> ## Documentation Index
> Fetch the complete documentation index at: https://docs.openserv.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Choose reasoning effort

> Tune reasoning depth against quality, latency, and cost.

<Frame>
  <img src="https://mintcdn.com/openserv/wCXyJJTiOX6drWSJ/images/tutorials/reasoning-effort.webp?fit=max&auto=format&n=wCXyJJTiOX6drWSJ&q=85&s=88ced701d5257bbab5679e31037a470a" alt="Three calibrated reasoning paths balancing depth, speed, and cost" width="1536" height="1024" data-path="images/tutorials/reasoning-effort.webp" />
</Frame>

Reasoning-capable models accept `low`, `medium`, or `high` effort.

```js theme={null}
const response = await client.chat.completions.create({
  model: "gpt-5.4-mini",
  reasoning_effort: "medium",
  messages: [
    { role: "system", content: "Solve constrained planning problems carefully." },
    { role: "user", content: "Plan this project under these constraints: ..." },
  ],
});
```

Start with `low`. Move higher only when evaluation shows a measurable improvement that justifies extra cost and latency.