---
title: Workbench limits
url: https://www.tines.com/stories/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/stories/docs/llms.txt) › [Workbench](https://www.tines.com/llm/stories/docs/workbench.md)*

# Workbench limits

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

| Element | Description |
| --- | --- |
| Context window | Model dependent  
*200,000 tokens  
**1 million tokens* |
| Max output | 8,192 tokens |
| Messages & tool runs per minute per tenant | 25 (EU tenants) 50 (US tenants) 100 (custom AI provider) |
| Input tokens per minute per tenant | 300,000 (EU tenants) 500,000 (US tenants) 1,000,000 (custom AI provider) |
| Default truncation limit (can be disabled) | 50,000 tokens |

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