gpt-realtime-2 does not have a published shutdown date per OpenAI's deprecation page (checked 2026-10-26). No official replacement is published on that page. Published on the official docs: input price $4 per million tokens, context window 128,000 tokens, max output 32,000 tokens.
active
The image shows the model id and the status from this page. The link opens this page.
shields.io can use the JSON file at /badge/openai/gpt-realtime-2.json. The badges page has the endpoint snippet.
| Announced | Not published |
|---|---|
| Deprecated | Not published |
| Shutdown | Not published |
| Kind | none |
Not published.
See the replacement diff · OpenAI models · All deprecated models · All retired models
No request-error page names this model id.
| Input price / 1M | $4 · source, checked 2026-10-26 |
|---|---|
| Output price / 1M | $24 · source, checked 2026-10-26 |
| Cached input / 1M | $0.4 · source, checked 2026-10-26 |
| Context window | 128,000 · source, checked 2026-10-26 |
| Max output | 32,000 · source, checked 2026-10-26 |
| Reasoning | Not published |
| Vision | Not published |
| Tools | Not published |
gpt-realtime-2 does not have a published shutdown date per OpenAI's deprecation page (checked 2026-10-26). No official replacement is published on that page. Published on the official docs: input price $4 per million tokens, context window 128,000 tokens, max output 32,000 tokens.
No official replacement is published on that page.
gpt-realtime-2 status is active.
Model ID: gpt-realtime-2 | Reasoning model with tool use
No logged changes for this model yet.