Astra's API page: 1,050,000-token context, $10/$50 per million, and a 2x surcharge above 272K input tokens
OpenAI API docs·high signal
The developer docs list a 1,050,000-token context window (922,000 max input, 128,000 max output), an April 30, 2026 knowledge cutoff, text and image in but text only out, and one snapshot named gpt-6-astra. Pricing is $10 input, $1 cached input, $12.50 cache write, $50 output per million, but requests over 272K input tokens bill input and cache at 2x and output at 1.5x, which is the detail long-context agent loops need before they budget. Rollout started with Trusted Access Program enterprises, with API, AWS and Plus/Pro/Business/Enterprise plans following in days.