curl --location 'http://0.0.0.0:4000/chat/completions' \
--header 'Content-Type: application/json' \
--data ' {
 "model": "gpt-3.5-turbo",
 "messages": [
 {
 "role": "user",
 "content": "what llm are you"
 }
 ]
 }
'

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

response = client.chat.completions.create(model="gpt-3.5-turbo", 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 ="gpt-3.5-turbo",
 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)

import litellm

litellm.completion(model="azure/my-o3-deployment", messages=[{"role":"user","content":"Hello, world!"}])# 👈 Note: 'o3' in the deployment name

model_list:
-model_name: o3-mini
litellm_params:
model: azure/o3-model
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEY

import litellm

litellm.completion(model="azure/o_series/my-random-deployment-name", messages=[{"role":"user","content":"Hello, world!"}])# 👈 Note: 'o_series/' in the deployment name

model_list:
-model_name: o3-mini
litellm_params:
model: azure/o_series/my-random-deployment-name
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEY

import litellm

response = litellm.completion(
 model="azure/gpt5_series/my-gpt-5-deployment",
 messages=[{"role":"user","content":"Hello, world!"}]
)

model_list:
-model_name: gpt-5
litellm_params:
model: azure/gpt5_series/my-gpt-5-deployment
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEY

import litellm

# Deployment name contains 'gpt-5' - automatically inferred
response = litellm.completion(
 model="azure/my-gpt-5-deployment",
 messages=[{"role":"user","content":"Hello, world!"}]
)

model_list:
-model_name: gpt-5-mini
litellm_params:
model: azure/my-gpt-5-deployment # deployment name contains 'gpt-5'
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEY

from litellm import completion
import os

os.environ["AZURE_API_KEY"]=""
os.environ["AZURE_API_BASE"]=""
os.environ["AZURE_API_VERSION"]=""

response = completion(
 model="azure/azure-openai-4o-audio",
 messages=[
{
"role":"user",
"content":"I want to try out speech to speech"
}
],
 modalities=["text","audio"],
 audio={"voice":"alloy","format":"wav"}
)

print(response)

model_list:
-model_name: azure-openai-4o-audio
litellm_params:
model: azure/azure-openai-4o-audio
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEY
api_version: os.environ/AZURE_API_VERSION

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

curl http://localhost:4000/v1/chat/completions \
 -H "Authorization: Bearer $LITELLM_API_KEY" \
 -H "Content-Type: application/json" \
 -d '{
 "model": "azure-openai-4o-audio",
 "messages": [{"role": "user", "content": "I want to try out speech to speech"}],
 "modalities": ["text","audio"],
 "audio": {"voice": "alloy", "format": "wav"}
 }'

response = litellm.completion(
 model ="azure/<your deployment name>",# model = azure/<your deployment name> 
 api_base ="",# azure api base
 api_version ="",# azure api version
 azure_ad_token="",# your accessToken from step 3 
 messages =[{"role":"user","content":"good morning"}],
)

model_list:
-model_name: gpt-3.5-turbo
litellm_params:
model: azure/chatgpt-v-2
api_base: https://openai-gpt-4-test-v-1.openai.azure.com/
api_version:"2023-05-15"
azure_ad_token: os.environ/AZURE_AD_TOKEN

from litellm import completion
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

# DefaultAzureCredential automatically discovers credentials from:
# - Environment variables (AZURE_CLIENT_ID, AZURE_CLIENT_SECRET, AZURE_TENANT_ID)
# - Managed Identity (AKS, Azure VMs, etc.)
# - Azure CLI credentials
# - And other Azure identity sources
token_provider = get_bearer_token_provider(DefaultAzureCredential(),"https://cognitiveservices.azure.com/.default")

response = completion(
 model ="azure/<your deployment name>",# model = azure/<your deployment name> 
 api_base ="",# azure api base
 api_version ="",# azure api version
 azure_ad_token_provider=token_provider,
 messages =[{"role":"user","content":"good morning"}],
)

import litellm

# Enable automatic fallback to DefaultAzureCredential
litellm.enable_azure_ad_token_refresh =True

response = litellm.completion(
 model ="azure/<your deployment name>",
 api_base ="",
 api_version ="",
 messages =[{"role":"user","content":"good morning"}],
)

export AZURE_TENANT_ID=""
export AZURE_CLIENT_ID=""
export AZURE_CLIENT_SECRET=""

