Your prompt crossed a pricing cliff
Some models double their input price above a prompt-size threshold.
Long-context pricing is not always linear. Google's Pro tiers charge one rate up to a 200,000-token prompt and roughly double it above that. The jump applies to the whole request, not just the tokens past the line.
That makes the threshold a genuine cliff. A prompt at 199,000 tokens and one at 201,000 tokens differ by one percent in size and by about a hundred percent in price.
If you are near a threshold, it is worth knowing exactly where you sit. Trimming retrieved context to stay below the line is often the single highest-value optimisation available, and it is invisible unless you are looking for it.
210k-token prompt billed at the high tier: every token costs double.190k-token prompt after trimming retrieval: the whole request drops to the base tier.Check your own prompt
The analyser checks this pattern along with the other 25, prices each finding against your request volume, and hands back a rewritten prompt. It runs in your browser — nothing is uploaded.
Run the analyserMore on model choice
- A newer model at a lower priceSome model upgrades cost less on both input and output than the model you're currently using.
- This model counts your prompt differentlyThe same text is not the same number of tokens on every model. Upgrades can raise your bill silently.
- Running out of roomA prompt filling most of the context window leaves nothing for the conversation.
- Output is most of this billWhen output is most of the bill, shortening the prompt barely moves the total.