Crusoe
Crusoe provides managed inference for leading open-weight language models on renewable-powered GPU infrastructure.
Installation
Section titled “Installation”The OpenAI provider is an optional dependency. To install, run:
pip install 'strands-agents[openai]'npm install @strands-agents/sdk openaiGenerate an API key in the Security tab of the
Crusoe Cloud Console, export it as
CRUSOE_API_KEY, and point the provider at Crusoe’s endpoint:
import os
from strands import Agentfrom strands.models.openai import OpenAIModel
model = OpenAIModel( client_args={ "api_key": os.environ["CRUSOE_API_KEY"], "base_url": "https://api.inference.crusoecloud.com/v1/", }, model_id="zai/GLM-5.2",)
agent = Agent(model=model)response = agent("Explain tool calling in one sentence.")print(response)import { Agent } from '@strands-agents/sdk'import { OpenAIModel } from '@strands-agents/sdk/models/openai'
const model = new OpenAIModel({ api: 'chat', apiKey: process.env.CRUSOE_API_KEY, clientConfig: { baseURL: 'https://api.inference.crusoecloud.com/v1/', }, modelId: 'zai/GLM-5.2',})
const agent = new Agent({ model })const response = await agent.invoke('Explain tool calling in one sentence.')console.log(response)Configuration
Section titled “Configuration”Two client settings connect the provider to Crusoe Managed Inference:
- API key: from the Security tab of the Crusoe Cloud Console
- Base URL:
https://api.inference.crusoecloud.com/v1/
Model IDs come from the
Crusoe Managed Inference overview,
for example zai/GLM-5.2 or nvidia/Nemotron-3-Super-120B-A12B. For model
parameters and other provider options, see the
OpenAI provider guide.