- Organizations
- OpenAI
- GPT-Live-1
GPT-Live-1: Benchmarks, Pricing & Examples
GPT-Live-1 is a language model from OpenAI, released in September 2026.
GPT-Live-1 is OpenAI's full-duplex voice model for real-time conversations, available via the new v1/live/sessions API. It listens and speaks at the same time, reasoning jointly over incoming and outgoing audio to avoid the latency and
GPT-Live-1 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Quality Tracker
GPT-Live-1 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
Try now
Make it with
GPT-Live-1.
GPT-Live-1 latency
GPT-Live-1 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
GPT-Live-1 license
GPT-Live-1 is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of July 2025.
- License
- Proprietary
- Hosted access
- Knowledge cutoff
- July 2025
Proprietary license - usage restrictions apply
GPT-Live-1 resources
Official sources for GPT-Live-1: provider documentation, official launch post.
GPT-Live-1 vs other models
The most-compared alternatives to GPT-Live-1 are MiMo-V2.5-Pro, Qwen3.6 Plus, Ling 3.0 Flash. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like GPT-Live-1
Models ranked just above and below GPT-Live-1 by LLM Stats score.
FAQ
Common questions about GPT-Live-1.