[GH-ISSUE #34] Use Anthropic Prompt Caching #8

Closed
opened 2026-02-16 06:16:47 -05:00 by yindo · 2 comments
Owner

Originally created by @janpawellek on GitHub (Sep 25, 2025).
Original GitHub issue: https://github.com/langchain-ai/deepagentsjs/issues/34

This project uses claude-sonnet-4-20250514 as the default model, which makes a lot of sense.

However, is it possible to enable Anthropic's prompt caching feature then? This would drastically reduce the cost of an agent run, as Deep Agents may have a large number of long-running tool calls.

Originally created by @janpawellek on GitHub (Sep 25, 2025). Original GitHub issue: https://github.com/langchain-ai/deepagentsjs/issues/34 This project uses `claude-sonnet-4-20250514` as the default model, which makes a lot of sense. However, is it possible to enable Anthropic's [prompt caching feature](https://js.langchain.com/docs/integrations/chat/anthropic/#prompt-caching) then? This would drastically reduce the cost of an agent run, as Deep Agents may have a large number of long-running tool calls.
yindo closed this issue 2026-02-16 06:16:47 -05:00
Author
Owner

@christian-bromann commented on GitHub (Sep 26, 2025):

Will add prompt caching in #32

@christian-bromann commented on GitHub (Sep 26, 2025): Will add prompt caching in #32
Author
Owner

@janpawellek commented on GitHub (Dec 5, 2025):

Added in v1.1.0, thank you!

@janpawellek commented on GitHub (Dec 5, 2025): Added in v1.1.0, thank you!
yindo changed title from Use Anthropic Prompt Caching to [GH-ISSUE #34] Use Anthropic Prompt Caching 2026-06-05 17:20:54 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langchain-ai/deepagentsjs#8