AI model · OpenAI
GPT Audio
Model ID: openai/gpt-audio
- Input
- $2.50 per 1M tokens
- Output
- $10 per 1M tokens
- Context
- 128K tokens at once
- Max output
- 16K tokens per reply
- Released
- 19 Jan 2026 OpenAI
What it can do
- NoReasoning
- YesTool calling
- NoImage input
- NoOpen weights
- NoFree to use
Takes text, audio; gives text, audio.
How its listing describes it
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.
Sources
- OpenAI: GPT Audio on OpenRouter — read 2 Oct 2026