Skip to main content

OpenAI LLM models

Reference for OpenAI models served via LiveKit Inference.

Overview

LiveKit Inference includes support for the following OpenAI models. Pricing information for each model and provider is available on the pricing page.

Model nameModel IDProviders
GPT-4oopenai/gpt-4o
azure
GPT-4o miniopenai/gpt-4o-mini
azure
GPT-4.1openai/gpt-4.1
azure
GPT-4.1 miniopenai/gpt-4.1-mini
azure
GPT-4.1 nanoopenai/gpt-4.1-nano
azure
GPT-5openai/gpt-5
azure
GPT-5 miniopenai/gpt-5-mini
azure
GPT-5 nanoopenai/gpt-5-nano
azure
GPT OSS 120Bopenai/gpt-oss-120b
basetengroq(Cerebras coming soon)

Usage

To request a model be served through the OpenAI Platform and customize additional parameters, use the LLM class from the inference module:

from livekit.agents import AgentSession, inference
session = AgentSession(
llm=inference.LLM(
model="openai/gpt-5-mini",
provider="azure",
extra_kwargs={
"reasoning_effort": "low"
}
),
# ... tts, stt, vad, turn_detection, etc.
)
import { AgentSession, inference } from '@livekit/agents';
session = new AgentSession({
llm: new inference.LLM({
model: "openai/gpt-5-mini",
provider: "openai",
extraKwargs: {
reasoning_effort: "low"
}
}),
// ... tts, stt, vad, turn_detection, etc.
});

Parameters

This section describes the most commonly used parameters. For a complete list of all available parameters, see the plugin reference links in the Additional resources section.

modelstringRequired

The model to use for the LLM. Must be a model from OpenAI.

providerstringRequired

The provider to use for the LLM. Must be openai to use OpenAI models and other parameters.

extra_kwargsdictOptional

Additional parameters to pass to the provider's Chat Completions API, such as reasoning_effort or max_completion_tokens.

Additional resources

The following links provide more information about OpenAI in LiveKit Inference.