Skip to main content
LemonData supports the native Google Gemini API format for Gemini models. This allows direct compatibility with Google AI SDKs.

​
Path Parameters

​
model
string
required
Model name (e.g., gemini-2.5-pro, gemini-2.5-flash).

​
Query Parameters

​
key
string
API key (alternative to header authentication).

​
Authentication

Gemini endpoints support multiple authentication methods:
  • ?key=YOUR_API_KEY query parameter
  • x-goog-api-key: YOUR_API_KEY header
  • Authorization: Bearer YOUR_API_KEY header

​
Request Body

​
contents
array
required
Conversation contents.Each content object contains:
  • role (string): user or model
  • parts (array): Content parts (text parts or inline_data image parts)
​
systemInstruction
object
System instruction for the model.
​
generationConfig
object
Generation configuration:
  • temperature (number): Sampling temperature
  • topP (number): Nucleus sampling probability
  • topK (integer): Top-K sampling
  • maxOutputTokens (integer): Maximum output tokens
  • stopSequences (array): Stop sequences
​
safetySettings
array
Safety filter settings.

​
Response

​
candidates
array
Generated content candidates.
​
usageMetadata
object
Token usage information.
curl -X POST "https://api.lemondata.cc/v1beta/models/gemini-2.5-pro:generateContent?key=sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "parts": [{"text": "Hello, Gemini!"}]
      }
    ],
    "generationConfig": {
      "temperature": 0.7,
      "maxOutputTokens": 1024
    }
  }'

​
Vision Input Example

For Gemini vision requests, place images inside contents[].parts[] as structured inline_data parts. The data field should contain Base64-encoded file bytes, and mime_type should match the uploaded image format. 
{
  "contents": [
    {
      "role": "user",
      "parts": [
        { "text": "Please describe this image." },
        {
          "inline_data": {
            "mime_type": "image/jpeg",
            "data": "/9j/4AAQSkZJRgABAQ..."
          }
        }
      ]
    }
  ]
}

{
  "candidates": [
    {
      "content": {
        "role": "model",
        "parts": [
          {"text": "Hello! How can I assist you today?"}
        ]
      },
      "finishReason": "STOP",
      "safetyRatings": [
        {"category": "HARM_CATEGORY_HARASSMENT", "probability": "NEGLIGIBLE"}
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 5,
    "candidatesTokenCount": 10,
    "totalTokenCount": 15
  }
}