POST
/
v1beta
/
models
/
{model}
:generateContent
curl -X POST "https://api.example.com/v1beta/models/gemini-2.5-pro:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "What is the weather in San Francisco?"
          }
        ]
      }
    ],
    "tools": [
      {
        "functionDeclarations": [
          {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
              "type": "object",
              "properties": {
                "location": {
                  "type": "string",
                  "description": "The city and state, e.g. San Francisco, CA"
                },
                "unit": {
                  "type": "string",
                  "enum": ["celsius", "fahrenheit"],
                  "description": "Temperature unit"
                }
              },
              "required": ["location"]
            }
          }
        ]
      }
    ]
  }'

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "functionCall": {
              "name": "get_weather",
              "args": {
                "location": "San Francisco, CA"
              }
            }
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP"
    }
  ]
}
Official documentation: https://ai.google.dev/gemini-api/docs/function-calling
Function calling allows Gemini models to interact with external APIs and tools by generating structured function calls based on natural language requests.

​
Request Parameters

​
key
string
required
API key.
​
contents
array
required
Content array.Each content object contains:
  • role (string): Role (user or model)
  • parts (array): Content parts array
​
tools
array
Tools configuration defining available functions.Each tool object contains:
  • functionDeclarations (array): Array of function declarations
    • name (string): Function name
    • description (string): Function description
    • parameters (object): JSON schema for function parameters
​
generationConfig
object
Generation configuration.
  • temperature (number): Sampling temperature
  • topP (number): Nucleus sampling parameter

​
Response

Returns function call requests that should be executed and their results sent back to the model. 
curl -X POST "https://api.example.com/v1beta/models/gemini-2.5-pro:generateContent?key=YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [
          {
            "text": "What is the weather in San Francisco?"
          }
        ]
      }
    ],
    "tools": [
      {
        "functionDeclarations": [
          {
            "name": "get_weather",
            "description": "Get the current weather for a location",
            "parameters": {
              "type": "object",
              "properties": {
                "location": {
                  "type": "string",
                  "description": "The city and state, e.g. San Francisco, CA"
                },
                "unit": {
                  "type": "string",
                  "enum": ["celsius", "fahrenheit"],
                  "description": "Temperature unit"
                }
              },
              "required": ["location"]
            }
          }
        ]
      }
    ]
  }'

{
  "candidates": [
    {
      "content": {
        "parts": [
          {
            "functionCall": {
              "name": "get_weather",
              "args": {
                "location": "San Francisco, CA"
              }
            }
          }
        ],
        "role": "model"
      },
      "finishReason": "STOP"
    }
  ]
}