Model overview
The entry rate is gpt-5-6-luna: $1 per million input tokens and $6 output, one fifth of sol and two fifths of terra, with cached input at $0.10. It gives up nothing on paper, the same 1,050,000-token context, the same reasoning, tools, structured output and vision support, which makes it the right first try for bulk classification, extraction and other high-volume work where throughput per dollar decides more than depth does. Every model in this line keeps the same six-to-one output-to-input ratio, so changing tier scales a bill uniformly and never shifts the balance between prompt and completion.
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.