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 13 Oct 2026 22:07 UTC.
Upstream edited
Recorded here
Lines+10added
Lines−12removed
From line
1
where the diff opens
First seen
21 Aug 2026
this site's first read of the page
Recorded edits5to this page, all time
The whole hunk
from line 1, old and new numbered
/
from line 1
11# Models in Claude Desktop
22
3> How the model picker in Claude Desktop works in Claude for Government, what the 1M context window entry does for long conversations that would otherwise be compacted at the standard 200K window, how to choose it, and what controls which models you see.
3> Switch models in Claude Desktop on Claude for Government, see what the 1M context window does, and find what controls which models you see.
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) your organization has assigned to you, so a colleague may see a different list. A 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.
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) your organization has assigned to you, so a colleague may see a different list.
88
9A 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.
10
911## Larger context window
1012
11Some models appear in the picker twice. In Chat and Cowork the second entry has **1M context window** under the model's name, and in Code it shows **1M** after the name. Both entries are the same model, and the difference is how much of a conversation Claude can keep in view at once, which is called the context window and is measured in tokens (a token is a short piece of text, roughly a word or part of one). The standard entry keeps up to about 200,000 tokens (200K) in view. The **1M context window** entry keeps up to about one million (1M), five times as much.
13The context window is how much of a conversation Claude can keep in view at once, measured in tokens (a token is a short piece of text, roughly a word or part of one). Some models offer a window of about one million tokens (1M). Such a model appears once in the picker, and new conversations, tasks, and Code sessions on it use the 1M window.
1214
13When 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 the **1M context window** entry this happens much later, so long pieces of work keep their full detail for longer. Until a conversation outgrows the standard entry's window, the two entries behave the same and use the same amount of your [allowance](/docs/government/account/usage). Past that point the **1M context window** entry keeps sending Claude the whole conversation rather than a summary, so each further message uses more of your allowance and responses can take longer to start.
14
15For Cowork tasks on very large document sets, for example hundreds of pages of PDFs, use the **1M context window** entry so Claude can keep more of the documents in view before it compacts.
16
17To use the larger window, open the model picker and choose the model's entry marked **1M context window**, or **1M** in Code. The entry in use has a check mark next to it, and the model name in the message box reads the same for both entries in Chat and Cowork, so open the picker to check. If you have not picked a model before, the larger window may already be selected. The entry appears only for models where Claude for Government offers the larger window, so if no model in your picker has it, ask your organization's owner whether your seat tier can include a model that does.
18
1915<Note>
20 The **1M context window** entry appears in Claude Desktop 1.17377.1 and later. Claude Desktop 1.28929.0 and later also keep the entry you chose for new conversations and after a restart. Versions in between return to the standard entry each time, so choose the **1M context window** entry again when you start new work, or ask your IT administrator to update Claude Desktop.
16 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.
2117</Note>
2218
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) and responses can take longer to start.
20
2321## Model availability for administrators
2422
25The models a member sees come from the **Allowed models** of their [seat tier](/docs/government/org-admin/seat-tiers). Whether a model also offers the **1M context window** entry is set by Anthropic for each model rather than in the admin portal. To see which models offer it, open the model picker in Claude Desktop, which shows the entries for your own seat tier. When you change a tier's allowed models, access changes straight away. A change of either kind, to a tier's allowed models or to which models offer the entry, shows in the picker's list the next time the member starts Claude Desktop.
23The models a member sees come from the **Allowed models** of their [seat tier](/docs/government/org-admin/seat-tiers). 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.
2624
27Usage on either entry counts against the same spend limits. A long conversation on the **1M context window** entry uses more only because each message carries more of the conversation.
25A long conversation at the 1M window uses more of the spend limits, because each message carries more of the conversation.
2826
No line in this hunk matches that.