from litellm import completion

response = completion(
 model="claude-sonnet-4-5-20250929",
 messages=[{"role":"user","content":"What is the capital of France?"}],
 response_format={
"type":"json_schema",
"json_schema":{
"name":"capital_response",
"strict":True,
"schema":{
"type":"object",
"properties":{
"country":{"type":"string"},
"capital":{"type":"string"}
},
"required":["country","capital"],
"additionalProperties":False
}
}
}
)

print(response.choices[0].message.content)
# Output: {"country": "France", "capital": "Paris"}

model_list:
-model_name: claude-sonnet-4-5
litellm_params:
model: anthropic/claude-sonnet-4-5-20250929
api_key: os.environ/ANTHROPIC_API_KEY

litellm --config /path/to/config.yaml

curl http://0.0.0.0:4000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $LITELLM_KEY" \
 -d '{
 "model": "claude-sonnet-4-5",
 "messages": [{"role": "user", "content": "What is the capital of France?"}],
 "response_format": {
 "type": "json_schema",
 "json_schema": {
 "name": "capital_response",
 "strict": true,
 "schema": {
 "type": "object",
 "properties": {
 "country": {"type": "string"},
 "capital": {"type": "string"}
 },
 "required": ["country", "capital"],
 "additionalProperties": false
 }
 }
 }
 }'

model_list:
-model_name: claude-4### RECEIVED MODEL NAME ###
litellm_params:# all params accepted by litellm.completion() - https://docs.litellm.ai/docs/completion/input
model: claude-opus-4-20250514### MODEL NAME sent to `litellm.completion()` ###
api_key:"os.environ/ANTHROPIC_API_KEY"# does os.getenv("ANTHROPIC_API_KEY")

litellm --config /path/to/config.yaml

ANTHROPIC_API_KEY=sk-ant****

model_list:
-model_name:"*"
litellm_params:
model:"*"

litellm --config /path/to/config.yaml

curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
 "model": "anthropic/claude-3-haiku-20240307",
 "messages": [
 {
 "role": "user",
 "content": "what llm are you"
 }
 ]
 }
'

$ litellm --model claude-opus-4-20250514

# Server running on http://0.0.0.0:4000

curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
 "model": "claude-3",
 "messages": [
 {
 "role": "user",
 "content": "what llm are you"
 }
 ]
 }
'

import openai
client = openai.OpenAI(
 api_key="anything",
 base_url="http://0.0.0.0:4000"
)

# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="claude-3", messages =[
{
"role":"user",
"content":"this is a test request, write a short poem"
}
])

print(response)

from langchain.chat_models import ChatOpenAI
from langchain.prompts.chat import(
 ChatPromptTemplate,
 HumanMessagePromptTemplate,
 SystemMessagePromptTemplate,
)
from langchain.schema import HumanMessage, SystemMessage

chat = ChatOpenAI(
 openai_api_base="http://0.0.0.0:4000",# set openai_api_base to the LiteLLM Proxy
 model ="claude-3",
 temperature=0.1
)

messages =[
 SystemMessage(
 content="You are a helpful assistant that im using to make a test request to."
),
 HumanMessage(
 content="test from litellm. tell me why it's amazing in 1 sentence"
),
]
response = chat(messages)

print(response)

response =await litellm.acompletion(
 model="anthropic/claude-3-5-sonnet-20240620",
 messages=[
{
"role":"system",
"content":[
{
"type":"text",
"text":"You are an AI assistant tasked with analyzing legal documents.",
},
{
"type":"text",
"text":"Here is the full text of a complex legal agreement",
"cache_control":{"type":"ephemeral"},
},
],
},
{
"role":"user",
"content":"what are the key terms and conditions in this agreement?",
},
]
)

LiteLLM Proxy is OpenAI compatible

This is an example using the OpenAI Python SDK sending a request to LiteLLM Proxy

