Can My Agent Uselookup · compare · cite

Aug 28, 2026 · Catalog foundation is up

Product feature · models-context

Context windowMeasured product property

Record the documented context-window limit by product, model, and mode.

Terminology basis: Measured product property. Google — Gemini Apps limits and context windows

Context window: 2 supported, 1 partial, 0 unsupported, 28 unreviewed across 31 cataloged products.

Markdown · JSON

Explore this familyMore in Models and context11 capabilities

Current evidence by product

Can my agent use Context window?

Read across for the answer. 3 of 31 current product columns have reviewed evidence; unreviewed does not mean unsupported.

Known issues (0)Report an issue
  • Supported2
  • Partial1
  • Unsupported0
  • Unknown28
  • Not applicable0

Web

9 products

Desktop

13 products

CLI

9 products

Unknown means no public evidence has been reviewed for that product and capability. It does not mean unsupported.

How statuses are assigned

Definition and scope

What this capability means

“Context length” is not one provider-wide number. The catalog records the exact harness, selected model or mode, advertised total context window, maximum accepted input when separately documented, reserved output budget, and observation date. Tool definitions, hidden instructions, memory, file extraction, images, video frames, and previous turns may all consume the same budget.

A sourced cell should carry the numeric limit and unit in its evidence note or structured qualifier. Mark it partial when the harness supports the model but enforces a lower cap, exposes only a qualitative label, or dynamically routes among models with different limits. Do not infer a web, desktop, editor, or CLI limit from an API model card unless the harness documentation explicitly adopts it.

Useful conformance work tests boundary behavior: rejection, truncation, silent omission, compaction, retrieval, and “lost in the middle” quality are different outcomes. A large accepted input is not proof that every supplied token remains equally influential.

Traceable compatibility

Assertion ledger

Documentation evidence only. No runtime conformance test is implied.

Geminiweb · current
Supported
Target
2026-08-28 Gemini Apps limits documentation observation · hosted-observation
Environment
hosted-default
Observed
2026-08-28
  • plan32k tokens without an AI plan; 128k with AI Plus; 1 million with AI Pro or AI Ultra
  • runtimethe published window is shared by prompt, chat, and uploaded content and is not a guarantee of uniform attention quality
Evidence
Claude CLIcli · current
Partial
Target
current Claude Code documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • planOpus with 1M context is included on Max, Team, and Enterprise; Pro requires usage credits, and Sonnet 1M requires credits on subscription plans
  • runtimethe [1m] model suffix selects an eligible 1M variant; effective input remains lower after system, tools, history, and output reservations
Evidence
Cursordesktop · current
Supported
Target
current Cursor models documentation · dated-documentation
Environment
local-default
Observed
2026-08-28
  • runtimenormal mode uses 200k tokens; Max Mode extends to the selected model's maximum, with some supported models reaching 1M
  • planMax Mode availability and billing depend on plan and model
Evidence
  1. 1. Evidence checked 2026-08-28: Google publishes Gemini Apps context windows of 32k tokens without an AI plan, 128k with AI Plus, and 1 million with AI Pro or AI Ultra.
  2. 2. Evidence checked 2026-08-28: Anthropic documents 1 million-token Claude Code variants and plan/model eligibility; this is not a claim that every Claude Code session receives 1M context.
  3. 3. Evidence checked 2026-08-28: Cursor documents a normal 200k-token context window and Max Mode up to the maximum supported by the selected model, including models with windows up to 1M.