Skip to content

Use CrewAI with amazee.ai

CrewAI is a framework for building multi-agent AI systems. Connect it to amazee.ai to run your crews through your regional endpoint with full data residency and budget controls.

Prerequisites

Connect CrewAI to amazee.ai

Option 1 — Environment variables

Set these before running your crew:

export OPENAI_API_KEY="your-amazee-ai-api-key"
export OPENAI_API_BASE="https://llm.[your-region].amazee.ai/v1"

Replace [your-region] with your region code (e.g. ch103, us103, de103).

Then use the model in your crew definition:

from crewai import LLM

llm = LLM(model="openai/claude-sonnet-4-5")

Option 2 — Explicit configuration in code

from crewai import LLM

llm = LLM(
    model="openai/claude-sonnet-4-5",
    api_key="your-amazee-ai-api-key",
    base_url="https://llm.[your-region].amazee.ai/v1",
    temperature=0.7,
)

Option 3 — YAML configuration

In your crew's YAML config:

llm:
  provider: openai
  config:
    model: openai/claude-sonnet-4-5
    api_key: your-amazee-ai-api-key
    base_url: https://llm.[your-region].amazee.ai/v1

Verify

Run your crew and check my.amazee.ioUsage to confirm requests are flowing through your amazee.ai endpoint.

Troubleshooting

Auth errors : Make sure OPENAI_API_KEY is set or api_key is passed directly to the LLM constructor.

Model not found : Prefix the model ID with openai/ (e.g. openai/claude-sonnet-4-5). CrewAI uses LiteLLM under the hood, which requires the provider prefix.

Import errors : If using LiteLLM features, install with pip install 'crewai[litellm]'.