Model overview
Sitting between the two, gpt-5-6-terra charges $2.50 per million input tokens and $15 output, half of sol on both sides and two and a half times luna. The window is the same 1,050,000 tokens and the declared parameters are the same reasoning, tools, structured output and vision, so price is the only variable. It is the natural default of the three: move up only when a task measurably fails here, and move down when it clearly does not need the headroom. Cached input costs $0.25, a tenth of the listed rate, and the surcharge above 272K input tokens applies here exactly as it does to the other two.
Billing conditions: Standard API price. Cache writes cost 1.25x uncached input. Prompts over 272K input tokens cost 2x input and 1.5x output for the full request.
- Context window
- 1,050,000 tokens
- Knowledge cutoff
- —
- Price last verified
- First observed
Descriptions, capabilities, and tariffs come from the linked source. First-party prices take priority; OpenRouter fallbacks are labelled.