Model overview
gpt-5-6-sol is the top rate of the three OpenAI entries: $5 per million input tokens and $30 output, exactly double terra and five times luna, for the same 1,050,000-token window and the same reasoning, tools, structured output and vision support. Nothing in the published metadata separates it from its siblings except price, so it is a capability bet rather than a feature choice: pick it when a task fails at $2.50 input, and drop back when it does not. Cached input lands at $0.50, a tenth of the uncached rate, and cache writes cost 1.25 times uncached input. Past 272K input tokens the full request bills at twice input and one and a half times output.
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.