The page specifies a 1,050,000-token context window and 128,000 maximum output tokens. It supports function calling and, through the Responses API, tools including hosted shell, apply patch, computer use, and MCP. Listed standard text pricing is $2 per million input tokens and $10 per million output tokens. OpenAI advises developers to compare the model with Astra on their own tasks; the documentation does not establish that quality or cost advantages will hold for every workload.
Raw SignalSep 30, 20261 min read1 source
Give your coding agents more room to work.
In one minute
OpenAI’s model documentation lists GPT-6.1 Sol as an API model for complex coding, computer use, and professional work, describing it as offering near-Astra performance at lower cost.