425 pages for budget.

API usage primer for Claude Claude Developer Platform · in the page claude_api_primer …e.com/docs/en/build-with-claude/effort) parameter rather than a token budget. Adaptive thinking is supported on Claude 4.6 and later models and Claude Mythos Preview. On Claude 5 and later models and… openai-sdk Claude Developer Platform · in the page cli-sdks-libraries/libraries/openai-sdk …"Who are you?"}], extra_body={"thinking": {"type": "enabled", "budget_tokens": 2000}}, ) ``` ```typescript TypeScript const response = await openai.chat.completions.create({ messag… compliance-api Claude Developer Platform · in the page manage-claude/compliance-api …shared limit, and the remote session endpoints carry a second request budget on top. See [429 Too Many Requests](https://platform.claude.com/docs/en/manage-claude/compliance-errors#429-too-many-reques… compliance-errors Claude Developer Platform · in the page manage-claude/compliance-errors …aude/compliance-api#how-the-compliance-api-works)**. The limit is one budget shared across every key under the parent (Compliance Access Keys and the Admin API keys of all linked organizations) and ac… before_id is the first_id from a previous response Claude Developer Platform · in the page manage-claude/compliance-integration-patterns …ession endpoints, the remote session endpoints carry a second request budget on top. See [429 Too Many Requests](https://platform.claude.com/docs/en/manage-claude/compliance-errors#429-too-many-reques… compliance-sessions Claude Developer Platform · in the page manage-claude/compliance-sessions …Compliance API rate limit; they are not subject to the second request budget that applies to the remote session endpoints. See [429 Too Many Requests](https://platform.claude.com/docs/en/manage-claude… inference-hooks-configuration Claude Developer Platform · in the page manage-claude/inference-hooks-configuration …verdict timeout (ms)**: 1 to 10,000ms, with a default of 5,000ms. The budget covers the entire exchange, and a slower verdict counts as an unreachable server, so set the lowest value your server can r… inference-hooks-endpoint Claude Developer Platform · in the page manage-claude/inference-hooks-endpoint …ts a verdict timeout between 1 and 10,000ms (5,000ms by default). The budget covers the entire exchange: connection, TLS handshake, request, and response. The same timeout applies to tool call frames.… plugins-api Claude Developer Platform · in the page manage-claude/plugins-api …, `marketplace_repo_access_denied`, `marketplace_sync_transient_fetch_budget_exhausted`, `marketplace_validate_network_error`, and usually `marketplace_validate_deadline_exceeded`. ## Unrecognized va… spend-limits-api Claude Developer Platform · in the page manage-claude/spend-limits-api …er inheriting it is gated against their own spend, not a pooled group budget. Reading `GET /v1/organizations/spend_limits/effective` returns every current member with their resolved effective spend l… First request Claude Developer Platform · in the page manage-claude/usage-cost-api …backs * **Cache efficiency:** Measure and optimize prompt caching * **Budget monitoring:** Set up alerts for spending thresholds * **CSV export:** Generate reports for finance teams ## Frequently ask… dreams Claude Developer Platform · in the page managed-agents/dreams …`timeout` | The pipeline exceeded its runtime budget. | | `internal_error` | Unclassified pipeline failur… events-and-streaming Claude Developer Platform · in the page managed-agents/events-and-streaming …-streaming#answer-tool-calls-that-pause-the-session). | | `budget_reached` | The session's tracked list cost reached its [budget](https://platform.claude.com/docs/en/managed-agents/budget… multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …cross-checking. | Every agent in a run uses tokens, so set a [session budget](https://platform.claude.com/docs/en/managed-agents/budgets) to cap the session's spend, runs included. Tell the agent in i… reference Claude Developer Platform · in the page managed-agents/reference …Carries the session's usage totals and, if the session has one, its [budget](https://platform.claude.com/docs/en/managed-agents/budgets).… scheduled-deployments Claude Developer Platform · in the page managed-agents/scheduled-deployments …n missed or duplicate executions are unacceptable. </Note> ### Set a budget on each run Pass the optional `budget` (csharp, go: `Budget`) object when you create or update the deployment. It takes th… secure-deployment Claude Developer Platform · in the page managed-agents/secure-deployment …| `budget` on each session and deployment | A cap sized to what you expect a run to cost… secure-deployment-monitoring Claude Developer Platform · in the page managed-agents/secure-deployment-monitoring …| | Sessions that reach a budget or terminate | The `session.budget_reached` and `session.status_terminated` webhooks… secure-deployment-risks Claude Developer Platform · in the page managed-agents/secure-deployment-risks …| The tool set, permission policies, and budget that you set… session-observability Claude Developer Platform · in the page managed-agents/session-observability …data, its cumulative cost over time, and spend against the session's [budget](https://platform.claude.com/docs/en/managed-agents/budgets) when one is set.