GPT-6.1 Sol

GPT-6.1 Sol is OpenAI's recommended cost-performance model: same $2/$10 pricing as GPT-6 Sol (cached input halved to $0.10), but much stronger, scoring 75.2% on DeepSWE v1.1 versus 68.8% for GPT-6 Sol and 71.4% on OSWorld 2.0 against Astra's 73.5%. It supports reasoning effort from low to max and tool calling through the Responses and Chat Completions APIs. Input is text and images (no audio or video) with a 1.05M-token context window and up to 128K output tokens.