Google ADK

Use Arbytra as your LLM provider in Google’s Agent Development Kit (ADK). This integration is Python-only. For TypeScript, use the Vercel AI SDK integration.

Prerequisites

An Arbytra API key

Install

pip install "arbytra[adk]"

Use SDK adapter

Use the ArbytraLlm adapter:

from arbytra.frameworks.adk import ArbytraLlm

llm = ArbytraLlm(model="gpt-5.4")

ArbytraLlm is a native BaseLlm implementation that supports text and function calling. It maps OpenAI API errors to typed Arbytra error classes.

import asyncio
from arbytra.frameworks.adk import ArbytraLlm
from google.adk import Agent, Runner
from google.adk.sessions import InMemorySessionService
from google.genai import types

llm = ArbytraLlm(model="gpt-5.4")

agent = Agent(
    model=llm,
    name="assistant",
    instruction="You are a helpful assistant.",
)

session_service = InMemorySessionService()
runner = Runner(agent=agent, app_name="my_app", session_service=session_service, auto_create_session=True)

user_message = types.Content(
    role="user", parts=[types.Part(text="What is 2+2?")]
)

async def main():
    async for event in runner.run_async(user_id="user-1", session_id="session-1", new_message=user_message):
        if event.content and event.content.parts:
            for part in event.content.parts:
                if part.text:
                    print(part.text, end="", flush=True)

asyncio.run(main())

inline_data and file_data parts raise NotImplementedError.

Configure options

Parameter	Type	Default	Description
`model`	`str`	(required)	Model ID
`api_key`	`str`	`ARBYTRA_API_KEY` env	API key
`routing`	`RoutingOptions \| None`	`None`	Routing configuration
`base_url`	`str`	`"https://api.arbytra.com/v1"`	API base URL

Configure routing

Pass a RoutingOptions instance to control routing:

from arbytra.frameworks.adk import ArbytraLlm
from arbytra.route_types import RoutingOptions

llm = ArbytraLlm(
    model="gpt-5.4",
    routing=RoutingOptions(optimize="cost"),
)

Configure manually

Alternative: configure ADK with LiteLlm manually

If you prefer to use Google’s LiteLlm class directly:

import os
from google.adk.models.lite_llm import LiteLlm

llm = LiteLlm(
    model="openai/gpt-5.4",
    api_key=os.environ["ARBYTRA_API_KEY"],
    api_base="https://api.arbytra.com/v1",
    custom_llm_provider="openai",
)

LiteLLM ignores api_base for model names containing provider keywords (like gpt or claude). Always include custom_llm_provider="openai" to force LiteLLM to respect your custom base URL.

For routing options and typed error mapping, use ArbytraLlm.

Get Started

Guides

Response API

Frameworks

Integrations

Specifications

Platform

Changelog

Prerequisites

Install

Use SDK adapter

Configure options

Configure routing

Configure manually

​Prerequisites

​Install

​Use SDK adapter

​Configure options

​Configure routing

​Configure manually

Prerequisites

Install

Use SDK adapter

Configure options

Configure routing

Configure manually