… session-operations Claude Developer Platform · in the page managed-agents/session-operations …p/sse"} ] } ) ``` </CodeGroup> ## Updating the session budget A session [created with a budget](https://platform.claude.com/docs/en/managed-agents/sessions#set-a-session-budget) accept… session-threads Claude Developer Platform · in the page managed-agents/session-threads …managed-agents/workflow-runs#know-when-the-work-is-done). A [session budget](https://platform.claude.com/docs/en/managed-agents/budgets) is a single shared cap across all of a session's threads. As t… sessions Claude Developer Platform · in the page managed-agents/sessions …en/managed-agents/agent-setup) for details. </Tip> ### Set a session budget To cap what a session can spend, pass the optional `budget` (csharp, go: `Budget`) object when you create it. A budget is… webhooks Claude Developer Platform · in the page managed-agents/webhooks …| | `session.budget_reached` | The session reached its [budget](https://platform.claude.com/docs/en/managed-agents/budgets) and pause… workflow-runs Claude Developer Platform · in the page managed-agents/workflow-runs …ates and events, when the work is done, requests while a run is open, budgets, and limits." featureMetadata: topic: title: Managed Agents url: https://platform.claude.com/docs/en/managed-age… Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations: Claude Developer Platform · in the page models/fable-5-1/migration-guide …isabled"}` and manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) return a 400 error. * **Prefill:** Prefilling the assistant message returns a 400 error, unchanged from Claude… overview Claude Developer Platform · in the page models/fable-5-1/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… whats-new-fable-5-1 Claude Developer Platform · in the page models/fable-5-1/whats-new-fable-5-1 …Adaptive thinking is always on. `thinking: {"type": "enabled"}` with `budget_tokens` and `thinking: {"type": "disabled"}` both return a 400 error. Omit `thinking` or send `{"type": "adaptive"}`. * `th… overview Claude Developer Platform · in the page models/fable-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… overview Claude Developer Platform · in the page models/haiku-4-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… migration-guide Claude Developer Platform · in the page models/haiku-5-5/migration-guide …unt-tokens). 3. If your requests send `thinking: {"type": "enabled", "budget_tokens": N}`, change `thinking` to `{"type": "adaptive"}`. See [Configure thinking](https://platform.claude.com/docs/en/mod… overview Claude Developer Platform · in the page models/haiku-5-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… whats-new-haiku-5-5 Claude Developer Platform · in the page models/haiku-5-5/whats-new-haiku-5-5 …| Breaking | Replace `budget_tokens` with adaptive thinking.… overview Claude Developer Platform · in the page models/mythos-5-1/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… overview Claude Developer Platform · in the page models/mythos-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… overview Claude Developer Platform · in the page models/opus-4-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… overview Claude Developer Platform · in the page models/opus-4-6/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… overview Claude Developer Platform · in the page models/opus-4-7/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… overview Claude Developer Platform · in the page models/opus-4-8/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …g) is always on. `thinking: {"type": "disabled"}` and manual thinking budgets (`thinking: {"type": "enabled", "budget_tokens": N}`) are rejected. See the [before and after for thinking](https://platfo… overview Claude Developer Platform · in the page models/opus-5-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… whats-new-opus-5-5 Claude Developer Platform · in the page models/opus-5-5/whats-new-opus-5-5 …on: a request that sets `thinking: {"type": "disabled"}`, or a manual budget with `thinking: {"type": "enabled", "budget_tokens": N}`, returns a 400 `invalid_request_error`. Omit the `thinking` field,… overview Claude Developer Platform · in the page models/opus-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… Models overview Claude Developer Platform · in the page models/overview …by effort. Extended thinking is the manual thinking.type “enabled” + budget\_tokens mode on earlier models; it is deprecated on Claude Opus 4.6 and Claude Sonnet 4.6 and not accepted on later models.… overview Claude Developer Platform · in the page models/sonnet-4-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… overview Claude Developer Platform · in the page models/sonnet-4-6/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …type. It leaves out five settings that return a 400 error: [thinking budgets](https://platform.claude.com/docs/en/models/sonnet-5-5/migration-guide#sonnet-46-breaking-changes), [sampling parameters](… overview Claude Developer Platform · in the page models/sonnet-5-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va… whats-new-sonnet-5-5 Claude Developer Platform · in the page models/sonnet-5-5/whats-new-sonnet-5-5 …adaptive thinking. `between_tools` takes no other field: `display`, `budget_tokens`, or `block_binding` sent with it returns a 400 error. Manual thinking budgets (`thinking: {"type": "enabled", "budg… overview Claude Developer Platform · in the page models/sonnet-5/overview …how much to think, steered by effort. Extended thinking is the manual budget\_tokens mode on earlier models. * **Default effort:** The effort parameter’s default on the Claude API. Models without a va…