OpenAI: GPT Astra Latest
~openai/gpt-astra-latest · OpenAIUnmeasurable- Declared family
- Router
- Declared tokenizer tag
- Router
- Entered catalogue
- 11 September 2026
- Measurement
- Excluded: a router, not one stable model
- Evidence confidence
- Unknown
This catalogue entry is an alias: a name that points at another model rather than a model of its own. Its serving contract is listed below; the identity evidence lives on the record of the model it serves.
| We checked | What we found | Where it came from |
|---|---|---|
| How it counts tokens | Not measured yet | we measured it |
| How its API is set up | Set up identically to 4 other listings, field for field | api_523f730f |
| How much it can read and write | Reads up to 1,050,000 tokens at once, writes up to 128,000 | its own listing |
| Whether it thinks before answering | Always reasons, and cannot be turned off, at max, xhigh, high, medium, low, medium by default | its own listing |
This model always redirects to the latest model in the GPT Astra family.
Supported parameters
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstool_choicetoolsverbosity
defaults: {}