What
- A new
overageScope/limitScopevalue,group_pool, is now recognized alongside the existing org spend-cap and channel scopes, representing a team's shared usage budget rather than an individual member's own cap. - Rate-limit messaging now has dedicated copy for this case: "You've hit your team's shared budget. Switch to another model... to continue," and when overage purchasing is available, "Run /usage-credits to raise it and keep using ${model} or switch models..." (otherwise it points to
/modelto switch models). It also points admins/users at claude.ai/admin-settings/usage. - The Claude-in-Slack usage schema (
CLAUDE_IN_SLACK_V2) gained an optionallimitScopefield with valuesservice/channel/group_pool, so denied requests in Slack report which kind of limit was hit. - The scope value itself is now parsed generically from a response header via a helper, instead of being hardcoded to the literal string
'channel', so other scope values (likegroup_pool) can be recognized and propagated through telemetry.
Why
This lets Claude Code tell users precisely when they've hit a team-wide pooled budget rather than their own individual limit, and point them at the right next step (raising the pool, switching models, or contacting an admin) instead of a generic rate-limit message.
Names in the bundle/usage-credits/model
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added since
A small documentation edit on Error reference touched a line naming /usage-credits after this was published.
* On Team and Enterprise, increase the limit in [**Organization settings > Usage**](https://claude.ai/admin-settings/usage) if you manage billing, or ask an admin to. `/usage-credits` sends that request to your admin for youerrors see the edit
Confirmed since
Anthropic's documentation has since written up /usage-credits, on Error reference.
* On Pro and Max, increase your monthly spend limit in [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, or run `/usage-credits`errors see the edit
Added since
A small documentation edit on Deploy Claude Desktop on 3P with an LLM gateway touched a line naming /model after this was published.
If your gateway serves a Claude model under an opaque routing alias, it can mark the model as Claude by returning an `anthropic_family_tier` field (a Claude tier name such as `sonnet` or `opus`) on that model object in its `/v1/models` res…third-party/claude-desktop/gateway see the edit
Confirmed since
Anthropic's documentation has since written up /model, on Claude Code changelog.
* Added `CLAUDE_CODE_GATEWAY_MODEL_DISCOVERY_TIMEOUT_MS` to extend the LLM gateway `/v1/models` discovery timeout (default 3s)changelog see the edit
One source agreesOne thing we can check says the same as this entry.
Anthropic's documentation agrees
Anthropic's documentation has since written up /model, on Claude Code changelog.