Using CrewAI Without LiteLLM

Overview

CrewAI supports two paths for connecting to LLM providers:

Native integrations — direct SDK connections to OpenAI, Anthropic, Google Gemini, Azure OpenAI, and AWS Bedrock
LiteLLM fallback — a translation layer that supports 100+ additional providers

This guide explains how to use CrewAI exclusively with native provider integrations, removing any dependency on LiteLLM.

The litellm package was quarantined on PyPI due to a security/reliability incident. If you rely on LiteLLM-dependent providers, you should migrate to native integrations. CrewAI’s native integrations give you full functionality without LiteLLM.

Why Remove LiteLLM?

Reduced dependency surface — fewer packages means fewer potential supply-chain risks
Better performance — native SDKs communicate directly with provider APIs, eliminating a translation layer
Simpler debugging — one less abstraction layer between your code and the provider
Smaller install footprint — LiteLLM brings in many transitive dependencies

Native Providers (No LiteLLM Required)

These providers use their own SDKs and work without LiteLLM installed:

OpenAI

GPT-4o, GPT-4o-mini, o1, o3-mini, and more.

uv add "crewai[openai]"

Anthropic

Claude Sonnet, Claude Haiku, and more.

uv add "crewai[anthropic]"

Google Gemini

Gemini 2.0 Flash, Gemini 2.0 Pro, and more.

uv add "crewai[gemini]"

Azure OpenAI

Azure-hosted OpenAI models.

uv add "crewai[azure]"

AWS Bedrock

Claude, Llama, Titan, and more via AWS.

uv add "crewai[bedrock]"

If you only use native providers, you never need to install crewai[litellm]. The base crewai package plus your chosen provider extra is all you need.

How to Check If You’re Using LiteLLM

Check your model strings

If your code uses model prefixes like these, you’re routing through LiteLLM:

Prefix	Provider	Uses LiteLLM?
`ollama/`	Ollama	✅ Yes
`groq/`	Groq	✅ Yes
`together_ai/`	Together AI	✅ Yes
`mistral/`	Mistral	✅ Yes
`cohere/`	Cohere	✅ Yes
`huggingface/`	Hugging Face	✅ Yes
`openai/`	OpenAI	❌ Native
`anthropic/`	Anthropic	❌ Native
`gemini/`	Google Gemini	❌ Native
`azure/`	Azure OpenAI	❌ Native
`bedrock/`	AWS Bedrock	❌ Native

Check if LiteLLM is installed

# Using pip
pip show litellm

# Using uv
uv pip show litellm

If the command returns package information, LiteLLM is installed in your environment.

Check your dependencies

Look at your pyproject.toml for crewai[litellm]:

# If you see this, you have LiteLLM as a dependency
dependencies = [
    "crewai[litellm]>=0.100.0",  # ← Uses LiteLLM
]

# Change to a native provider extra instead
dependencies = [
    "crewai[openai]>=0.100.0",   # ← Native, no LiteLLM
]

Migration Guide

Step 1: Identify your current provider

Find all LLM() calls and model strings in your code:

# Search your codebase for LLM model strings
grep -r "LLM(" --include="*.py" .
grep -r "llm=" --include="*.yaml" .
grep -r "llm:" --include="*.yaml" .

Step 2: Switch to a native provider

Switch to OpenAI
Switch to Anthropic
Switch to Gemini
Switch to Azure OpenAI
Switch to AWS Bedrock

from crewai import LLM

# Before (LiteLLM):
# llm = LLM(model="groq/llama-3.1-70b")

# After (Native):
llm = LLM(model="openai/gpt-4o")

# Install
uv add "crewai[openai]"

# Set your API key
export OPENAI_API_KEY="sk-..."

from crewai import LLM

# Before (LiteLLM):
# llm = LLM(model="together_ai/meta-llama/Meta-Llama-3.1-70B")

# After (Native):
llm = LLM(model="anthropic/claude-sonnet-4-20250514")

# Install
uv add "crewai[anthropic]"

# Set your API key
export ANTHROPIC_API_KEY="sk-ant-..."

from crewai import LLM

# Before (LiteLLM):
# llm = LLM(model="mistral/mistral-large-latest")

# After (Native):
llm = LLM(model="gemini/gemini-2.0-flash")

# Install
uv add "crewai[gemini]"

# Set your API key
export GEMINI_API_KEY="..."

from crewai import LLM

# After (Native):
llm = LLM(
    model="azure/your-deployment-name",
    api_key="your-azure-api-key",
    base_url="https://your-resource.openai.azure.com",
    api_version="2024-06-01"
)

# Install
uv add "crewai[azure]"

from crewai import LLM

# After (Native):
llm = LLM(
    model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0",
    aws_region_name="us-east-1"
)

