Most capable GPT-6 model for demanding reasoning, coding and agentic work. 1050000 128000 true Recommended Executor default for a strong balance of capability and cost. 1050000 128000 true Cost-efficient GPT-6 model for focused, high-volume Executor runs. 1050000 128000 true Frontier model for complex professional work and the hardest coding/reasoning tasks. 1050000 128000 true Prompts with more than 272K input tokens are priced at 2x input and 1.5x output for the full request. Cache writes are billed at 1.25x the uncached input token rate. Recommended WTeam Executor default: strong coding and agentic capability with a better cost/performance balance than Sol. 1050000 128000 true Prompts with more than 272K input tokens are priced at 2x input and 1.5x output for the full request. Cache writes are billed at 1.25x the uncached input token rate. Cost-sensitive model for high-volume testing, routine tool routing and cheaper WTeam Executor runs. 1050000 128000 true Prompts with more than 272K input tokens are priced at 2x input and 1.5x output for the full request. Cache writes are billed at 1.25x the uncached input token rate. Cheapest currently available general-purpose text model for the Responses API. 400000 128000 true