Assuming you have a model=anthropic/claude-3-5-sonnet-20240620 on the litellm proxy config.yaml

import openai
client = openai.AsyncOpenAI(
 api_key="anything",# litellm proxy api key
 base_url="http://0.0.0.0:4000"# litellm proxy base url
)


response =await client.chat.completions.create(
 model="anthropic/claude-3-5-sonnet-20240620",
 messages=[
{
"role":"system",
"content":[
{
"type":"text",
"text":"You are an AI assistant tasked with analyzing legal documents.",
},
{
"type":"text",
"text":"Here is the full text of a complex legal agreement",
"cache_control":{"type":"ephemeral"},
},
],
},
{
"role":"user",
"content":"what are the key terms and conditions in this agreement?",
},
]
)

import litellm

response =await litellm.acompletion(
 model="anthropic/claude-3-5-sonnet-20240620",
 messages =[{"role":"user","content":"What's the weather like in Boston today?"}]
 tools =[
{
"type":"function",
"function":{
"name":"get_current_weather",
"description":"Get the current weather in a given location",
"parameters":{
"type":"object",
"properties":{
"location":{
"type":"string",
"description":"The city and state, e.g. San Francisco, CA",
},
"unit":{"type":"string","enum":["celsius","fahrenheit"]},
},
"required":["location"],
},
"cache_control":{"type":"ephemeral"}
},
}
]
)

LiteLLM Proxy is OpenAI compatible

This is an example using the OpenAI Python SDK sending a request to LiteLLM Proxy

Assuming you have a model=anthropic/claude-3-5-sonnet-20240620 on the litellm proxy config.yaml

import openai
client = openai.AsyncOpenAI(
 api_key="anything",# litellm proxy api key
 base_url="http://0.0.0.0:4000"# litellm proxy base url
)

response =await client.chat.completions.create(
 model="anthropic/claude-3-5-sonnet-20240620",
 messages =[{"role":"user","content":"What's the weather like in Boston today?"}]
 tools =[
{
"type":"function",
"function":{
"name":"get_current_weather",
"description":"Get the current weather in a given location",
"parameters":{
"type":"object",
"properties":{
"location":{
"type":"string",
"description":"The city and state, e.g. San Francisco, CA",
},
"unit":{"type":"string","enum":["celsius","fahrenheit"]},
},
"required":["location"],
},
"cache_control":{"type":"ephemeral"}
},
}
]
)

import litellm

response =await litellm.acompletion(
 model="anthropic/claude-3-5-sonnet-20240620",
 messages=[
# System Message
{
"role":"system",
"content":[
{
"type":"text",
"text":"Here is the full text of a complex legal agreement"
*400,
"cache_control":{"type":"ephemeral"},
}
],
},
# marked for caching with the cache_control parameter, so that this checkpoint can read from the previous cache.
{
"role":"user",
"content":[
{
"type":"text",
"text":"What are the key terms and conditions in this agreement?",
"cache_control":{"type":"ephemeral"},
}
],
},
{
"role":"assistant",
"content":"Certainly! the key terms and conditions are the following: the contract is 1 year long for $10/mo",
},
# The final turn is marked with cache-control, for continuing in followups.
{
"role":"user",
"content":[
{
"type":"text",
"text":"What are the key terms and conditions in this agreement?",
"cache_control":{"type":"ephemeral"},
}
],
},
]
)

LiteLLM Proxy is OpenAI compatible

This is an example using the OpenAI Python SDK sending a request to LiteLLM Proxy

Assuming you have a model=anthropic/claude-3-5-sonnet-20240620 on the litellm proxy config.yaml

import openai
client = openai.AsyncOpenAI(
 api_key="anything",# litellm proxy api key
 base_url="http://0.0.0.0:4000"# litellm proxy base url
)

response =await client.chat.completions.create(
 model="anthropic/claude-3-5-sonnet-20240620",
 messages=[
# System Message
{
"role":"system",
"content":[
{
"type":"text",
"text":"Here is the full text of a complex legal agreement"
*400,
"cache_control":{"type":"ephemeral"},
}
],
},
# marked for caching with the cache_control parameter, so that this checkpoint can read from the previous cache.
{
"role":"user",
"content":[
{
"type":"text",
"text":"What are the key terms and conditions in this agreement?",
"cache_control":{"type":"ephemeral"},
}
],
},
{
"role":"assistant",
"content":"Certainly! the key terms and conditions are the following: the contract is 1 year long for $10/mo",
},
# The final turn is marked with cache-control, for continuing in followups.
{
"role":"user",
"content":[
{
"type":"text",
"text":"What are the key terms and conditions in this agreement?",
"cache_control":{"type":"ephemeral"},
}
],
},
]
)

