GPT-5 is OpenAI’s new flagship reasoning model, powering the default ChatGPT experience and now exposed directly through the API. A larger transformer core is paired with a real-time router that orchestrates deep chain-of-thought, parallel tool calls, and multimodal reasoning, letting one request span tasks as varied as end-to-end app generation, legal analysis, or medical literature review. The API delivers the full “thinking” tier: every call can accept 272 000 input tokens and emit 128 000 reasoning-plus-output tokens, for a record 400 000-token context. Developers steer behaviour with two fresh dials—reasoning_effort (from minimal to high) and verbosity (low → high)—and can drop JSON in favour of custom tools defined by context-free grammars. Across OpenAI’s evals GPT-5 cuts hallucinations by ~80 %, scores 74.9 % on SWE-bench Verified, and reaches 97 % on τ²-bench tool use. Safety improvements include stricter self-evaluation and a new safe-completion strategy. Pricing is US $1.25 / M input tokens and US $10 / M output tokens, with prompt caching and batch endpoints to trim cost further.