Context window

How much text a model can consider at once, measured in tokens. What falls outside it is forgotten.

When you ask a model a question, it can only weigh the text inside its context window: the prompt plus everything it has already written. Early chatbots managed a few thousand tokens, a few pages; by 2024 the leading models accepted hundreds of thousands, enough for whole books. Anything beyond the window is simply not there for the model to use.

Where it mattered in the record

  1. Alibaba announces Qwen3.8-Max, its largest model to date

    Alibaba announced Qwen3.8-Max on 3 August 2026 with 2.4 trillion parameters, about 95 billion active at a time through a sparse mixture of experts, a context window up to 1 million tokens, and native text, image and video input. Weights were scheduled to follow a week later.

  2. Mistral releases Small 4 and joins Nvidia’s Nemotron Coalition

    Mistral AI released Mistral Small 4 on 16 March 2026, a 119-billion-parameter mixture-of-experts model with 6 billion active parameters, a 256,000-token context window and an Apache 2.0 license. It joined Nvidia’s Nemotron Coalition the same day.

  3. Anthropic and OpenAI ship rival coding models minutes apart

    Anthropic released Claude Opus 4.6 with agent teams in Claude Code and a 1 million-token context window in beta. OpenAI released GPT-5.3-Codex minutes later, reporting a 25% speed increase for Codex users.

  4. OpenAI makes GPT-5 the default model in ChatGPT

    OpenAI released GPT-5 on 7 August 2025, describing it as a unified model that combined the step-by-step reasoning of the o-series with the faster replies of the GPT series, with a 400,000-token context window. It became the default for free and paid ChatGPT users.

  5. Meta releases Llama 3.1 with a 405-billion-parameter model

    Meta released Llama 3.1 on 23 July 2024, including a 405-billion-parameter model it called the largest openly available foundation model to date, with a 128,000-token context window. Meta said it matched GPT-4o and Claude 3.5 Sonnet on knowledge, math, and tool-use benchmarks.

  6. Anthropic launches the Claude 3 model family

    Anthropic released Claude 3 Opus, Sonnet, and Haiku on 4 March 2024, three models spanning a range of speed and capability, with a 200,000-token context window and image input. Anthropic reported that Opus matched or exceeded GPT-4 on several public benchmarks.

Every term in the glossary