Skip to main content
For details about all available parameters, visit the API reference page.

​
Getting Started with OpenAI SDK

To start using Emby’s Chat Completions API, you’ll need to install the OpenAI SDK and set up your API key with the environment variable EMBY_API_KEY. 
pip install openai

​
Performing a Basic Chat Completion

The simplest way to use the Chat Completions API is to send a list of messages and receive a single response. Messages are provided in chronological order, with each message containing a role (“system”, “user”, or “assistant”) and content. 
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("EMBY_API_KEY"),
    base_url="https://dev.emby.ai/v1"
)

chat_completion = client.chat.completions.create(
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        {
            "role": "user",
            "content": "Explain the importance of fast language models",
        }
    ],

    model="gpt-5"
)

print(chat_completion.choices[0].message.content)

​
Performing a Chat Completion with a Stop Sequence

Stop sequences allow you to control where the model should stop generating. When the model encounters any of the specified stop sequences, it will halt generation at that point. This is useful when you need responses to end at specific points. 
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("EMBY_API_KEY"),
    base_url="https://dev.emby.ai/v1"
)

chat_completion = client.chat.completions.create(
    # Required parameters
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant."
        },
        # Set a user message for the assistant to respond to.
        {
            "role": "user",
            "content": "Count to 10.  Your response must begin with \"1, \".  example: 1, 2, 3, ...",
        }
    ],

    # The language model which will generate the completion.
    model="gpt-5",

    # Optional parameters

    temperature=0.5,
    max_completion_tokens=1024,
    top_p=1,
    stop=", 6",
    stream=False,
)

# Print the completion returned by the LLM.
print(chat_completion.choices[0].message.content)

​
Performing an Async Chat Completion

For applications that need to maintain responsiveness while waiting for completions, you can use the asynchronous client. This lets you make non-blocking API calls using Python’s asyncio framework. 
import asyncio
import os
from openai import AsyncOpenAI


async def main():
    client = AsyncOpenAI(
        api_key=os.environ.get("EMBY_API_KEY"),
        base_url="https://dev.emby.ai/v1"
    )

    chat_completion = await client.chat.completions.create(
        # Required parameters
        messages=[
            {
                "role": "system",
                "content": "You are a helpful assistant."
            },
            # Set a user message for the assistant to respond to.
            {
                "role": "user",
                "content": "Explain the importance of fast language models",
            }
        ],
        model="gpt-5",

        # Optional parameters
        temperature=0.5,
        max_completion_tokens=1024,
        top_p=1,
        stop=None,
        stream=False,
    )

    # Print the completion returned by the LLM.
    print(chat_completion.choices[0].message.content)

asyncio.run(main())

​
Structured Outputs and JSON

Need reliable, type-safe JSON responses that match your exact schema? Emby’s Structured Outputs feature is designed so that model responses strictly conform to your JSON Schema without validation or retry logic. For complete guides on implementing structured outputs with JSON Schema or using JSON Object Mode, see our structured outputs documentation. Key capabilities:
  • JSON Schema enforcement: Responses match your schema exactly
  • Type-safe outputs: No validation or retry logic needed
  • Programmatic refusal detection: Handle safety-based refusals programmatically
  • JSON Object Mode: Basic JSON output with prompt-guided structure