Model Tracker
GPT-Realtime-2.1
GPT-Realtime-2.1 is an AI model made by OpenAI. OpenAI released it on 6 July 2026. It is generally available.
GPT-Realtime-2.1 is an AI model made by OpenAI. OpenAI released it on 6 July 2026. It is generally available. It takes text, image, audio and returns text, audio. Its context window is 128,000 tokens. Its longest answer is 32,000 tokens. Through the API it costs $4.00 per 1M tokens for input and $24.00 per 1M tokens for output. Its knowledge cutoff is 30 September 2024.
- Released
- 6 July 2026 — developers.openai.com, read 16 October 2026
- Status
- Generally available — developers.openai.com, read 16 October 2026
- Takes
- Text, Image, Audio — developers.openai.com, read 16 October 2026
- Returns
- Text, Audio — developers.openai.com, read 16 October 2026
- Open weights
- Not confirmed: The model page and related official pages do not state whether this model's weights are open or downloadable.
- Licence
- Not confirmed: The official pages checked do not name a licence for this model.
- Context window
- 128,000 tokens — developers.openai.com, read 16 October 2026
- Longest answer
- 32,000 tokens — developers.openai.com, read 16 October 2026
- Knowledge cutoff
- 30 September 2024 — developers.openai.com, read 16 October 2026
- API price, input
- $4.00 per 1M tokens — developers.openai.com, read 16 October 2026
- API price, output
- $24.00 per 1M tokens — developers.openai.com, read 16 October 2026
- Where
- API — developers.openai.com, read 16 October 2026
- Parameters
- Not confirmed: The official pages checked do not publish a parameter count for this model.
- Model card
- https://developers.openai.com/api/docs/models/gpt-realtime-2.1 — developers.openai.com, read 16 October 2026
Questions
When was GPT-Realtime-2.1 released?
OpenAI released GPT-Realtime-2.1 on 6 July 2026.
Is GPT-Realtime-2.1 still available?
Yes: it is generally available, as OpenAI states it.
What is the context window of GPT-Realtime-2.1?
The context window of GPT-Realtime-2.1 is 128,000 tokens, as OpenAI prints it.
How much does the GPT-Realtime-2.1 API cost?
On the standard tier, GPT-Realtime-2.1 costs $4.00 per 1M tokens for input and $24.00 per 1M tokens for output, as OpenAI lists it.
What does GPT-Realtime-2.1 take and return?
GPT-Realtime-2.1 takes text, image, audio and returns text, audio.
What is the knowledge cutoff of GPT-Realtime-2.1?
The knowledge cutoff of GPT-Realtime-2.1 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
- GPT-Realtime-2.1 Model | OpenAI API (read 16 October 2026)
- Models | OpenAI API (read 16 October 2026)
- Changelog | OpenAI API (read 16 October 2026)
- Pricing | OpenAI API (read 16 October 2026)