Skip to content
TheChatArchiveThe Chat Archive
gpt-4o-search-preview-high-loc· OpenAIHugging Face LMArena Search Arena 24K

what is the largest token size limit for LLM right now

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with Perplexitysonar-reasoning-pro-high’s answer.
  1. User

    what is the largest token size limit for LLM right now

  2. Assistant

    As of April 2025, the largest context window available in a large language model (LLM) is offered by Google's Gemini 1.5 Pro, which supports up to 1 million tokens[1]. This substantial context window allows the model to process extensive documents and datasets in a single prompt, making it highly effective for tasks requiring a deep understanding of large contexts.

    In comparison, other notable LLMs include Anthropic's Claude 3 series (Haiku, Sonnet, and Opus), each with a context window of 200,000 tokens, and OpenAI's GPT-4 Turbo, which supports up to 128,000 tokens[2].

    It's important to note that while these models can handle large input sizes, the maximum number of tokens they can generate in a single output is often smaller. For instance, GPT-4 Turbo has a maximum output of 4,096 tokens[2].

    Additionally, research efforts like Microsoft's LongRoPE have demonstrated methods to extend LLM context windows beyond 2 million tokens. However, such extensions are primarily experimental and may not yet be widely implemented in publicly available models[3].

    In summary, as of now, Google's Gemini 1.5 Pro holds the record for the largest context window in a publicly available LLM, supporting up to 1 million tokens.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.