Model details
GPT-5.1 is an upgrade to OpenAI's GPT-5 series, rolled out as two complementary variants: GPT-5.1 Instant, the most-used conversational model, now warmer and more playful by default while staying clear and useful, and GPT-5.1 Thinking, the advanced reasoning model designed to be easier to understand, faster on routine tasks, and more persistent on complex ones. The release emphasizes a dual focus on measurable intelligence gains and a more enjoyable communication style, addressing direct user feedback that a great assistant should be both smart and pleasant to talk to. Alongside the model upgrade, OpenAI introduced more intuitive controls for shaping ChatGPT's tone so responses can match the conversational tone a user wants from one chat to the next.
Practically, GPT-5.1 fits teams and individuals who want a flexible assistant that can shift between quick, friendly exchanges and deeper reasoning without changing tools. Instant handles day-to-day questions, brainstorming, and lightweight instructions, while Thinking is aimed at multi-step problems that benefit from sustained analysis. The tone controls make it easier to tune outputs for different audiences, from concise professional replies to more expressive creative drafts, so the same model can adapt to writing, planning, coding help, and exploratory conversation within a single workflow.
Transparent token rates
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
OpenRouter
Large language models are increasingly integrated into medical education, yet their performance in non-English clinical examinations, particularly Persian, remains limited. This study evaluated how GPT-4o and GPT-5.1 perform on Iranian Rheumatology Board examination questions. A total of 204 multiple-choice items were
OpenRouter
GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. $1.25 per million input tokens, $10 per million output tokens. 400,000 token context window, maximum output of 128,000 tokens. Higher uptime with 2 providers. Includes independent benchmarks from Artificial Analys
OpenRouter
Compare Kimi K2.5 from moonshotai and GPT-5.1-Codex-Mini from OpenAI on key metrics including benchmarks, price, context length, and other model features.
OpenRouter
Compare GPT-5.1 Chat from OpenAI and Qwen3 Coder Next from Qwen on key metrics including benchmarks, price, context length, and other model features.
