Model Tracker
GPT-Realtime-Whisper
GPT-Realtime-Whisper is an AI model made by OpenAI. It is generally available. It takes text, audio and returns text. Its context window is 16,000 tokens.
GPT-Realtime-Whisper is an AI model made by OpenAI. It is generally available. It takes text, audio and returns text. Its context window is 16,000 tokens. Its longest answer is 2,000 tokens. Its knowledge cutoff is 30 September 2024.
- Released
- Not confirmed: The official model page and model catalog do not state a release or first-availability date.
- Status
- Generally available — developers.openai.com, read 16 October 2026
- Takes
- Text, Audio — developers.openai.com, read 16 October 2026
- Returns
- Text — developers.openai.com, read 16 October 2026
- Open weights
- Not confirmed: The official model page does not state whether downloadable weights are available.
- Licence
- Not confirmed: The official model page does not name a licence for this model.
- Context window
- 16,000 tokens — developers.openai.com, read 16 October 2026
- Longest answer
- 2,000 tokens — developers.openai.com, read 16 October 2026
- Knowledge cutoff
- 30 September 2024 — developers.openai.com, read 16 October 2026
- API price, input
- Not confirmed: The pricing page shows dashes for token-based input and output, and lists only an estimated cost per minute; it does not print a standard input price per 1M tokens.
- API price, output
- Not confirmed: The pricing page shows dashes for token-based input and output, and lists only an estimated cost per minute; it does not print a standard output price per 1M tokens.
- Where
- API — developers.openai.com, read 16 October 2026
- Parameters
- Not confirmed: The official model page does not publish a parameter count.
- Model card
- Not confirmed: The official model page is a model details page, but it does not identify or link a model card or system card for this model.
Questions
Is GPT-Realtime-Whisper still available?
Yes: it is generally available, as OpenAI states it.
What is the context window of GPT-Realtime-Whisper?
The context window of GPT-Realtime-Whisper is 16,000 tokens, as OpenAI prints it.
What does GPT-Realtime-Whisper take and return?
GPT-Realtime-Whisper takes text, audio and returns text.
What is the knowledge cutoff of GPT-Realtime-Whisper?
The knowledge cutoff of GPT-Realtime-Whisper is 30 September 2024.
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
- Models | OpenAI API (read 16 October 2026)
- GPT-Realtime-Whisper Model | OpenAI API (read 16 October 2026)
- Pricing | OpenAI API (read 16 October 2026)