Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
GPT-Realtime-2.1 is an OpenAI realtime model designed for advanced voice-agent and speech-to-speech AI applications. It improves on GPT-Realtime-2 with stronger alphanumeric recognition, better silence and noise handling, and more natural interruption behavior. The model supports text, audio, and image inputs, while producing text and audio outputs for interactive realtime experiences. Developers can use GPT-Realtime-2.1 across endpoints such as Chat Completions, Responses, Realtime, realtime translation, realtime transcription sessions, and related OpenAI API workflows. The model supports function calling, configurable reasoning effort, instruction following, and reasoning token support for complex voice-agent tasks. Its 128,000-token context window and 32,000-token maximum output make it suitable for longer conversations and more detailed realtime workflows. GPT-Realtime-2.1 does not support video, structured outputs, fine-tuning, or predicted outputs according to OpenAI’s current documentation. Pricing starts at $4 per 1 million text input tokens and $24 per 1 million text output tokens, with separate pricing for audio and image tokens. By combining realtime audio interaction, reasoning, tool use, and multimodal input, GPT-Realtime-2.1 helps developers build responsive AI agents for support, sales, operations, translation, transcription, and interactive voice applications.
Description
Mercury 2 represents a groundbreaking advancement in reasoning models, specifically designed for real-time voice interaction as it can quickly answer phone calls. Unlike traditional autoregressive models that leave callers in silence while generating responses one token at a time, Mercury 2 employs a diffusion large language model architecture capable of producing over 1000 tokens per second with standard NVIDIA GPUs. This remarkable speed allows it to complete a full reasoning process and begin speaking within a timeframe that aligns with natural conversational flow, effectively shortening the typical wait time from several seconds to approximately 300 milliseconds. The operational mechanism of Mercury models involves transforming clear text into noise, after which a conventional Transformer is trained to reverse this transformation and predict the original text across all positions at once. By utilizing a denoising approach that engages multiple tokens simultaneously, generation becomes more efficient, enabling speeds akin to custom silicon on NVIDIA H100s while improving responsiveness in voice applications. As a result, Mercury 2 not only enhances user experience but also sets a new standard for interactive voice technologies.
API Access
Has API
API Access
Has API
Integrations
OpenAI
Cerebras
GPT-4.1
Groq
Inception Labs
LiveKit
Pipecat
Retell AI
Vapi AI
gpt-realtime
Integrations
OpenAI
Cerebras
GPT-4.1
Groq
Inception Labs
LiveKit
Pipecat
Retell AI
Vapi AI
gpt-realtime
Pricing Details
$0.40 per cached input
Free Trial
Free Version
Pricing Details
No price information available.
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
OpenAI
Founded
2015
Country
United States
Website
developers.openai.com/api/docs/models/gpt-realtime-2.1
Vendor Details
Company Name
Inception
Country
United States
Website
www.inceptionlabs.ai/blog/mercury-2-the-first-reasoning-model-fast-enough-to-pick-up-the-phone