425 pages for budget.

Delete a Credential Claude Developer Platform · in the page api/beta/vaults/credentials/delete …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… List Credentials Claude Developer Platform · in the page api/beta/vaults/credentials/list …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… Validate an MCP OAuth Credential Claude Developer Platform · in the page api/beta/vaults/credentials/mcp_oauth_validate …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… Retrieve a Credential Claude Developer Platform · in the page api/beta/vaults/credentials/retrieve …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… Update a Credential Claude Developer Platform · in the page api/beta/vaults/credentials/update …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… Delete a Vault Claude Developer Platform · in the page api/beta/vaults/delete …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… List Vaults Claude Developer Platform · in the page api/beta/vaults/list …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… Retrieve a Vault Claude Developer Platform · in the page api/beta/vaults/retrieve …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… Update a Vault Claude Developer Platform · in the page api/beta/vaults/update …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… Webhooks Claude Developer Platform · in the page api/beta/webhooks …id: string` - `workspace_id: string` - `BetaWebhookSessionBudgetReachedEventData object` - `type: "session.budget_reached"` - `id: string` ID of the session that tri… Completions Claude Developer Platform · in the page api/completions …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… Create a Text Completion Claude Developer Platform · in the page api/completions/create …nnels-2026-06-22"` - `"structured-outputs-2025-11-13"` - `"task-budgets-2026-03-13"` - `"thinking-display-updates-2026-08-18"` - `"ce-user-management-2026-07-13"` - `"mid-conversation-o… errors Claude Developer Platform · in the page api/errors …not supported on this model ``` Use `thinking: {"type": "enabled", "budget_tokens": N}` on these models; see [Extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinki… Messages Claude Developer Platform · in the page api/messages …nk. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, and w… Batches Claude Developer Platform · in the page api/messages/batches …nk. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, a… Create a Message Batch Claude Developer Platform · in the page api/messages/batches/create …nk. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, a… Count tokens in a Message Claude Developer Platform · in the page api/messages/count_tokens …nk. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, and w… Create a Message Claude Developer Platform · in the page api/messages/create …nk. With `{"type": "enabled"}` (manual extended thinking), you set a `budget_tokens` of at least 1,024. Thinking tokens count toward your `max_tokens` limit. Which `type` values are accepted, and w… Models Claude Developer Platform · in the page api/models …ts thinking with type 'enabled' (extended thinking with a caller-set `budget_tokens`). - `created_at: string` RFC 3339 datetime string representing the time at which the model was released. Ma… List Models Claude Developer Platform · in the page api/models/list …ts thinking with type 'enabled' (extended thinking with a caller-set `budget_tokens`). - `created_at: string` RFC 3339 datetime string representing the time at which the model was released. Ma… Get a Model Claude Developer Platform · in the page api/models/retrieve …ts thinking with type 'enabled' (extended thinking with a caller-set `budget_tokens`). - `created_at: string` RFC 3339 datetime string representing the time at which the model was released. Ma… spans Claude Developer Platform · in the page api/opentelemetry/spans …| | `anthropic.thinking.budget_tokens` | `int` | The [`budget_tokens`](https://platform.claude.com/docs/en/api/messages#thinking_config_enabl… sent_count = len(messages sent in the compaction request) Claude Developer Platform · in the page build-with-claude/compaction …end puts response ``` </CodeGroup> #### Enforcing a total token budget When a model works on long tasks with many tool-use iterations, total token consumption can grow significantly. You can co… compaction-background Claude Developer Platform · in the page build-with-claude/compaction-background …ThreadPoolExecutor(max_workers=1) # Set this near your real input budget. It is low here so a short conversation compacts. COMPACT_AT_TOKENS = 2500 SYSTEM = "You help design a recipe app's dat… compaction-keep-recent-turns Claude Developer Platform · in the page build-with-claude/compaction-keep-recent-turns …client = anthropic.Anthropic() # Set this near your real input budget. It is low here so a short conversation compacts. COMPACT_AT_TOKENS = 2500 SYSTEM = "You help design a recipe app's dat… compaction-on-demand Claude Developer Platform · in the page build-with-claude/compaction-on-demand …so that a short conversation compacts. Set yours near your real input budget. <CodeGroup exclude="shell"> ```python Python from anthropic.types.beta import BetaMessageParam client = anthropic.