CrewAI

Overview

CrewAI supports OpenAI-compatible LLMs by setting the model, API key, and base URL on environment variables or on the LLM class.

Type: Agent FrameworkPrimary Path: OpenAI-compatible chat completionsSupport Confidence: Supported custom endpoint path

Environment Variables

import os

os.environ["OPENAI_API_KEY"] = "sk-your-api-key"
os.environ["OPENAI_API_BASE"] = "https://api.aisonar.dev/v1"
os.environ["OPENAI_MODEL_NAME"] = "claude-sonnet-5"

LLM Class

from crewai import Agent, LLM

llm = LLM(
    model="claude-sonnet-5",
    base_url="https://api.aisonar.dev/v1",
    api_key="sk-your-api-key",
)

agent = Agent(
    role="Research analyst",
    goal="Summarize technical tradeoffs clearly",
    backstory="You produce concise implementation notes.",
    llm=llm,
)

Model Suggestions

Use gpt-5.4-mini for routine crews, claude-sonnet-5 or gpt-5.4 for planning-heavy agents, and deepseek-v4-flash for faster low-cost iterations.

Endpoint Notes

CrewAI’s OpenAI-compatible path is best for Chat Completions style agent calls. Use AI Sonar native endpoints directly only when the tool or SDK you choose can speak those native protocols.

Semantic Kernel Pydantic AI

Compatibility Matrix

Coding Tools

Native SDKs

Frameworks & Platforms

Chat Apps

Overview

Environment Variables

LLM Class

Model Suggestions

Endpoint Notes

​Overview

​Environment Variables

​LLM Class

​Model Suggestions

​Endpoint Notes

Overview

Environment Variables

LLM Class

Model Suggestions

Endpoint Notes