---
title: Workbench limits
url: https://www.tines.com/docs/workbench/workbench-limits/
updated: 2026-04-27T10:59:36+00:00
---

*[tines.com](https://www.tines.com/llms.txt) › [Docs](https://www.tines.com/llms.txt) › [Workbench](https://www.tines.com/llm/docs/workbench.md)*

# Workbench limits

*[View on tines.com](https://www.tines.com/docs/workbench/workbench-limits/)*

<table border="1" height="263" style="border-collapse: collapse;"><tbody><tr><td>Element</td><td>Description</td></tr><tr><td>Context window</td><td><p>Model dependent<br><em>200,000 tokens<br></em><em>1 million tokens</em></p></td></tr><tr><td>Max output</td><td>8,192 tokens</td></tr><tr><td>Messages &amp; tool runs per minute per tenant</td><td><p>25 (EU tenants)</p><p>50 (US tenants)</p><p>100 (custom AI provider)</p></td></tr><tr><td>Input tokens per minute per tenant</td><td><p>300,000 (EU tenants)</p><p>500,000 (US tenants)</p><p>1,000,000 (custom AI provider)</p></td></tr><tr><td>Default truncation limit (can be disabled)</td><td><p>50,000 tokens</p></td></tr></tbody></table>

To better understand what a token is, check out [Anthropic's docs here](https://docs.anthropic.com/en/docs/resources/glossary#tokens).