Context Window Checker
Paste a prompt, a file, or a transcript and see which models it fits inside, and what one call would cost.
These token counts are estimates
This is an estimate based on characters per token, not a real tokenizer. Every model family tokenizes differently: Anthropic notes that Claude 4.7 and later produce roughly 30% more tokens for the same text than their earlier models. Expect to be within about 10 to 20% for English prose, and further out for code, non-Latin scripts, and heavily structured text. For exact counts, use your provider’s token counting API.
Treat anything within about 20% of a limit as too close to rely on. The window also holds your system prompt, your tool definitions, and the model's own reply, none of which are counted above.
8 models in the pricing table are not shown, because we could not verify a published context window for them.
Prices checked on 2026-07-26. Model pricing changes often. Confirm with the provider before you budget against these numbers.