Data as of October 25, 2026 · How the score is built
GPT-Live-1
Decision readingGPT-Live-1 is tracked, but not publicly ranked yet. Published speech or voice results from AudioAgentBench appear below. They do not produce a weighted text-model score.
Released Sep 10, 2026 — see all recent releases
Voice benchmark evidence
AudioAgentBench is an owner-defined voice evaluation. Its result stays separate from BenchLM's weighted text-model ranking.
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Base entry
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- gpt-live-1OpenAI GPT-Live 1 model documentation
- Context window
- Not publishedOpenAI GPT-Live 1 model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- July 31, 2025OpenAI GPT-Live 1 model documentation
- Input modalities
- audio, textOpenAI GPT-Live 1 model documentation
- Output modalities
- audio, textOpenAI GPT-Live 1 model documentation
- Parameters
- Not disclosed by the provider
- Availability
- OpenAI APIOpenAI: GPT-Live-1 in the API
- Cloud regions
- Not tracked yet
- Lifecycle
- activeOpenAI: GPT-Live-1 in the API
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordOpenAI model documentation
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
We track GPT-Live-1, but no weighted text-model benchmark result is published on the site yet. This page shows the metadata and separate protocol evidence we can verify now; a BenchLM score will appear only if compatible public evaluations land.
GPT-Live-1 is a proprietary model. No explicit reasoning mode is documented in this profile.
Available in the OpenAI API as gpt-live-1 since September 10, 2026 through v1/live/sessions over WebRTC, WebSockets, and SIP telephony, after first shipping in ChatGPT Voice. Audio and text in, audio and text out; reasoning and tool calls are delegated to a Responses model or a client-side agent and billed separately.
GPT-Live-1 is a display-only full-duplex voice model that listens and speaks at the same time and delegates reasoning and tool use to a backend model. OpenAI’s API launch evaluation remains separate from BenchLM’s weighted text-model ranking.
Speech or voice evidence appears above; text-model benchmark coverage remains empty.
Last updated October 25, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does GPT-Live-1 perform overall in AI benchmarks?
GPT-Live-1 has published speech or voice results in AudioAgentBench. Those results remain separate from the weighted text-model ranking, so this profile does not assign a BenchLM score or overall rank. Use the linked evaluation's metric and run conditions to compare speech systems.
Does GPT-Live-1 have full benchmark coverage on BenchLM?
No. GPT-Live-1's speech or voice results appear in AudioAgentBench, but it has no published text-model benchmark rows. The voice evaluation does not fill the text-model coverage slots or produce an overall rank. Missing text coverage is not treated as a zero score.
What is the context window size of GPT-Live-1?
GPT-Live-1's provider has not published a context-window limit for this exact model. The profile leaves the value unavailable instead of borrowing a number from an earlier family member or a third-party route. Maximum output length is tracked separately when the provider documents it.