# 1M Token Long Context Window

### Anthropic Claude: 1M token context

Anthropic’s Claude model family supports expanding the context window from the default 200K tokens to **1,000,000 tokens (1M)**—5× the default capacity. 

{% hint style="info" %}
Infron automatically enables the 1M token context window for Claude Sonnet 4/4.5/4.6 models. No configuration is required.
{% endhint %}

* Learn more: [Announcement](https://www.anthropic.com/news/1m-context), [Context windows docs](https://platform.claude.com/docs/en/build-with-claude/context-windows#1-m-token-context-window)
* Pricing: Requests that exceed 200K tokens are charged at premium rates. See [pricing details](https://docs.anthropic.com/en/about-claude/pricing#long-context-pricing).

With Infron, you can enable this capability effortlessly to handle large-scale document analysis, code review, long-running conversations, and more.

#### Supported Models

The following Claude models currently support the 1M-token context window:

| Model                 | Default Context Window | Extended Context Window |
| --------------------- | ---------------------- | ----------------------- |
| **Claude Opus 4.6**   | 200K tokens            | 1M tokens               |
| **Claude Sonnet 4.5** | 200K tokens            | 1M tokens               |
| **Claude Sonnet 4**   | 200K tokens            | 1M tokens               |

{% hint style="info" %}
The 1M-token context window is currently a Beta feature, and functionality and pricing may change in future versions.
{% endhint %}

#### Long-Context Pricing

When the number of tokens in a request exceeds 200K, long-context pricing will apply automatically. The multipliers are as follows:

| Pricing Item      | Up to 200K         | Over 200K                 |
| ----------------- | ------------------ | ------------------------- |
| **Input tokens**  | 1x (standard rate) | 2x (double rate)          |
| **Output tokens** | 1x (standard rate) | 1.5x (1.5× standard rate) |


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://infronai.gitbook.io/docs/features/1m-token-long-context-window.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.