GPT-Live-1

Why teams choose it

Tradeoffs to know

• Image and video are not supported on the API card. Structured outputs and fine-tuning are not supported.
• The live model has a small context window. Put tools and business rules in the backend prompt.
• Interrupting speech does not automatically cancel delegated backend work.

When not to use this

• Not ideal for simple tasks where cheaper models in the same lineup are good enough.
• Avoid for regulated or high-stakes outputs without evaluations that mimic your tooling, data, and review process.
• Pair catalog notes with comparisons and your own benchmarks before declaring a routing winner.

Technical specs

Inputs

audio, text

Outputs

audio, text

Capabilities

full-duplex voice, speech-to-speech, streaming ASR transcripts, interruption handling, turn detection, keyword biasing, backend delegation

License

Proprietary API

Model string

gpt-live-1

Benchmarks

{
  "api_id": "gpt-live-1",
  "source": "https://developers.openai.com/api/docs/models/gpt-live-1",
  "vendor_reported": true,
  "knowledge_cutoff": "2025-07-31",
  "session_price_per_minute_usd": 0.05
}