You can now set a budget on a Claude Managed Agents session: a hard cap on the session's spend
By Steven Van ·
You can now set a budget on a Claude Managed Agents session: a hard cap on the session's spend, priced at public list rates.
Anthropic's Claude Managed Agents sessions can now be capped with a budget: a hard limit on spend, priced at public list rates. A session that reaches its budget pauses with the "budget_reached" stop reason instead of starting new model requests; changing or removing the budget resumes it. Deployments apply the same budget to each session they start.
The same update adds a few other controls for Managed Agents sessions:
- An advisor role: a model at least as capable as the agent's own that the session's primary thread can consult mid-turn for strategic guidance, added as a {"type": "advisor"} entry in the agent's multiagent roster.
- Control over where model inference runs, set with inference_geo inside the model object when an agent is created, or overridden for a single session.
- Skills loaded from a GitHub repository: when a session mounts a repository, any skills in its root .claude/skills directory are discovered automatically at session start.
Anthropic
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.
View Anthropic →