# Install
uv add "crewai[bedrock]"

# Configure AWS credentials
export AWS_ACCESS_KEY_ID="..."
export AWS_SECRET_ACCESS_KEY="..."
export AWS_DEFAULT_REGION="us-east-1"

Step 3: Keep Ollama without LiteLLM

If you’re using Ollama and want to keep using it, you can connect via Ollama’s OpenAI-compatible API:

from crewai import LLM

# Before (LiteLLM):
# llm = LLM(model="ollama/llama3")

# After (OpenAI-compatible mode, no LiteLLM needed):
llm = LLM(
    model="llama3",
    custom_openai=True,
    base_url="http://localhost:11434/v1",
    api_key="ollama"  # Ollama doesn't require a real API key
)

Many local inference servers (Ollama, vLLM, LM Studio, llama.cpp) expose an OpenAI-compatible API. You can use custom_openai=True with a custom base_url to connect to any of them natively while keeping the model ID your gateway expects.

Step 4: Update your YAML configs

# Before (LiteLLM providers):
researcher:
  role: Research Specialist
  goal: Conduct research
  backstory: A dedicated researcher
  llm: groq/llama-3.1-70b          # ← LiteLLM
  
# After (Native provider):
researcher:
  role: Research Specialist
  goal: Conduct research
  backstory: A dedicated researcher
  llm: openai/gpt-4o               # ← Native

Step 5: Remove LiteLLM

Once you’ve migrated all your model references:

# Remove litellm from your project
uv remove litellm

# Or if using pip
pip uninstall litellm

# Update your pyproject.toml: change crewai[litellm] to your provider extra
# e.g., crewai[openai], crewai[anthropic], crewai[gemini]

Step 6: Verify

Run your project and confirm everything works:

# Run your crew
crewai run

# Or run your tests
uv run pytest

Custom OpenAI-Compatible Endpoints

Many providers and local servers (Ollama, vLLM, LM Studio, llama.cpp, LiteLLM proxies, and hosted gateways) expose an OpenAI-compatible API. Instead of routing these through LiteLLM, you can talk to them directly with CrewAI’s native OpenAI integration by setting custom_openai=True. This is the recommended replacement for any LiteLLM provider that offers an OpenAI-compatible endpoint.

How it works

custom_openai=True forces CrewAI to use the native OpenAI SDK, regardless of the model name.
The model ID is passed to the endpoint without validation against OpenAI’s known-model list. This lets you use arbitrary model IDs your gateway expects (for example, anthropic/claude-sonnet-4-6 served behind an OpenAI-compatible proxy). An optional leading openai/ routing prefix is stripped.
A base URL is required. CrewAI resolves it, in order, from:
1. base_url=...
2. api_base=...
3. OPENAI_BASE_URL environment variable
4. OPENAI_API_BASE environment variable (legacy)
If none are set, CrewAI raises a ValueError so misconfiguration fails fast instead of silently hitting api.openai.com.

from crewai import LLM

llm = LLM(
    model="anthropic/claude-sonnet-4-6",  # passed through as-is
    custom_openai=True,
    base_url="https://your-gateway.example/v1",
    api_key="your-key",
)

Connect to common servers

Ollama
vLLM
LM Studio
Env vars

from crewai import LLM

llm = LLM(
    model="llama3.2:latest",
    custom_openai=True,
    base_url="http://localhost:11434/v1",
    api_key="ollama",  # Ollama ignores it, but the client requires a value
)

from crewai import LLM

llm = LLM(
    model="meta-llama/Meta-Llama-3.1-8B-Instruct",
    custom_openai=True,
    base_url="http://localhost:8000/v1",
    api_key="not-needed",
)

from crewai import LLM

llm = LLM(
    model="your-loaded-model",
    custom_openai=True,
    base_url="http://localhost:1234/v1",
    api_key="lm-studio",
)

export OPENAI_BASE_URL="https://your-gateway.example/v1"
export OPENAI_API_KEY="your-key"

from crewai import LLM

# base_url is picked up from OPENAI_BASE_URL / OPENAI_API_BASE
llm = LLM(model="anthropic/claude-sonnet-4-6", custom_openai=True)

If you use the openai/ prefix with a model that isn’t a known OpenAI model and pass base_url or api_base directly, CrewAI automatically treats it as a custom OpenAI-compatible endpoint. Environment variables alone do not enable automatic routing for unknown models; set custom_openai=True when configuring the endpoint through OPENAI_BASE_URL or OPENAI_API_BASE.

