Model Tracker
gpt-4o-audio
gpt-4o-audio is an AI model made by OpenAI. OpenAI released it on 17 October 2024. It is deprecated. It takes text, audio and returns text, audio.
gpt-4o-audio is an AI model made by OpenAI. OpenAI released it on 17 October 2024. It is deprecated. It takes text, audio and returns text, audio. Its context window is 128,000 tokens. Its longest answer is 16,384 tokens. Its knowledge cutoff is 1 October 2023.
- Released
- 17 October 2024 — developers.openai.com, read 19 October 2026
- Status
- Deprecated — developers.openai.com, read 19 October 2026
- Takes
- Text, Audio — developers.openai.com, read 19 October 2026
- Returns
- Text, Audio — developers.openai.com, read 19 October 2026
- Open weights
- Not confirmed: The maker's cited model and API pages do not state whether the weights are open.
- Licence
- Not confirmed: The maker's cited pages do not name a licence for this model.
- Context window
- 128,000 tokens — developers.openai.com, read 19 October 2026
- Longest answer
- 16,384 tokens — developers.openai.com, read 19 October 2026
- Knowledge cutoff
- 1 October 2023 — developers.openai.com, read 19 October 2026
- API price, input
- Not confirmed: The current pricing page does not list this model. Its model page gives separate text-token and audio-token input prices, so there is no single input price to enter for this field.
- API price, output
- Not confirmed: The current pricing page does not list this model. Its model page gives separate text-token and audio-token output prices, so there is no single output price to enter for this field.
- Where
- API — developers.openai.com, read 19 October 2026
- Parameters
- Not confirmed: The maker's cited pages do not publish a parameter count for this model.
- Model card
- Not confirmed: two readings disagree: https://developers.openai.com/api/docs/models/gpt-4o-audio-preview and https://platform.openai.com/docs/models/gpt-4o-audio-preview
Questions
When was gpt-4o-audio released?
OpenAI released gpt-4o-audio on 17 October 2024.
Is gpt-4o-audio still available?
It is deprecated: OpenAI has announced the date it will retire it.
What is the context window of gpt-4o-audio?
The context window of gpt-4o-audio is 128,000 tokens, as OpenAI prints it.
What does gpt-4o-audio take and return?
gpt-4o-audio takes text, audio and returns text, audio.
What is the knowledge cutoff of gpt-4o-audio?
The knowledge cutoff of gpt-4o-audio is 1 October 2023.
More from OpenAI
- ada
- babbage
- babbage-002
- code-davinci-002
- computer-use-preview
- curie
- dall-e-3
- DALL·E
- DALL·E 2
- davinci
- davinci-002
- GPT-3.5 Turbo
- GPT-3.5 Turbo Instruct
- GPT-4
- GPT-4 Turbo
- GPT-4.1
- GPT-4.1 mini
- GPT-4.1 nano
- GPT-4.5
- GPT-4.5 Preview
- GPT-4o
- GPT-4o mini
- GPT-4o Mini Search Preview
- GPT-4o Mini Transcribe
Sources
- Deprecations | OpenAI API (read 19 October 2026)
- GPT-4o Audio Model | OpenAI API (read 19 October 2026)
- Changelog | OpenAI API (read 19 October 2026)
- Pricing | OpenAI API (read 19 October 2026)