Vertex Text generation - ZnapAI Documentation

Request

curl --location "https://api.znapai.com/v1beta1/projects/default/locations/global/publishers/google/models/gemini-2.5-flash-lite:generateContent" \
  --header "Authorization: Bearer $ZnapAI_API_KEY" \
  --header "Content-Type: application/json" \
  --header 'spend-logs-metadata: {"user_id": "user-123", "project_id": "proj_abc", "env": "production"}' \
  --data '{
        "contents": [
          {"role": "user", "parts": [{"text": "Say hello world"}]}
        ]
      }'

Response

{
    "candidates": [
        {
            "content": {
                "role": "model",
                "parts": [
                    {
                        "text": "Hello world"
                    }
                ]
            },
            "finishReason": "STOP",
            "avgLogprobs": -4.6243147850036621
        }
    ],
    "usageMetadata": {
        "promptTokenCount": 3,
        "candidatesTokenCount": 2,
        "totalTokenCount": 32,
        "trafficType": "ON_DEMAND",
        "promptTokensDetails": [
            {
                "modality": "TEXT",
                "tokenCount": 3
            }
        ],
        "candidatesTokensDetails": [
            {
                "modality": "TEXT",
                "tokenCount": 2
            }
        ],
        "thoughtsTokenCount": 27
    },
    "modelVersion": "gemini-2.5-flash-lite",
    "createTime": "2026-04-08T17:29:25.479946Z",
    "responseId": "dZDWacqlHdvzpt8Pud6xqAg"
}

Parameters

header

An optional header used for spend logging metadata, containing JSON properties like user_id, project_id, and env.

array

required

The conversation history or input prompts as an array of content objects.

Show contents[]

string

The role of the creator of the content (e.g. "user" or "model").

array

required

An ordered list of parts that constitute a single message turn.

Show parts[]

string

The text prompt or response content.

object

System instructions that provide context, rules, or guidelines to the model.

Show systemInstruction

array

required

An ordered list of parts that constitute the system instruction.

Show parts[]

string

The text content of the system instruction.

object

Configuration options for model generation and outputs.

Show generationConfig

number

Controls the randomness of the output.

number

The maximum cumulative probability of tokens to consider when sampling.

integer

The maximum number of tokens to consider when sampling.

integer

Number of generated responses to return.

integer

The maximum number of tokens to include in a candidate.

array

A list of strings that tell the model to stop generating text.

string

Output response mimetype of the generated candidate text (e.g. text/plain or application/json).

object

Output response schema of the generated candidate text when responseMimeType is application/json. Schema must be a subset of the OpenAPI schema.

array

A list of unique safety settings for blocking unsafe content.

Show safetySettings[]

string

The category for this setting (e.g. HARM_CATEGORY_HATE_SPEECH).

string

Block threshold for this category (e.g. BLOCK_MEDIUM_AND_ABOVE).

array

A list of Tools the model may use to generate the next response. Supported tools are function declarations, code execution, and Google Search.

Show tools[]

array

A list of function declarations the model can call.

Show functionDeclarations[]

string

required

The name of the function to call.

string

A description of what the function does.

object

Describes the parameters for the function in JSON Schema format.

Show parameters

string

The type of the parameters object. Usually "object".

object

A map of parameter names to their schema definitions.

array

List of required parameter names.

object

Enables the model to execute code as part of generation. Pass an empty object {} to enable.

object

Tool to support Google Search grounding in model responses. Pass an empty object {} to enable.

object

Tool configuration for any Tool specified in the request.

Show toolConfig

object

Configuration for function calling behavior.

Show functionCallingConfig

string

Controls how the model uses the provided functions. One of:

"AUTO" — model decides whether to call a function or respond in text
"ANY" — model must call one of the provided functions
"NONE" — model must not call any functions

array

Optional. When mode is "ANY", limits the model to only call functions from this list.

Params to Avoid

Param	Reason
`model`	Model is specified in the URL path
`spend-logs-metadata`	This metadata must be passed as an HTTP header, not in the JSON request body

​Request

​Response

​Parameters

​Params to Avoid

Request

Response

Parameters

Params to Avoid