Agents
Token Budget
A limit on how many tokens a model or agent may spend on a task, used to control cost and stop long runs from sprawling.
In depth
A limit on how many tokens a model or agent may spend on a task, used to control cost and stop long runs from sprawling. Claude's task budgets apply this to agentic loops: you give the model one total covering thinking, tool calls, tool results, and output. The model then sees a running countdown so it can prioritize and wrap up cleanly. A task budget only guides pacing, while max_tokens stays the hard per-request cap that cuts off output when reached.
Primary source: platform.claude.com
Example
In practice, developers reach for Token Budget when they need the capability described above as part of an AI feature or workflow.
Go deeper at Developers Digest
Hands-on guides, comparisons, and tutorials that cover Agents.
FAQ
Common questions
What is Token Budget?
A limit on how many tokens a model or agent may spend on a task, used to control cost and stop long runs from sprawling.
Why does Token Budget matter for AI developers?
Token Budget sits in the Agents part of the AI stack. Understanding it helps you make better decisions when building, debugging, and shipping AI features.
Where can I learn more about Token Budget?
Developers Digest publishes tutorials and videos that cover Agents topics including Token Budget. Check the blog and YouTube channel for hands-on walkthroughs.
Related
Related terms
Agents
Context Editing
A beta Claude API feature that automatically clears stale content from a conversation server-side before it reaches the model, while your client keeps the full history.
Agents
Fable 5
Anthropic's most capable widely released model, launched June 9, 2026 as the first Mythos-class model available for general use, with a 1M-token context window and up to 128K output tokens at $10 per million input and $50 per million output tokens.
Agents
Eval Harness
The infrastructure that runs evals end to end: it feeds tasks to the model or agent, records every step, applies graders, and aggregates the results into scores.
Put this concept to work
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever