Skip to main content Skills Marketplace Discover and explore AI skills built by the community.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Show prompt details A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/majiayu000/claude-skill-registry --skill litellmThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Download Zip Downloading... More from this repository Related occupations SOC
Based on SOC occupation classification
name litellm description Unified LLM API with LiteLLM. Call 100+ LLM providers with one interface. Use for multi-provider AI, cost optimization, fallbacks, and LLM gateway deployment.
LiteLLM
Expert guidance for unified LLM API access across providers.
Installation
pip install litellm
Quick Start
from litellm import completion
response = completion(
model="gpt-4o" ,
messages=[{"role" : "user" , "content" : "Hello!" }]
)
response = completion(
model="claude-3-5-sonnet-20241022" ,
messages=[{"role" : "user" , "content" : "Hello!" }]
)
response = completion(
model="azure/gpt-4o" ,
messages=[{"role" : "user" , "content" : "Hello!" }],
api_base="https://my-resource.openai.azure.com" ,
api_key="your-key" ,
api_version="2024-02-01"
)
response = completion(
model="ollama/llama3.1" ,
messages=[{"role" : "user" , "content"
"Hello!"
"http://localhost:11434"
Streaming from litellm import completion
response = completion(
model="gpt-4o" ,
messages=[{"role" : "user" , "content" : "Tell me a story" }],
stream=True
)
for chunk in response:
if chunk.choices[0 ].delta.content:
print (chunk.choices[0 ].delta.content, end="" )
Async import asyncio
from litellm import acompletion
async def main ():
response = await acompletion(
model="gpt-4o" ,
messages=[{"role" : "user" , "content" : "Hello!" }]
)
print (response.choices[0 ].message.content)
asyncio.run(main())
Embeddings from litellm import embedding
response = embedding(
model="text-embedding-3-small" ,
input =["Hello world" ]
)
response = embedding(
model="cohere/embed-english-v3.0" ,
input =["Hello world" ]
)
embeddings = response.data[0 ].embedding
Function Calling from litellm import completion
tools = [{
"type" : "function" ,
"function" : {
"name" : "get_weather" ,
"description" : "Get weather for a city" ,
"parameters" : {
"type" : "object" ,
"properties" : {
"city" : {"type" : "string" }
},
"required" : ["city" ]
}
}
}]
response = completion(
model="gpt-4o" ,
messages=[{"role" : "user" , "content" : "What's the weather in Paris?" }],
tools=tools,
tool_choice="auto"
)
if response.choices[0 ].message.tool_calls:
for tool_call in response.choices[0 ].message.tool_calls:
print (f"Function: {tool_call.function.name} " )
print (f"Arguments: {tool_call.function.arguments} " )
Fallbacks & Retries from litellm import completion
import litellm
litellm.set_verbose = True
response = completion(
model="gpt-4o" ,
messages=[{"role" : "user" , "content" : "Hello" }],
fallbacks=["claude-3-5-sonnet-20241022" , "gpt-3.5-turbo" ],
num_retries=3
)
Router (Load Balancing) from litellm import Router
router = Router(
model_list=[
{
"model_name" : "gpt-4" ,
"litellm_params" : {
"model" : "azure/gpt-4-deployment" ,
"api_base" : "https://us-east.openai.azure.com" ,
"api_key" : "key1"
}
},
{
"model_name" : "gpt-4" ,
"litellm_params" : {
"model" : "azure/gpt-4-deployment" ,
"api_base" : "https://us-west.openai.azure.com" ,
"api_key" : "key2"
}
}
],
routing_strategy="least-busy"
)
response = router.completion(
model="gpt-4" ,
messages=[{"role" : "user" , "content" : "Hello" }]
)
Proxy Server
Configuration (config.yaml) model_list:
- model_name: gpt-4
litellm_params:
model: azure/gpt-4
api_base: https://my-resource.openai.azure.com
api_key: os.environ/AZURE_API_KEY
api_
- model_name: claude
litellm_params:
model: claude-3-5-sonnet-20241022
api_key: os.environ/ANTHROPIC_API_KEY
litellm_settings:
drop_params: true
set_verbose: false
general_settings:
master_key: sk-1234
database_url: postgresql://user:pass@localhost/litellm
Run Proxy
litellm --config config.yaml --port 4000
docker run -p 4000:4000 \
-v $(pwd )/config.yaml:/app/config.yaml \
ghcr.io/berriai/litellm:main-latest \
--config /app/config.yaml
Use Proxy from openai import OpenAI
client = OpenAI(
base_url="http://localhost:4000" ,
api_key="sk-1234"
)
response = client.chat.completions.create(
model="gpt-4" ,
messages=[{"role" : "user" , "content" : "Hello" }]
)
Cost Tracking from litellm import completion
import litellm
litellm.success_callback = ["langfuse" ]
response = completion(
model="gpt-4o" ,
messages=[{"role" : "user" , "content" : "Hello" }]
)
print (f"Cost: ${response._hidden_params['response_cost' ]} " )
Budget Management from litellm import BudgetManager
budget = BudgetManager(project_name="my-project" )
budget.create_budget(
total_budget=100 ,
user="user-123" ,
duration="monthly"
)
if budget.get_current_cost("user-123" ) < budget.get_total_budget("user-123" ):
response = completion(model="gpt-4o" , messages=[...])
budget.update_cost(response._hidden_params['response_cost' ], "user-123" )
Model Aliases import litellm
litellm.model_alias_map = {
"fast" : "gpt-3.5-turbo" ,
"smart" : "gpt-4o" ,
"cheap" : "claude-3-haiku-20240307"
}
response = completion(
model="smart" ,
messages=[{"role" : "user" , "content" : "Hello" }]
)
Resources 