GPT-6 Astra

gpt-6-astra

OpenAI's most capable model for the hardest end-to-end work

Intelligence: 52.7
Context: 1.05M
Training cutoff: 2026-04
Added: 2026-09-03
Inputs: Vision

Providers

One route serves GPT-6 Astra, and every figure below is measured on it. Where the selected window has too little traffic, the figure names what it is based on instead.

OpenAI only route

gpt-6-astra

Uptime

100.0%

Input / 1M: $10.00 ≤272K input
Output / 1M: $50.00 ≤272K input
TTFT: 2.00s fixed prompt · n=8
Output rate: 58.7 tok/s fixed prompt · n=8

1.05M context 128,000 max output cache $2.00 read / $25.00 write per 1M VisionRetention 30 days Training No Provider terms, reviewed 2026-10-13warming · 30m

Prompt caching Automatic reuse Eligible Cache key Affinity hint Caller breakpoints None advertised

TTFT is the median time to the first visible answer token over real ModelRelay requests, with a fixed prompt standing in for models that have no traffic yet. Speed ranks by it. Intelligence is the Artificial Analysis Intelligence Index.