Models in Claude Desktop changedgovernment/desktop/models
Nearest release: v2.1.299, published 2 hours after upstream edited the page. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Upstream edited this page at 13 Oct 2026 21:38 UTC, give or take a minute or two: the time comes from Anthropic’s own sitemap rather than from a commit. This site recorded the change at 23 Oct 2026 18:07 UTC.
Upstream edited
Recorded here
Lines+3added
Lines−3removed
From line
4
where the diff opens
First seen
21 Aug 2026
this site's first read of the page
Recorded edits7to this page, all time
The whole hunk
from line 4, old and new numbered
/
from line 4
44
55> **Who this is for:** Anyone who uses Claude Desktop in Claude for Government. The last section is for administrators.
66
7The model picker shows which Claude model answers you and lets you switch to another. It sits at the bottom of the message box in Chat, Cowork, and Code. Which models it lists depends on the [seat tier](/docs/government/account/profile.md) your organization has assigned to you, so a colleague may see a different list.
7The model picker shows which Claude model answers you and lets you switch to another. It sits at the bottom of the message box in Chat, Cowork, and Code. Which models it lists depends on the [seat tier](https://claude.com/docs/government/account/profile.md) your organization has assigned to you, so a colleague may see a different list.
88
99A model that needs a newer version of Claude Desktop does not appear in the picker until the app is updated. If you are missing a model that a colleague on the same seat tier has, update Claude Desktop, or ask your IT administrator to update it.
1010
from line 16
1616>
1717> Before Claude Desktop 2.31226.0, such a model appears twice. To be sure of the larger window, check that the entry marked **1M context window**, or **1M** in Code, is selected when you start new work.
1818
19When a long conversation or task gets close to filling the context window, Claude summarizes the earlier part to make room and carries on from the summary, which the app calls compacting. With a 1M window this happens much later than with a window of about 200,000 tokens (200K), so long pieces of work keep their full detail for longer. Past the point where a 200K window would compact, each further message carries the whole conversation rather than a summary, so it uses more of your [allowance](/docs/government/account/usage.md) and responses can take longer to start.
19When a long conversation or task gets close to filling the context window, Claude summarizes the earlier part to make room and carries on from the summary, which the app calls compacting. With a 1M window this happens much later than with a window of about 200,000 tokens (200K), so long pieces of work keep their full detail for longer. Past the point where a 200K window would compact, each further message carries the whole conversation rather than a summary, so it uses more of your [allowance](https://claude.com/docs/government/account/usage.md) and responses can take longer to start.
2020
2121## Model availability for administrators
2222
23The models a member sees come from the **Allowed models** of their [seat tier](/docs/government/org-admin/seat-tiers.md). Whether a model offers the [1M context window](#larger-context-window) is set by Anthropic for each model rather than in the admin portal. When you change a tier's allowed models, access changes straight away, and the member's model picker shows the change the next time they start Claude Desktop.
23The models a member sees come from the **Allowed models** of their [seat tier](https://claude.com/docs/government/org-admin/seat-tiers.md). Whether a model offers the [1M context window](#larger-context-window) is set by Anthropic for each model rather than in the admin portal. When you change a tier's allowed models, access changes straight away, and the member's model picker shows the change the next time they start Claude Desktop.
2424
2525A long conversation at the 1M window uses more of the spend limits, because each message carries more of the conversation.
2626
No line in this hunk matches that.