gpt-6-astra does not have a published shutdown date per OpenAI's deprecation page (checked 2026-10-25). No official replacement is published on that page. Published on the official docs: input price $10 per million tokens, context window 1,050,000 tokens, max output 128,000 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-6-astra.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
These rows are from the breaking-changes list. JSON · CSV
| Old setting | What happens | Fix | Source |
|---|---|---|---|
| function tools on POST /v1/chat/completions | Function tools with reasoning_effort are not supported for gpt-6.1-sol in /v1/chat/completions. To use function tools, use /v1/responses or set reasoning_effort to 'none'. | Call the Responses API for function tools. Do not set reasoning_effort to none on gpt-6.1-sol or gpt-6-astra. | GPT-6.1 Sol model page, checked 2026-10-25 · Error page |
| Input price / 1M | $10 · source, checked 2026-10-26 |
|---|---|
| Output price / 1M | $50 · source, checked 2026-10-26 |
| Cached input / 1M | $1 · source, checked 2026-10-26 |
| Context window | 1,050,000 · source, checked 2026-10-26 |
| Max output | 128,000 · source, checked 2026-10-26 |
| Reasoning | Not published |
| Vision | Not published |
| Tools | Not published |
gpt-6-astra does not have a published shutdown date per OpenAI's deprecation page (checked 2026-10-25). No official replacement is published on that page. Published on the official docs: input price $10 per million tokens, context window 1,050,000 tokens, max output 128,000 tokens.
No official replacement is published on that page.
gpt-6-astra status is active.
GPT-6 Astra supports Chat Completions, but tool calling requires the Responses API. GPT-6 Astra does not support reasoning effort none.
Model ID: gpt-6-astra. reasoning.effort supports low, medium, high, xhigh, and max. Context 1050000. Max output 128000. Input $10. Cached input $1. Output $50. Knowledge cutoff Apr 30, 2026.
Model ID: gpt-6-astra | Our most capable model for the most demanding work.
No logged changes for this model yet.