Primary use stated or inferred cautiously from official documentation.
GPT-Live-1.1
A voice model that listens while speaking. The November 19 update improves pronunciation, accent consistency and transcription in multilingual conversations. It accepts audio and text and returns both in a Live session.
The essential
Maximum input capacity when published by the source.
Documented maximum generation limit.
Verified availability channels.
Primary functional family and verified specialties.
Declared terms for API access, model weights, or self-hosting.
Limits and integration
| API ID | gpt-live-1.1 |
|---|---|
| Model type | Voice and audio · Multimodal |
| Access model | Paid proprietary |
| License | Proprietary |
| Deployment | Hosted API |
| Release | 19 NOV 2026 |
| Knowledge cutoff | Not published |
| Entrance | Audio · Text |
| Exit | Audio · Text |
| Context window | Not published |
| maximum output | Streaming audio and text |
| Reasoning | Not published |
| Published tools | Features |
| Structured Outings | Not published |
| Batch processing | Unavailable |
| Prompt cache | Not published |
| Fine-tuning | Unavailable |
| Verified platforms | OpenAI API |
Natural voice interfaces with interruptions and backend delegation for reasoning and tools.
Uses v1/live/sessions only: this is not the Realtime, Responses or Chat Completions endpoint. Concurrent-session limits are specific to each model and organization. No numerical context limit is published.
What it can do
Orientation
Natural voice interfaces with interruptions and backend delegation for reasoning and tools.
Context
Not published · Streaming audio and text
Tools and integration
Features
Access
OpenAI Live API
Documented cost
| Concept | Worth | Unit/condition |
|---|---|---|
| Standard input | 0.05 USD / active minute | Standard API rate |
| Cached input | Not published | Reading reused prefixes |
| Cache write or storage | Not published | The condition varies by provider |
| Standard output | 0.02 USD / WebRTC standby minute | May include reasoning tokens |
| Batch input | Not published | Asynchronous processing |
| Batch output | Not published | Asynchronous processing |
Billed by duration, not per million tokens: USD 0.05 per active minute and USD 0.02 per WebRTC standby minute with inference paused. Delegated models and tools are charged separately.
i Prices change and may depend on level, region or context length. Check the source before making a decision.
How to read the results
No verified quantitative score for this version.
i No verified quantitative score for this version.
Inferama only highlights a “best result” when the metric, test set, configuration, and date allow for an equivalent comparison. The supplier's figures are presented as claims from its own source.
Chronology
gpt-live-1.1
New voice version; standby is a session state, not another model.