OpenAI: GPT-5.1-Codex-Mini

GPT-5.1-Codex-Mini is a paid model from OpenAI that accepts both text and image inputs and produces text outputs. It supports tool use and reasoning, which makes it applicable to agentic workflows and multi-step tasks. Structured output support is unconfirmed. The context window reaches 400,000 tokens, with up to 100,000 tokens available for completions, so it can handle long documents or extended conversations without truncation. At $0.25 per million input tokens and $2.00 per million output tokens, it sits on the affordable end of the reasoning-capable model tier. Its blended benchmark score of 50.2 comes from only one benchmark, so performance data is thin and comparisons to better-covered models should be treated cautiously. Teams running high-volume, tool-driven pipelines who want reasoning support without premium pricing may find it worth testing, but buyers prioritizing proven benchmark breadth should note the limited coverage before committing.