?
safetySettings?
tools?
systemInstruction?

Response Body

application/json

curl -X POST "https://api.beeaicloud.com/v1beta/models/string:generateContent" \  -H "Content-Type: application/json" \  -d '{}'
{
  "candidates": [
    {
      "content": {
        "role": "string",
        "parts": [
          {}
        ]
      },
      "finishReason": "string",
      "safetyRatings": [
        {}
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 0,
    "candidatesTokenCount": 0,
    "totalTokenCount": 0
  }
}

How is this guide?

Gemini Media Recognition | BeeBridge AI