Gemini 3.5 Flash

Identifier for the type of task being performed

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

Determines how the API delivers task results.

Include task cost in the response.

Include token usage statistics in the response.

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

Array of audio inputs (UUID, URL, or Base64).

Array of document inputs (UUID, URL, or Base64).

Array of image inputs (UUID, URL, Data URI, or Base64).

Array of video inputs (UUID, URL, or Base64).

Identifier of the model to use for generation.

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

JSON Schema for structured output. Only honoured when outputFormat is JSON. Accepts the OpenAI envelope ({name, schema, strict}) or a bare JSON Schema; bare schemas are auto-wrapped with name='response' and strict=true.

Array of chat messages forming the conversation context. The final message must use the user role.

System-level instruction that guides the model's behavior and output style across the entire generation.

Controls randomness in generation. Lower values produce more deterministic outputs, higher values increase variation and creativity.

Nucleus sampling parameter that controls diversity by limiting the probability mass. Lower values make outputs more focused, higher values increase diversity.

Penalizes tokens based on their frequency in the output so far. A value of 0.0 disables the penalty.

Maximum number of tokens to generate in the response.

Encourages the model to introduce new topics. A value of 0.0 disables the penalty.

Array of sequences that will cause the model to stop generating further tokens when encountered.

Controls the depth of internal reasoning the model performs before generating a response.

Top-K sampling parameter that limits the number of highest-probability tokens considered at each step.

Controls how the model selects which tool to call. This only takes effect when tools are defined.

"toolChoice": {
  "type": "auto"
}

"toolChoice": {
  "type": "tool",
  "name": "get_weather"
}

"toolChoice": {
  "type": "any"
}

An array of tool definitions that the model may call during generation. The model can invoke one or more tools based on the conversation context, outputting structured calls with arguments instead of (or alongside) free-text.

For function tools, each definition requires:

• type: "function"
• name: Unique identifier (alphanumeric, hyphens, underscores; max 64 chars).
• description: What the function does. The model uses this to decide when to call it.
• schema: JSON Schema object describing the expected input arguments.

"tools": [
  {
    "type": "function",
    "name": "get_weather",
    "description": "Get current weather for a city",
    "schema": {
      "type": "object",
      "properties": {
        "city": { "type": "string", "description": "City name" }
      },
      "required": ["city"]
    }
  }
],
"toolChoice": { "type": "auto" }

"tools": [
  { "type": "search" }
]

"tools": [
  { "type": "codeInterpreter" }
]

"tools": [
  {
    "type": "function",
    "name": "search_products",
    "description": "Search the product catalog by query and filters.",
    "schema": {
      "type": "object",
      "properties": {
        "query": { "type": "string" },
        "category": { "type": "string" }
      },
      "required": ["query"]
    }
  },
  {
    "type": "function",
    "name": "add_to_cart",
    "description": "Add a product to the user's shopping cart.",
    "schema": {
      "type": "object",
      "properties": {
        "productId": { "type": "string" },
        "quantity": { "type": "integer", "minimum": 1 }
      },
      "required": ["productId"]
    }
  }
]

Controls the token budget allocated to images and video frames. Higher values preserve more detail at the cost of additional tokens.

Enable live web search grounding to incorporate real-world, up-to-date information into image generation.

Latitude for location-biased Google Search grounding.

Longitude for location-biased Google Search grounding.

Encrypted reasoning context returned from a previous response. Pass it back to maintain multi-turn reasoning continuity.