impulse

GPT Live 1

Frontier labRealtime
API id gpt-live-1
Input / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Where to run it

2 hosts serve GPT Live 1. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
OpenAILab API
gpt-live-1
-
gpt-live-1
-
Retires 10 Sep 2027

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
AudioText
Produces
AudioText
Features
Audio inputAudio output

Similar models

This model has no listed price, so these are current models with similar capabilities.

Smaller OpenAI models

Other frontier labs

Open-weight picks

No similar open-weight match.

Call it

Using OpenAI's API.

Python
from openai import OpenAI

client = OpenAI()  # reads OPENAI_API_KEY

response = client.responses.create(model="gpt-live-1", input="Hello")
print(response.output_text)

Quick answers

Which APIs offer GPT Live 1?

GPT Live 1 runs on 2 APIs: OpenAI and Azure OpenAI.

Is GPT Live 1 being retired?

Azure OpenAI retires it on 10 Sep 2027. 1 host keeps serving it.

What is GPT Live 1's API model id?

Use gpt-live-1 with OpenAI.

Sources

Raw catalog entry for gpt-live-1 on OpenAI
{
  "input_cost_per_second": 0.000833333333333,
  "litellm_provider": "openai",
  "mode": "realtime",
  "source": "https://developers.openai.com/api/docs/pricing",
  "supported_modalities": [
    "text",
    "audio"
  ],
  "supported_output_modalities": [
    "text",
    "audio"
  ],
  "supports_audio_input": true,
  "supports_audio_output": true,
  "supports_function_calling": true
}