GPT-5

5 (base release, 2025-08-07) · Family: GPT

OpenAI's flagship unified model (released 2025-08-07) with a router that switches between fast answers and deep reasoning (GPT-5 Thinking).

✓ Active✓ Public access★ FeaturedLLMMultimodalReasoning modelTool-using model📁 GPT

Context window

400K tokenów (272K wejścia + 128K wyjścia)

tokens

Parameters

Nieujawnione publicznie

parameters

Max output

128,000

tokens

Release date

7 August 2025

🏢OpenAIProducer

Access:APIHostedDeployment:☁ Cloud

Overview

GPT-5 is OpenAI's flagship model unveiled on 7 August 2025. It replaced GPT-4o and o3 as the default model in ChatGPT and the API. GPT-5 is not a single model but a unified system: a fast base model handles most queries, while a built-in router directs harder tasks to a deeper reasoning variant (GPT-5 Thinking) when needed.

The model is multimodal on input (text and image) and produces text, code and structured data. It offers a context window of up to 400K tokens in the API (272K input + 128K output). GPT-5 set new state-of-the-art results in agentic coding (SWE-bench Verified), mathematics (AIME 2025) and multimodal reasoning, while reducing hallucinations compared with its predecessors.

GPT-5 is available in ChatGPT across all plans (Free, Plus, Pro, Team, Enterprise, Edu) and in the OpenAI API in gpt-5, gpt-5-mini and gpt-5-nano variants. The model weights are closed; access is only through OpenAI's hosted products and API.

Classification

LLMMultimodalReasoning modelTool-using model

Family: GPT

Access & deployment

APIHosted

Cloud

Weights: Closed

Key parameters

📏 Context: 400K tokenów (272K wejścia + 128K wyjścia)

🧩 Parameters: Nieujawnione publicznie

✓ Tools

📥 Input: text, image, documents

Technical specification

Context window

400K tokenów (272K wejścia + 128K wyjścia)

tokens

Parameters

Nieujawnione publicznie

parameters

Max output tokens

128,000

tokens per response

Knowledge cutoff

30 Sept 2024

Knowledge boundary

License

Proprietary (OpenAI Terms of Use; ChatGPT / API commercial terms)

Hardware requirements

Not applicable — the model is hosted only on the OpenAI API and ChatGPT products. No on-device or local version.

Features:✓ Tool use

Modalities

⬇ Input

textimagedocuments

⬆ Output

textcodestructured_data

Capabilities and applications

Native model capabilities

Reasoning

The model's ability to reason logically and solve complex problems.

Category: reasoning

Advanced reasoning

The ability to perform multi-step, structured reasoning: analysing problems, planning steps, and drawing conclusions from hypotheses. Reasoning-first models (e.g. GPT-5.1 Thinking) dedicate a portion of inference to chains of thought before responding.

Category: reasoning

Coding

Generating, analysing and modifying code in many programming languages. Covers writing functions, debugging, refactoring, code review, and creating tests. Measured by benchmarks such as HumanEval and SWE-bench.

Category: coding

Agentic coding

Multi-hour, multi-step programming tasks performed autonomously by the model: cloning a repository, running tests, iterating on fixes, integrating with CLI tools. Characteristic of Codex variants (GPT-5.1-Codex-Mini, Codex-Max).

Category: coding

Agentic capability

The model's ability to autonomously plan and execute multi-step tasks by sequentially using tools, maintaining context, and adapting to intermediate results.

Category: planning

Long context

Support for large context windows — tens to hundreds of thousands (or millions) of input tokens. Enables analysis of entire codebases, long documents, and many parallel conversations without losing earlier information. GPT-5.1 supports 400,000 tokens.

Category: language

Multimodal understanding

Category: multimodal

Image understanding

Analysing and interpreting the content of images.

Category: vision

Tool use

The model's ability to call external functions, APIs and tools during a conversation: calculator, search engine, code editor, database. The model decides when and how to use a tool and interprets its result.

Category: planning

Function Calling

Category: planning

Instruction following

Precisely following instructions contained in the prompt: response format, length, style, constraints (e.g. 'reply in six words'). GPT-5.1 significantly improved this capability compared to GPT-5.

Category: language

Mathematical reasoning

The model's ability to solve mathematical tasks requiring multi-step reasoning — equations, proofs, combinatorics, geometry, calculus and competition-level problems.

Category: reasoning

Structured output

Producing data in structured formats such as JSON.

Category: structured_generation

Web browsing

Ability of the model to autonomously search and browse web pages to retrieve up-to-date information.

Category: other

Adaptive reasoning effort

The model decides how much 'thinking' to allocate to a given query: simple questions are answered quickly, complex problems receive more inference cycles. A GPT-5.1 feature (both Instant and Thinking) that shortens time on easy tasks and extends it for hard ones.

Category: reasoning

Benchmark results

5 benchmarks

SWE-bench

accuracy · agentic coding, with tools

74.9%