Large Language Models (LLM)

LLM inference available through Telnyx for LiveKit voice agents.

Telnyx hosts models with an OpenAI-compatible API. No concurrency limits. Use the standard OpenAI plugin with the .with_telnyx() helper:

from livekit.plugins import openai

llm = openai.LLM.with_telnyx(model="moonshotai/Kimi-K2.5")

Hosted models

These run on Telnyx infrastructure — no external API key needed, just your TELNYX_API_KEY:

Model	Description
moonshotai/Kimi-K2.5	Moonshot AI’s latest
zai-org/GLM-5	Zhipu AI’s latest
MiniMaxAI/MiniMax-M2.5	MiniMax’s latest

Full models list →

Proprietary models (BYOK)

For models like GPT-4o or Claude, Telnyx proxies the request using your own API key. Add your provider key in the Telnyx Portal under Inference settings.

# Proprietary model via BYOK (bring your own key)
llm = openai.LLM.with_telnyx(model="openai/gpt-4o-mini")

How it works

The .with_telnyx() helper points the standard livekit-plugins-openai package at the Telnyx inference endpoint. Same API shape as OpenAI — tool calling, streaming, and function calls all work.