A newer model at a lower price
Some model upgrades cost less on both input and output than the model you're currently using.
Model pricing does not move in one direction. Providers periodically ship a model that is both better and cheaper than the one it replaces, and the older one stays available for compatibility.
Pinned model identifiers are how teams end up on the wrong side of that. A version string set eighteen months ago in a config file keeps working, so nobody revisits it, and the bill quietly stays at the old rate.
This finding only fires where the replacement is cheaper on both input and output within the same model family. It is not a general recommendation to chase new releases — most upgrades cost more, and this tool will tell you when they do.
Validate on your evals before switching. "Cheaper and newer" is a strong prior, not a guarantee for your specific task.
Claude Opus 4.1 at $15 / $75 per million tokens.Claude Opus 4.5 at $5 / $25 — a third of the price, in the same family.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
- 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.
- 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.