from litellm import completion

response = completion(
 model="anthropic/claude-3-opus-20240229",
 messages=messages,
 tools=tools,
 tool_choice="none",
)

model_list:
-model_name: anthropic-claude-model
litellm_params:
model: anthropic/claude-3-opus-20240229
api_key: os.environ/ANTHROPIC_API_KEY

litellm --config /path/to/config.yaml

curl http://0.0.0.0:4000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer anything" \
 -d '{
 "model": "anthropic-claude-model",
 "messages": [{"role": "user", "content": "Who won the World Cup in 2022?"}],
 "tools": [{"type": "mcp", "server_label": "deepwiki", "server_url": "https://mcp.deepwiki.com/mcp", "require_approval": "never"}],
 "tool_choice": "none"
 }'

model_list:
-model_name: claude-4-sonnet
litellm_params:
model: anthropic/claude-sonnet-4-20250514
api_key: os.environ/ANTHROPIC_API_KEY

litellm --config /path/to/config.yaml

from litellm import completion

tools =[
{
"type":"computer_20241022",
"function":{
"name":"computer",
"parameters":{
"display_height_px":100,
"display_width_px":100,
"display_number":1,
},
},
}
]
model ="claude-3-5-sonnet-20241022"
messages =[{"role":"user","content":"Save a picture of a cat to my desktop."}]

resp = completion(
 model=model,
 messages=messages,
 tools=tools,
# headers={"anthropic-beta": "computer-use-2024-10-22"},
)

print(resp)

Live from v1.70.1+

The Anthropic Memory tool is currently in beta.

from litellm import completion

resp = completion(
 model="anthropic/claude-3-7-sonnet-20250219",
 messages=[{"role":"user","content":"What is the capital of France?"}],
 reasoning_effort="low",
)

-model_name: claude-3-7-sonnet-20250219
litellm_params:
model: anthropic/claude-3-7-sonnet-20250219
api_key: os.environ/ANTHROPIC_API_KEY

litellm --config /path/to/config.yaml

curl http://0.0.0.0:4000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer <YOUR-LITELLM-KEY>" \
 -d '{
 "model": "claude-3-7-sonnet-20250219",
 "messages": [{"role": "user", "content": "What is the capital of France?"}],
 "reasoning_effort": "low"
 }'

response = litellm.completion(
 model="anthropic/claude-3-7-sonnet-20250219",
 messages=[{"role":"user","content":"What is the capital of France?"}],
 thinking={"type":"enabled","budget_tokens":1024},
)

curl http://0.0.0.0:4000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $LITELLM_KEY" \
 -d '{
 "model": "anthropic/claude-3-7-sonnet-20250219",
 "messages": [{"role": "user", "content": "What is the capital of France?"}],
 "thinking": {"type": "enabled", "budget_tokens": 1024}
 }'

response = litellm.completion(
 model="anthropic/claude-opus-4-6",
 messages=[{"role":"user","content":"What is the optimal strategy for solving this problem?"}],
 thinking={"type":"adaptive"},
)

curl http://0.0.0.0:4000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $LITELLM_KEY" \
 -d '{
 "model": "anthropic/claude-opus-4-6",
 "messages": [{"role": "user", "content": "What is the optimal strategy for solving this problem?"}],
 "thinking": {"type": "adaptive"}
 }'

response = litellm.completion(
 model="anthropic/claude-opus-4-6",
 messages=[{"role":"user","content":"What is the capital of France?"}],
 thinking={"type":"enabled","budget_tokens":5000},
)

curl http://0.0.0.0:4000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer $LITELLM_KEY" \
 -d '{
 "model": "anthropic/claude-opus-4-6",
 "messages": [{"role": "user", "content": "What is the capital of France?"}],
 "thinking": {"type": "enabled", "budget_tokens": 5000}
 }'

from litellm import completion, supports_pdf_input
import base64
import requests

# URL of the file
url ="https://storage.googleapis.com/cloud-samples-data/generative-ai/pdf/2403.05530.pdf"

# Download the file
response = requests.get(url)
file_data = response.content

encoded_file = base64.b64encode(file_data).decode("utf-8")

