Context window checker

Paste a prompt, pick a model, and find out instantly whether it fits the context window — with the exact token count, the window size, and how many tokens you have left (optionally reserving room for the model's reply).

Model

Reserve for output

Prompt tokens

—

Context window

—

Tokens remaining

—

Window used

—

Context windows are approximate (some models offer larger long-context tiers) — verify against provider docs. OpenAI token counts are exact; others are estimates. "Reserve for output" subtracts space you want to leave for the model's reply.

What counts toward the context window?

The context window is the total tokens a model can handle in one request — input plus output combined. Everything you send counts: the system prompt, conversation history, retrieved/RAG context, tool definitions, and the user message. If the prompt alone fills the window, there's no room left for a response — so reserve space for the output you expect.

More free token tools

TokensToken counterPaste text, pick a model, and see exact tokens, characters, and chars/token — every token as a colored chip with its ID.CostLLM API cost calculatorReal token counts → dollar cost, split into input vs output, for the model you pick. Paste text to auto-count input.CostModel cost comparisonOne prompt + expected output length, costed side by side across every model in a sortable table.TokensTokenizer visualizerSee exactly how text splits into tokens, color-coded, with hover to inspect each token's ID and boundaries.TokensWord ↔ token estimatorQuick two-way converter between word count and token count, with real-tokenizer calibration.ExplainerFrom prompt to outputA clickable pipeline explaining how an LLM turns your prompt into output — tokenization, embeddings, transformer, sampling, and back.