Skip to main content

AI Usage > Model context tier

Written by Tom Williams

Dataset: AI Usage

Entity: AI Usage Measurement

Field ID: model_context_tier

Type: Select list

Description: The context window tier the model ran with, which is one of the price multipliers a model carries. Possible values are:

  • STANDARD the standard context window.

  • LONG the extended context window.

Not available yet. GitHub Copilot does not publish this measurement, so it is empty on every record you can query today. It is populated by Anthropic Claude and Cursor, which are coming soon.

Source: App

Transformation logic: N/A

App Mapping

GitHub Copilot

N/A - not exposed

Anthropic Claude (coming soon)

Calculated: from the context window grouping on direct API traffic

Cursor (coming soon)

Calculated: from maxMode, Cursor's extended context mode

OpenAI Platform (coming soon)

N/A

OpenAI Codex (coming soon)

N/A

Reporting Use Cases

The Model context tier field distinguishes ordinary requests from extended-context ones, which are priced differently and consume far more input tokens.

  • Understanding input token growth: Long-context work is the usual explanation for input tokens growing much faster than interactions.

  • Cursor max mode adoption: Grouping Cursor records by context tier shows how much of the team's work runs in max mode.

  • Sparsely populated: Only Anthropic and Cursor expose a context tier today.

Did this answer your question?