## check if model supports pdf input - (2024/11/11) only claude-3-5-haiku-20241022 supports it
supports_pdf_input("anthropic/claude-3-5-haiku-20241022")# True

response = completion(
 model="anthropic/claude-3-5-haiku-20241022",
 messages=[
{
"role":"user",
"content":[
{"type":"text","text":"You are a very professional document summarization specialist. Please summarize the given document."},
{
"type":"file",
"file":{
"file_data":f"data:application/pdf;base64,{encoded_file}",# 👈 PDF
}
},
],
}
],
 max_tokens=300,
)

print(response.choices[0])

-model_name: claude-3-5-haiku-20241022
litellm_params:
model: anthropic/claude-3-5-haiku-20241022
api_key: os.environ/ANTHROPIC_API_KEY

litellm --config /path/to/config.yaml

curl http://0.0.0.0:4000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer <YOUR-LITELLM-KEY>" \
 -d '{
 "model": "claude-3-5-haiku-20241022",
 "messages": [
 {
 "role": "user",
 "content": [
 {
 "type": "text",
 "text": "You are a very professional document summarization specialist. Please summarize the given document"
 },
 {
 "type": "file",
 "file": {
 "file_data": f"data:application/pdf;base64,{encoded_file}", # 👈 PDF
 }
 }
 }
 ]
 }
 ],
 "max_tokens": 300
 }'

from litellm import completion

resp = completion(
 model="claude-3-5-sonnet-20241022",
 messages=[
{
"role":"user",
"content":[
{
"type":"document",
"source":{
"type":"text",
"media_type":"text/plain",
"data":"The grass is green. The sky is blue.",
},
"title":"My Document",
"context":"This is a trustworthy document.",
"citations":{"enabled":True},
},
{
"type":"text",
"text":"What color is the grass and sky?",
},
],
}
],
)

citations = resp.choices[0].message.provider_specific_fields["citations"]

assert citations isnotNone

model_list:
-model_name: anthropic-claude
litellm_params:
model: anthropic/claude-3-5-sonnet-20241022
api_key: os.environ/ANTHROPIC_API_KEY

litellm --config /path/to/config.yaml

# RUNNING on http://0.0.0.0:4000

curl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
 "model": "anthropic-claude",
 "messages": [
 {
 "role": "user",
 "content": [
 {
 "type": "document",
 "source": {
 "type": "text",
 "media_type": "text/plain",
 "data": "The grass is green. The sky is blue.",
 },
 "title": "My Document",
 "context": "This is a trustworthy document.",
 "citations": {"enabled": True},
 },
 {
 "type": "text",
 "text": "What color is the grass and sky?",
 },
 ],
 }
 ]
}'

response = completion(
 model="claude-3-5-sonnet-20240620",
 messages=messages,
 user="user_123",
)

model_list:
-model_name: claude-3-5-sonnet-20240620
litellm_params:
model: anthropic/claude-3-5-sonnet-20240620
api_key: os.environ/ANTHROPIC_API_KEY

litellm --config /path/to/config.yaml

curl http://0.0.0.0:4000/v1/chat/completions \
 -H "Content-Type: application/json" \
 -H "Authorization: Bearer <YOUR-LITELLM-KEY>" \
 -d '{
 "model": "claude-3-5-sonnet-20240620",
 "messages": [{"role": "user", "content": "What is Anthropic?"}],
 "user": "user_123"
 }'

response = completion(
 model="claude-sonnet-4-5-20250929",
 messages=messages,
 tools=[
{
"type":"code_execution_20250825",
"name":"code_execution"
}
],
 container={
"skills":[
{
"type":"anthropic",
"skill_id":"pptx",
"version":"latest"
}
]
}
)

model_list:
-model_name: claude-sonnet-4-5-20250929
litellm_params:
model: anthropic/claude-sonnet-4-5-20250929
api_key: os.environ/ANTHROPIC_API_KEY

litellm --config /path/to/config.yaml

curl --location 'http://localhost:4000/chat/completions' \
--header 'Content-Type: application/json' \
--header 'Authorization: Bearer <YOUR-LITELLM-KEY>' \
--data '{
 "model": "claude-sonnet-4-5-20250929",
 "messages": [
 {
 "role": "user",
 "content": "Hi"
 }
 ],
 "tools": [
 {
 "type": "code_execution_20250825",
 "name": "code_execution"
 }
 ],
 "container": {
 "skills": [
 {
 "type": "anthropic",
 "skill_id": "pptx",
 "version": "latest"
 }
 ]
 }
}'