model_list:
-model_name: gpt-3.5-turbo
litellm_params:
model: azure/your-deployment-name
api_base: https://openai-gpt-4-test-v-1.openai.azure.com/

litellm_settings:
enable_azure_ad_token_refresh:true# 👈 KEY CHANGE

model_list:
-model_name: gpt-3.5-turbo
litellm_params:
model: azure/your-deployment-name
api_base: https://openai-gpt-4-test-v-1.openai.azure.com/

litellm_settings:
enable_azure_ad_token_refresh:true# 👈 KEY CHANGE

model_list:
-model_name: gpt-3.5-turbo
litellm_params:
model: azure/your-deployment-name
api_base: https://openai-gpt-4-test-v-1.openai.azure.com/

litellm_settings:
enable_azure_ad_token_refresh:true# 👈 KEY CHANGE

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

{"custom_id":"task-0","method":"POST","url":"/chat/completions","body":{"model":"REPLACE-WITH-MODEL-DEPLOYMENT-NAME","messages":[{"role":"system","content":"You are an AI assistant that helps people find information."},{"role":"user","content":"When was Microsoft founded?"}]}}
{"custom_id":"task-1","method":"POST","url":"/chat/completions","body":{"model":"REPLACE-WITH-MODEL-DEPLOYMENT-NAME","messages":[{"role":"system","content":"You are an AI assistant that helps people find information."},{"role":"user","content":"When was the first XBOX released?"}]}}
{"custom_id":"task-2","method":"POST","url":"/chat/completions","body":{"model":"REPLACE-WITH-MODEL-DEPLOYMENT-NAME","messages":[{"role":"system","content":"You are an AI assistant that helps people find information."},{"role":"user","content":"What is Altair Basic?"}]}}

from litellm
import os 

os.environ["AZURE_API_KEY"]=""
os.environ["AZURE_API_BASE"]=""

file_name ="azure_batch_completions.jsonl"
_current_dir = os.path.dirname(os.path.abspath(__file__))
file_path = os.path.join(_current_dir, file_name)
file_obj =await litellm.acreate_file(
file=open(file_path,"rb"),
 purpose="batch",
 custom_llm_provider="azure",
)
print("Response from creating file=", file_obj)

create_batch_response =await litellm.acreate_batch(
 completion_window="24h",
 endpoint="/v1/chat/completions",
 input_file_id=batch_input_file_id,
 custom_llm_provider="azure",
 metadata={"key1":"value1","key2":"value2"},
)

print("response from litellm.create_batch=", create_batch_response)

retrieved_batch =await litellm.aretrieve_batch(
 batch_id=create_batch_response.id,
 custom_llm_provider="azure"
)
print("retrieved batch=", retrieved_batch)

# Get file content
file_content =await litellm.afile_content(
 file_id=batch_input_file_id,
 custom_llm_provider="azure"
)
print("file content = ", file_content)

list_batches_response = litellm.list_batches(
 custom_llm_provider="azure",
 limit=2
)
print("list_batches_response=", list_batches_response)

# set Azure env variables
import os
import litellm
import json

os.environ['AZURE_API_KEY']=""# litellm reads AZURE_API_KEY from .env and sends the request
os.environ['AZURE_API_BASE']="https://openai-gpt-4-test-v-1.openai.azure.com/"
os.environ['AZURE_API_VERSION']="2023-07-01-preview"

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"],
},
},
}
]

response = litellm.completion(
 model="azure/chatgpt-functioncalling",# model = azure/<your-azure-deployment-name>
 messages=[{"role":"user","content":"What's the weather like in San Francisco, Tokyo, and Paris?"}],
 tools=tools,
 tool_choice="auto",# auto is default, but we'll be explicit
)
print("\nLLM Response1:\n", response)
response_message = response.choices[0].message
tool_calls = response.choices[0].message.tool_calls
print("\nTool Choice:\n", tool_calls)

model_list:
-model_name: azure-gpt-3.5
litellm_params:
model: azure/chatgpt-functioncalling
api_base: os.environ/AZURE_API_BASE
api_key: os.environ/AZURE_API_KEY
api_version:"2023-07-01-preview"

litellm --config config.yaml

curl -L -X POST 'http://localhost:4000/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer sk-1234' \
-d '{
 "model": "azure-gpt-3.5",
 "messages": [
 {
 "role": "user",
 "content": "Hey, how'\''s it going? Thinking long and hard before replying - what is the meaning of the world and life itself"
 }
 ]
}'