CREATIVE INTELLIGENCE · OpenAI
GPT Audio
GPT Audio is a tool-using, audio-generating model from OpenAI in the GPT family, living in The Tidal Isles (creative intelligence). It reads text and audio and writes text and audio, with a 128K-token context window and up to 16K tokens of output. On OpenRouter it costs $2.50 per million input tokens and $10.0 per million output tokens.
See GPT Audio in 3DOpen in the WorktableView on OpenRouter
Specifications
- Provider
- OpenAI
- Family
- GPT
- Province
- The Tidal Isles
- Context window
- 128K tokens
- Maximum output
- 16K tokens
- Input / 1M tokens
- $2.50
- Output / 1M tokens
- $10.0
- Accepts
- text, audio
- Produces
- text, audio
- Reasoning
- No
- Tool use
- Yes
- Added to OpenRouter
- 2026-01-19
- Model ID
openai/gpt-audio- Price history
- —All recorded prices
From the 2026-10-24 catalog snapshot. Prices are US dollars per million tokens.
More GPT models
- GPT-5.4 Image 2272K · $8.00 / $15.0
- GPT Audio Mini128K · $0.600 / $2.40
- GPT-5 Image Mini400K · $2.50 / $2.00
- GPT-5 Image400K · $10.0 / $10.0