Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Googleapis Python genai Tokens

From Leeroopedia
Knowledge Sources
Domains Authentication, Tokens
Last Updated 2026-02-15 14:00 GMT

Overview

Concrete tool for creating ephemeral authentication tokens provided by the Google Gen AI SDK.

Description

The Tokens and AsyncTokens classes provide an experimental API module for creating short-lived authentication tokens. These tokens support configurable expiration times and usage constraints, and can include live connect configuration for WebSocket sessions. Only the Gemini Developer API (ML Dev) backend is supported.

Usage

Import this when you need to create ephemeral auth tokens for client-side applications that require limited-scope access to the Gemini API, particularly for Live API WebSocket sessions.

Code Reference

Source Location

Signature

class Tokens(_api_module.BaseModule):
    def create(
        self,
        *,
        config: Optional[types.CreateAuthTokenConfigOrDict] = None,
    ) -> types.AuthToken: ...

class AsyncTokens(_api_module.BaseModule):
    async def create(
        self,
        *,
        config: Optional[types.CreateAuthTokenConfigOrDict] = None,
    ) -> types.AuthToken: ...

Import

from google import genai
client = genai.Client(api_key="...")
# Access via: client.tokens

I/O Contract

Inputs

Name Type Required Description
config CreateAuthTokenConfigOrDict No Token configuration with expire_time, uses, and live_connect_constraints

Outputs

Name Type Description
create() returns AuthToken Ephemeral token with token string and metadata

Usage Examples

from google import genai
from google.genai import types

client = genai.Client(api_key="GEMINI_API_KEY")

# Create an ephemeral auth token
token = client.tokens.create(
    config=types.CreateAuthTokenConfig(
        uses=1,
    )
)

print(f"Token: {token.token}")

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment