what is the largest token size limit for LLM right now
- User
what is the largest token size limit for LLM right now
- 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.
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.