Skip to content
Toolshed

Context Window Checker

Paste a prompt and see how much of each AI model's context window it fills and whether it fits with room for the answer. GPT, Claude, Gemini.

  • No uploads
  • No limits
  • No signup

  • GPT-6 AstraContext window: 1,050,000
    Prompt tokens: —
  • GPT-6.1 SolContext window: 1,050,000
    Prompt tokens: —
  • GPT-6.1 TerraContext window: 1,050,000
    Prompt tokens: —
  • GPT-6 LunaContext window: 1,050,000
    Prompt tokens: —
  • GPT-5.5Context window: 1,050,000
    Prompt tokens: —
  • GPT-5.4 miniContext window: 400,000
    Prompt tokens: —
  • GPT-4.1Context window: 1,047,576
    Prompt tokens: —
  • GPT-4o miniContext window: 128,000
    Prompt tokens: —
  • Claude Fable 5.1Context window: 1,000,000
    Prompt tokens: —
  • Claude Opus 5.5Context window: 1,000,000
    Prompt tokens: —
  • Claude Sonnet 5.5Context window: 1,000,000
    Prompt tokens: —
  • Claude Haiku 5.5Context window: 1,000,000
    Prompt tokens: —
  • Gemini 4 ArgonContext window: 1,048,576
    Prompt tokens: —
  • Gemini 3.8 FlashContext window: 1,048,576
    Prompt tokens: —
  • Gemini 3.1 Pro PreviewContext window: 1,048,576
    Prompt tokens: —
  • Gemini 3.5 Flash-LiteContext window: 1,048,576
    Prompt tokens: —
  • Gemini 2.5 Flash-LiteContext window: 1,048,576
    Prompt tokens: —

GPT-5.5, GPT-4.1 and GPT-4o counts are exact (tiktoken o200k_base). Numbers marked ≈ are estimates: Claude and Gemini don't publish their tokenizers (we use about 2.5 and 4 characters per token, the providers' own figures), and the GPT-6 tokenizer isn't published. Leave some margin when a prompt is close to the limit.

Limits checked Nov 5, 2026. Official model pages: OpenAI · Anthropic · Google

Input:
Text · TXT
Output:
Context usage
Runs on:
Your device
Size limit:
None
Account:
Not needed

How to use Context Window Checker

  1. Paste your prompt

    Paste the text you plan to send, or open a .txt, .md or .json file. Nothing is uploaded.

  2. Set the answer room

    Enter how many tokens you want to keep free for the model's reply.

  3. Compare the bars

    Each bar shows how much of a model's context window your prompt and answer fill, and whether they fit.

Why Context Window Checker on Toolshed

  • No uploads

    Everything runs in this browser tab. Your files never leave your device.

  • No limits

    No file-size caps, no daily quotas. Process as much as your device can handle.

  • No signup

    No account, no email, no watermark.

Frequently asked questions

What is a context window?

It's the most tokens a model can handle in one request: your prompt, any chat history and files, and the reply it writes. If the total is over the limit the request fails or old messages get cut.

Why keep room for the answer?

The reply counts against the same window, and each model also has a maximum output length. If your prompt fills the window there's no space left for a useful answer.

How exact is the check?

For GPT-5.5, GPT-4.1 and GPT-4o the token count is exact for plain text. For Claude, Gemini and GPT-6 it's an estimate, so keep a margin of 10–20% when you're near the limit.

Are my files uploaded anywhere?

No. Context Window Checker runs entirely in your browser. Your files are processed on your device and are never sent to a server.

Is there a file size limit?

No fixed limit. The only limit is your device's memory. Very large files work best in a desktop browser.

Is Context Window Checker really free?

Yes. There's no account and no watermark. A short optional ad, or a 20-second wait, unlocks each download. That's how we keep it free.