Active Context

# Choose how much *the model sees.*

Pick 200K, 500K or 1M once. Each thread stays under it, and older turns move to an archive the agent can search.

[Start free](https://context-mode.com/docs/quick-start)[Read the docs](https://context-mode.com/docs/active-context)

How it works

## The thread stays in bounds. *Nothing is thrown away.*

1. 01**Pick a limit** 200K, 500K or 1M, in Settings. It reaches every request within 30 seconds.
2. 02**At 89%** Old tool output and long answers move to the archive. A pointer stays.
3. 03**At the limit** The earliest turns move out in fixed steps. The last 8 messages always stay.

Proof

## A bigger limit *costs less.*

Effective input tokens, same 14 turns

100K limit**282,089** 1M limit**145,364**

fewer cache rewrites

Provider refusals near the window, 60-turn thread

Direct**37** Context Mode**1**

cut before refusal

One live pair, 2026-07-29; refusals from a simulated Claude Code thread in our test harness. Read them as the direction, not the size. [Method →](https://context-mode.com/docs/active-context#choose)

Features

## Long sessions, warm cache.

**No surprise compaction**

Codex, and Claude Code on the 1M window, stay under the point where they compact.

**Your words kept**

Your own messages are never shortened. Text that leaves is in the archive.

**One setting**

Per account, for both agents and every machine.

## Keep the whole session *in reach.*

*npx @context-mode/cli* connects your agents. 1,000 requests free, no card.

[Start free →](https://context-mode.com/docs/quick-start)[Read the docs →](https://context-mode.com/docs/active-context)