Quick Reference: Model String Mapping

Here are common migration paths from LiteLLM-dependent providers to native ones:

from crewai import LLM

# ─── LiteLLM providers → Native alternatives ────────────────────

# Groq → OpenAI or Anthropic
# llm = LLM(model="groq/llama-3.1-70b")
llm = LLM(model="openai/gpt-4o-mini")           # Fast & affordable
llm = LLM(model="anthropic/claude-haiku-3-5")    # Fast & affordable

# Together AI → OpenAI or Gemini
# llm = LLM(model="together_ai/meta-llama/Meta-Llama-3.1-70B")
llm = LLM(model="openai/gpt-4o")                 # High quality
llm = LLM(model="gemini/gemini-2.0-flash")       # Fast & capable

# Mistral → Anthropic or OpenAI
# llm = LLM(model="mistral/mistral-large-latest")
llm = LLM(model="anthropic/claude-sonnet-4-20250514")  # High quality

# Ollama → OpenAI-compatible (keep using local models)
# llm = LLM(model="ollama/llama3")
llm = LLM(
    model="llama3",
    custom_openai=True,
    base_url="http://localhost:11434/v1",
    api_key="ollama"
)

FAQ

Do I lose any functionality by removing LiteLLM?

No, if you use one of the five natively supported providers (OpenAI, Anthropic, Gemini, Azure, Bedrock). These native integrations support all CrewAI features including streaming, tool calling, structured output, and more. You only lose access to providers that are exclusively available through LiteLLM (like Groq, Together AI, Mistral as first-class providers).

Can I use multiple native providers at the same time?

Yes. Install multiple extras and use different providers for different agents:

uv add "crewai[openai,anthropic,gemini]"

researcher = Agent(llm="openai/gpt-4o", ...)
writer = Agent(llm="anthropic/claude-sonnet-4-20250514", ...)

Is LiteLLM safe to use now?

Regardless of quarantine status, reducing your dependency surface is good security practice. If you only need providers that CrewAI supports natively, there’s no reason to keep LiteLLM installed.

What about environment variables like OPENAI_API_KEY?

Native providers use the same environment variables you’re already familiar with. No changes needed for OPENAI_API_KEY, ANTHROPIC_API_KEY, GEMINI_API_KEY, etc.

How do I connect to Groq, Together AI, or other OpenAI-compatible providers without LiteLLM?

Most of these providers expose an OpenAI-compatible API. Use custom_openai=True with their base URL and API key — see Custom OpenAI-Compatible Endpoints. For example, Groq: LLM(model="llama-3.1-70b-versatile", custom_openai=True, base_url="https://api.groq.com/openai/v1", api_key="..."). The model ID is passed through untouched, so use whatever ID the provider expects.

LLM Connections — Full guide to connecting CrewAI with any LLM
LLM Concepts — Understanding LLMs in CrewAI
LLM Selection Guide — Choosing the right model for your use case

Get Started

Guides

Core Concepts

MCP Integration

Tools

Observability

Learn

Telemetry

Using CrewAI Without LiteLLM

Overview

Why Remove LiteLLM?

Native Providers (No LiteLLM Required)

OpenAI

Anthropic

Google Gemini

Azure OpenAI

AWS Bedrock

How to Check If You’re Using LiteLLM

Check your model strings

Check if LiteLLM is installed

Check your dependencies

Migration Guide

Step 1: Identify your current provider

Step 2: Switch to a native provider

Step 3: Keep Ollama without LiteLLM

Step 4: Update your YAML configs

Step 5: Remove LiteLLM

Step 6: Verify

Custom OpenAI-Compatible Endpoints

How it works

Connect to common servers

Quick Reference: Model String Mapping

FAQ

​Overview

​Why Remove LiteLLM?

​Native Providers (No LiteLLM Required)

OpenAI

Anthropic

Google Gemini

Azure OpenAI

AWS Bedrock

​How to Check If You’re Using LiteLLM

​Check your model strings

​Check if LiteLLM is installed

​Check your dependencies

​Migration Guide

​Step 1: Identify your current provider

​Step 2: Switch to a native provider

​Step 3: Keep Ollama without LiteLLM

​Step 4: Update your YAML configs

​Step 5: Remove LiteLLM

​Step 6: Verify

​Custom OpenAI-Compatible Endpoints

​How it works

​Connect to common servers

​Quick Reference: Model String Mapping

​FAQ

​Related Resources

Overview

Why Remove LiteLLM?

Native Providers (No LiteLLM Required)

How to Check If You’re Using LiteLLM

Check your model strings

Check if LiteLLM is installed

Check your dependencies

Migration Guide

Step 1: Identify your current provider

Step 2: Switch to a native provider

Step 3: Keep Ollama without LiteLLM

Step 4: Update your YAML configs

Step 5: Remove LiteLLM

Step 6: Verify

Custom OpenAI-Compatible Endpoints

How it works

Connect to common servers

Quick Reference: Model String Mapping

FAQ

Related Resources