CrewAI

Use Arbytra as your LLM provider in CrewAI for cost-effective multi-agent workflows. This integration is Python-only. For TypeScript, use the Vercel AI SDK integration.

Prerequisites

An Arbytra API key

Install

pip install "arbytra[crewai]"

Use SDK adapter

Use the ArbytraCrewAILLM adapter:

from arbytra.frameworks.crewai import ArbytraCrewAILLM

arbytra_llm = ArbytraCrewAILLM(model="gpt-5.4")

ArbytraCrewAILLM routes models through Arbytra’s OpenAI-compatible endpoint. It passes provider="openai" to CrewAI, which prevents CrewAI from routing to native provider SDKs.

from crewai import Agent, Task, Crew

researcher = Agent(
    role="Researcher",
    goal="Find accurate and comprehensive information",
    backstory="You are an expert researcher with attention to detail.",
    llm=arbytra_llm.llm,
    verbose=True,
)

writer = Agent(
    role="Writer",
    goal="Write clear, engaging content based on research",
    backstory="You are a skilled technical writer.",
    llm=arbytra_llm.llm,
    verbose=True,
)

research_task = Task(
    description="Research the latest trends in AI agents",
    agent=researcher,
    expected_output="A detailed summary of AI agent trends with sources",
)

writing_task = Task(
    description="Write a blog post based on the research findings",
    agent=writer,
    expected_output="A 500-word blog post about AI agent trends",
    context=[research_task],
)

crew = Crew(
    agents=[researcher, writer],
    tasks=[research_task, writing_task],
    verbose=True,
)

result = crew.kickoff()
print(result)

Pass arbytra_llm.llm to Agent, not the ArbytraCrewAILLM instance.

Configure options

Parameter	Type	Default	Description
`model`	`str`	(required)	Model ID (e.g., `"gpt-5.4"`, `"claude-sonnet-4-20250514"`)
`api_key`	`str \| None`	`ARBYTRA_API_KEY` env	API key
`routing`	`RoutingOptions \| None`	`None`	Routing configuration
`base_url`	`str`	`"https://api.arbytra.com/v1"`	API base URL
`reasoning_effort`	`str \| None`	`None`	Reasoning effort: `"low"`, `"medium"`, `"high"`, `"xhigh"`, `"max"`, `"off"`
`stop`	`str \| list[str] \| None`	`None`	Stop sequences
`**kwargs`			Passed through to `crewai.LLM`

Configure routing

Pass a RoutingOptions instance to control routing:

from arbytra.frameworks.crewai import ArbytraCrewAILLM
from arbytra.route_types import RoutingOptions

arbytra_llm = ArbytraCrewAILLM(
    model="gpt-5.4",
    routing=RoutingOptions(optimize="cost"),
)

metadata = arbytra_llm.last_routing_metadata
if metadata:
    print(f"Provider: {metadata.provider}")

last_routing_metadata returns metadata from the most recent non-streaming response. Different agents can use different models and routing strategies:

fast_llm = ArbytraCrewAILLM(model="gpt-4o", routing=RoutingOptions(optimize="ttft-focus"))
smart_llm = ArbytraCrewAILLM(model="gpt-5.4", routing=RoutingOptions(optimize="balanced"))

researcher = Agent(role="Researcher", goal="Find information", backstory="Expert", llm=smart_llm.llm)
writer = Agent(role="Writer", goal="Write content", backstory="Skilled writer", llm=fast_llm.llm)

Configure manually

Alternative: configure CrewAI manually

If you prefer to use CrewAI’s LLM class directly, pass provider="openai" to route models through Arbytra:

import os
from crewai import LLM

llm = LLM(
    model="gpt-5.4",
    provider="openai",  # routes models through Arbytra
    base_url="https://api.arbytra.com/v1",
    api_key=os.environ["ARBYTRA_API_KEY"],
)

For routing options and metadata access, use ArbytraCrewAILLM.

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