Azure Responses API

Usage

Create a model response

Non-streaming

# Non-streaming response
response = litellm.responses(
    model="azure/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn.",
    max_output_tokens=100,
    api_key=os.getenv("AZURE_RESPONSES_OPENAI_API_KEY"),
    api_base="https://litellm8397336933.openai.azure.com/",
    api_version="2023-03-15-preview",
)

print(response)

Streaming

# Streaming response
response = litellm.responses(
    model="azure/o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn.",
    stream=True,
    api_key=os.getenv("AZURE_RESPONSES_OPENAI_API_KEY"),
    api_base="https://litellm8397336933.openai.azure.com/",
    api_version="2023-03-15-preview",
)

for event in response:
    print(event)

First, add this to your litellm proxy config.yaml:

model_list:
  - model_name: o1-pro
    litellm_params:
      model: azure/o1-pro
      api_key: os.environ/AZURE_RESPONSES_OPENAI_API_KEY
      api_base: https://litellm8397336933.openai.azure.com/
      api_version: 2023-03-15-preview

Start your LiteLLM proxy:

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

# RUNNING on http://0.0.0.0:4000

Then use the OpenAI SDK pointed to your proxy:

Non-streaming

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# Non-streaming response
response = client.responses.create(
    model="o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn."
)

print(response)

Streaming

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# Streaming response
response = client.responses.create(
    model="o1-pro",
    input="Tell me a three sentence bedtime story about a unicorn.",
    stream=True
)

for event in response:
    print(event)

Azure Codex Models

Codex models use Azure's new /v1/preview API which provides ongoing access to the latest features with no need to update api-version each month.

LiteLLM will send your requests to the /v1/preview endpoint when you set api_version="preview".

Non-streaming

# Non-streaming response with Codex models
response = litellm.responses(
    model="azure/codex-mini",
    input="Tell me a three sentence bedtime story about a unicorn.",
    max_output_tokens=100,
    api_key=os.getenv("AZURE_RESPONSES_OPENAI_API_KEY"),
    api_base="https://litellm8397336933.openai.azure.com",
    api_version="preview", # 👈 key difference
)

print(response)

Streaming

# Streaming response with Codex models
response = litellm.responses(
    model="azure/codex-mini",
    input="Tell me a three sentence bedtime story about a unicorn.",
    stream=True,
    api_key=os.getenv("AZURE_RESPONSES_OPENAI_API_KEY"),
    api_base="https://litellm8397336933.openai.azure.com",
    api_version="preview", # 👈 key difference
)

for event in response:
    print(event)

First, add this to your litellm proxy config.yaml:

model_list:
  - model_name: codex-mini
    litellm_params:
      model: azure/codex-mini
      api_key: os.environ/AZURE_RESPONSES_OPENAI_API_KEY
      api_base: https://litellm8397336933.openai.azure.com
      api_version: preview # 👈 key difference

Start your LiteLLM proxy:

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

# RUNNING on http://0.0.0.0:4000

Then use the OpenAI SDK pointed to your proxy:

Non-streaming

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# Non-streaming response
response = client.responses.create(
    model="codex-mini",
    input="Tell me a three sentence bedtime story about a unicorn."
)

print(response)

Streaming

from openai import OpenAI

# Initialize client with your proxy URL
client = OpenAI(
    base_url="http://localhost:4000",  # Your proxy URL
    api_key="your-api-key"             # Your proxy API key
)

# Streaming response
response = client.responses.create(
    model="codex-mini",
    input="Tell me a three sentence bedtime story about a unicorn.",
    stream=True
)

for event in response:
    print(event)

Calling via /chat/completions

You can also call the Azure Responses API via the /chat/completions endpoint.

from litellm import completion

os.environ["AZURE_API_BASE"] = "https://my-azure-endpoint.openai.azure.com/"
os.environ["AZURE_API_VERSION"] = "2023-03-15-preview"
os.environ["AZURE_API_KEY"] = "my-api-key"

response = completion(
    model="azure/responses/my-custom-o1-pro",
    messages=[{"role": "user", "content": "Hello world"}],
)

print(response)

1. Setup config.yaml

model_list:
  - model_name: my-custom-o1-pro
    litellm_params:
      model: azure/responses/my-custom-o1-pro
      api_key: os.environ/AZURE_API_KEY
      api_base: https://my-azure-endpoint.openai.azure.com/
      api_version: 2023-03-15-preview

2. Start LiteLLM proxy

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

# RUNNING on http://0.0.0.0:4000

3. Test it!

curl http://localhost:4000/v1/chat/completions \\
  -X POST \\
  -H "Content-Type: application/json" \\
  -H "Authorization: Bearer $LITELLM_API_KEY" \\
  -d '{
    "model": "my-custom-o1-pro",
    "messages": [{"role": "user", "content": "Hello world"}]
  }'