# Choosing models by accuracy, cost, and latency with evals

> Original title: When your inference bill starts climbing, choosing the right model becomes a question of accuracy, cost, and latency.

- Source: OpenRouter
- Published: 2026-11-03T17:27:36.000Z
- Bad Influence: https://badinfluence.news/items/yzse8rje7wbo6lw7bjg25rpu3
- Original: https://x.com/OpenRouter/status/2117670039881216130

## Summary

OpenRouter's Chris Clark and Mercor's Osvald Nitski discuss how evals help teams decide when to optimize, switch models, or train their own as inference bills rise. The post frames model choice as a trade-off among accuracy, cost, and latency. It is a promotional announcement of a New Defaults conversation, with no benchmark figures or prices given.

## Post

When your inference bill starts climbing, choosing the right model becomes a question of accuracy, cost, and latency.

In our latest New Defaults, OpenRouter’s @cclark sat down with @OsvaldNitski from @mercor to discuss how evals help teams decide when to optimize, switch models, or train their own.

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2117669745541668864%2Fimg%2FU86RQRw2U2GV9WzN.jpg&mode=thumb&exp=1793923200&sig=e1716c06676ffa7f)