Expanded LLM Support: GPT-5 and Groq gpt-oss-120b for Voice AI Agents

8, Aug 2025

Telnyx is excited to announce expanded LLM support for Voice AI Agents, adding OpenAI’s GPT-5 and Groq’s gpt-oss-120b to your agent’s toolkit. These models open up new possibilities for delivering lifelike, real-time conversations with more choice, flexibility, and cost efficiency.

What’s new

Support for OpenAI GPT-5 with minimal reasoning effort enabled by default for real-time voice suitability.
Support for Groq gpt-oss-120b for high-speed, open-source performance.
Seamless integration with the AI Assistant Builder so you can test instantly.

Key benefits

Lower latency and pricing for GPT-5: Response times stay under real-time thresholds, and aggressively low cached input costs make it ideal for voice agents where most tokens are cached.
Groq’s gpt-oss-120b delivers high-throughput inference with competitive performance.

Voice AI Agents succeed or fail on speed. By optimizing GPT-5 for minimal reasoning effort, we’ve made it viable for real-time interactions without sacrificing conversational quality. And because most voice agent tokens are cached input, GPT-5’s pricing structure offers significant cost advantages. Groq’s gpt-oss-120b brings another competitive option for developers seeking open-source speed and scalability.

Sign up or log in to your Telnyx Mission Control Portal account.
Navigate to the AI Assistants section.
Create a new AI Agent or edit an existing one.
In the “Agent” tab, select your LLM from the dropdown list.
Test your agent directly in the AI Assistant Builder.

Ask AI

Expanded LLM Support: GPT-5 and Groq gpt-oss-120b for Voice AI Agents

8, Aug 2025

What’s new

Key benefits

Why it matters

Getting started