Running out of room
A prompt filling most of the context window leaves nothing for the conversation.
The context window holds your prompt, the conversation so far, tool results, and the response. A system prompt occupying most of it does not fail immediately — it fails on the fourth turn, in production, when the history finally overflows.
Truncation failures are unpleasant to debug because they depend on conversation length rather than on any single request. The symptom is a model that suddenly forgets its instructions.
A rough guide: if the static prompt is over about 60% of the window, either the window is too small for the job or the prompt is carrying content that belongs in retrieval.
140k-token prompt in a 200k window: four turns of history and you are truncating.A 20k prompt plus retrieval that fetches only what the current turn needs.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.
- Your prompt crossed a pricing cliffSome models double their input price above a prompt-size threshold.
- This model counts your prompt differentlyThe same text is not the same number of tokens on every model. Upgrades can raise your bill silently.
- Output is most of this billWhen output is most of the bill, shortening the prompt barely moves the total.