Skip to main content
CrewAI talks to LLMs through LiteLLM. Point its LLM at the Orbitrage gateway and every agent’s call is routed and traced.

​
Install

pip install -U orbitrage crewai

​
Setup

import os, orbitrage
orbitrage.init(os.environ["ORBITRAGE_API_KEY"], user_id="customer_42")

from crewai import Agent, Task, Crew, LLM

llm = LLM(
    model="openai/gpt-4o-mini",                  # see the model-name note below
    base_url="https://api.orbitrage.ai/v1",
    api_key=os.environ["ORBITRAGE_API_KEY"],
)

researcher = Agent(role="Researcher", goal="Find the answer",
                   backstory="A sharp analyst.", llm=llm, verbose=False)
task = Task(description="Summarize what an LLM router does, in one sentence.",
            expected_output="one sentence", agent=researcher)

print(Crew(agents=[researcher], tasks=[task], verbose=False).kickoff())
Model names: CrewAI/LiteLLM validate the model id client-side against their registry, so recognized OpenAI names work out of the box — openai/gpt-4o-mini, openai/gpt-4o, openai/gpt-4.1. The gateway serves them and traces everything.Non-OpenAI ids like openai/grok-4-fast, openai/claude-sonnet-4-6, or openai/auto are rejected by LiteLLM before the call is made. To use them, register the model with LiteLLM first:
import litellm
litellm.register_model({
    "grok-4-fast": {"litellm_provider": "openai", "mode": "chat",
                    "supports_function_calling": True},
})
llm = LLM(model="openai/grok-4-fast", base_url="https://api.orbitrage.ai/v1",
          api_key=os.environ["ORBITRAGE_API_KEY"])

​
Managed tools (server-side, no keys)

CrewAI agents use CrewAI-native tools, but you can call managed tools directly through the LLM with llm.call(...) — Orbitrage runs them server-side and returns the final answer. 
out = llm.call(
    [{"role": "user", "content": "Use the calculator to compute 1234*5678. Only the number."}],
    tools=[{
        "type": "function",
        "function": {"name": "calculator_orbitrage", "description": "Evaluate math",
                     "parameters": {"type": "object",
                                    "properties": {"expression": {"type": "string"}},
                                    "required": ["expression"]}},
    }],
)
print(out)   # 7006652
CrewAI’s LLM doesn’t forward custom headers, so per-request user_id switching isn’t available through it — the user_id you pass to orbitrage.init() attributes the whole crew’s run.