Follow Discord
Sweep 03 Oct 2026 · 20:28Z Build v2.1.289 510 read Stable v2.1.285 Latest v2.1.289 Next v2.1.289 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Code CLI 22 Sep 2026
One change · claude-code

Speed up responses with fast mode changedfast-mode

Nearest release: v2.1.280, published under an hour before 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 22 Sep 2026 16:44 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 28 Sep 2026 23:37 UTC.

Upstream edited
Recorded here
Lines+8added
Lines−8removed
From line 66 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits14to this page, all time

The whole hunk

from line 66, old and new numbered
/
lines
from line 66
6666 
6767Fast mode has higher per-token pricing than standard Opus:
6868 
69| Model | Input (MTok) | Output (MTok) |
70| -------- | ------------ | ------------- |
71| Opus 5.5 | \$8 | \$40 |
72| Opus 5 | \$10 | \$50 |
73| Opus 4.8 | \$10 | \$50 |
69| Model | Input (MTok) | Output (MTok) |
70| - | - | - |
71| Opus 5.5 | \$8 | \$40 |
72| Opus 5 | \$10 | \$50 |
73| Opus 4.8 | \$10 | \$50 |
7474 
7575Fast mode pricing is flat across the full 1M token context window. For the standard Opus rate to compare against, see the [Claude pricing reference](https://platform.claude.com/docs/en/about-claude/pricing).
7676 
from line 102
102102 
103103Fast mode and effort level both affect response speed, but differently:
104104 
105| Setting | Effect |
106| ---------------------- | -------------------------------------------------------------------------------- |
107| **Fast mode** | Same model quality, lower latency, higher cost |
105| Setting | Effect |
106| - | - |
107| **Fast mode** | Same model quality, lower latency, higher cost |
108108| **Lower effort level** | Less thinking time, faster responses, potentially lower quality on complex tasks |
109109 
110110You can combine both: use fast mode with a lower [effort level](/docs/en/model-config#adjust-effort-level) for maximum speed on straightforward tasks.
Feedback