# Qwen2.5-Turbo extends context window to 1M tokens

> Qwen released Qwen2.5-Turbo with its context window extended from 128K to 1M tokens (approximately 1 million English words). The release is described as including optimizations for both model capabilities and inference performance at extreme context lengths.

| | |
|---|---|
| **Tool** | Qwen |
| **Version** | — |
| **Kind** | announcement |
| **Published** | 2024-11-14 |
| **Observed** | 2026-08-11 |
| **Significance** | 4/5 |
| **Breaking** | no |
| **Categories** | capability, context-window, new-model |

## What changed


- Context window extended from 128K to 1M tokens (~1M English words)
- Includes optimizations for long-context inference performance


## Sources

- [blog_rss](https://qwenlm.github.io/blog/qwen2.5-turbo/) — retrieved 2026-08-11


## Community

_No curated reactions recorded. Facts and community takes are kept in separate layers
and never blended._

---
Canonical: https://changelogs.info/qwen/qwen2-5-turbo-extends-context-window-to-1m-tokens
Entity: https://changelogs.info/qwen
Event ID: `evt_2024-11-14_qwen_extending-the-context-length-to-1m-tokens`
Licence: event synthesis © changelogs.info, CC BY 4.0. Linked sources belong to their vendors.