OpenAI

GPT Audio

openai/gpt-audio

JSON

Specification

Published by the vendor; the platform bills at the target's declared price.

GPT Audio

tools

OpenAI openai/gpt-audio

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Audio is priced...

Input $/1M: $2.50
Output $/1M: $10.0
Context: 128K
Max output: 16K
Released: Jan 19, 2026
Modalities: textaudioaudio out

On this deployment

No routing target resolves to this model yet. Declare one and the router picks it up without retraining.

Not routable here yet

Add a target with metadata.model set to this id.

targets.yamlyaml

# targets.yaml - declare a target that runs GPT Audio
targets:
  - id: gpt-audio
    kind: llm
    name: GPT Audio
    metadata:
      model: openai/gpt-audio          # links the target to this catalogue entry
    capabilities:
      domains: [general]
      supports_tools: true
      context_window: 128000
    cost:
      usd_per_1k_tokens: 0.006250

Price among OpenAI models

Input list price per million tokens; GPT Audio is the 9th cheapest of 13 listed.

More from OpenAI

Other models by the same vendor in the catalogue.