… compaction-threshold Claude Developer Platform · in the page build-with-claude/compaction-threshold …end puts response ``` </CodeGroup> #### Enforcing a total token budget When a model works on long tasks with many tool-use iterations, total token consumption can grow significantly. You can co… context-windows Claude Developer Platform · in the page build-with-claude/context-windows …ss:** these models track their remaining context window (their "token budget") throughout a conversation. This lets the model manage long-running tasks against the space that remains rather than guess… effort Claude Developer Platform · in the page build-with-claude/effort …| Long-running agentic and coding tasks (over 30 minutes) with token budgets in the millions | | `high` | Spends as many tokens as the task needs for excellent results. The default on every model t… extended-thinking Claude Developer Platform · in the page build-with-claude/extended-thinking …thinking description: Configure manual extended thinking with a fixed budget_tokens budget on Claude models that support it, and migrate to adaptive thinking. --- <Note> To learn how zero data rete… mid-conversation-effort-example Claude Developer Platform · in the page build-with-claude/mid-conversation-effort-example …ss restarts and is safe under concurrent writers across machines. * **Budget enforcement:** track total subagents launched across the whole session, not just for each Workflow call, and refuse to exce… mid-conversation-system-messages Claude Developer Platform · in the page build-with-claude/mid-conversation-system-messages …auto-approve setting, available tools changed, or the remaining token budget dropped below a threshold. * **User input that should not interrupt an agentic loop.** A user types a follow-up while Claud… preserved-thinking Claude Developer Platform · in the page build-with-claude/preserved-thinking …el `system` prompt on each request to carry the current time, a token budget, a mode flag, or newly discovered project context. That invalidates every thinking block in the conversation. Instead, free… Request 2 caches its request content (not the response) Claude Developer Platform · in the page build-with-claude/prompt-caching …el-specific | ✘ | The thinking configuration (mode, and `budget_tokens` in extended mode) is rendered into the prompt, so changing it always invalidates message blocks; tool and system ca… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …you need a hard ceiling on thinking costs, extended thinking with a `budget_tokens` cap is still functional on Opus 4.6 and Sonnet 4.6 but is deprecated. On Claude 4.7 and later models, setting `budg… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …thinking only, summarized-only thinking output, no extended thinking budgets), see [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#configuring-thinking). For the `refusal` s… prompting-claude-haiku-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-haiku-5-5 …effort level to run, or your Claude Haiku 4.5 requests set a thinking budget: [Use effort to control thinking](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …ude Opus 4.8 at `max` or `xhigh` effort, set a large max output token budget so the model has room to think and act across its subagents and tool calls. Start at 64k tokens and tune from there. </Note… prompting-claude-opus-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5 …DE_MAX_CONCURRENT_SUBAGENTS` environment variables and the SDK's `max_budget_usd` (typescript: `maxBudgetUsd`) option. Older versions of Claude Code don't have them, so update Claude Code and any pinn… prompting-claude-opus-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-5-5 …you can estimate how long the task should take, give the model a time budget: have your harness add a short line at the end of each message it sends back to the model giving the elapsed time against t… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …it directly. Manual extended thinking (`thinking: {type: "enabled", budget_tokens: N}`) is not supported on Claude Sonnet 5 and returns a 400 error. It was deprecated on Claude Sonnet 4.6 and is now… prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …gineering/prompting-claude-sonnet-5-5#mid-turn-user-messages-and-task-budgets) * Code changes are reported as done without a test or build run: [Verification on coding tasks](https://platform.claude.c… refusals-and-fallback Claude Developer Platform · in the page build-with-claude/refusals-and-fallback …lly earns another refusal. Point the retry at the fallback model. * **Budget retries for each request, not for each turn or session.** A single turn can produce several refusals, for example an agent… skills-guide Claude Developer Platform · in the page build-with-claude/skills-guide …"user", "content": "Create an Excel file with a simple budget spreadsheet", } ], tools=[{"type": "code_execution_20250825", "name": "code_execution"}], ) # S… thinking Claude Developer Platform · in the page build-with-claude/thinking …| No `thinking` field | `"adaptive"` | `"enabled"` with `budget_tokens` | `"between_tools"` | `"disabled"` | | --------------------… thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …o start with a thinking block. (Models using a legacy manual thinking budget enforce that the final assistant turn of a thinking-enabled request starts with one; see [Turn structure in manual mode](ht… thinking-tool-workflows Claude Developer Platform · in the page build-with-claude/thinking-tool-workflows …pport only extended thinking, substitute `thinking: {type: "enabled", budget_tokens: N}`. The round-trip rules are identical. ## Walk through a two-turn tool-use round trip The example defines a `ge… thinking-troubleshooting Claude Developer Platform · in the page build-with-claude/thinking-troubleshooting …ing), a legacy manual mode configured as `thinking: {type: "enabled", budget_tokens: N}`. Extended thinking (`thinking.type: "enabled"` with `budget_tokens`) is deprecated on the Claude 4.6 models (r… vision-coordinates Claude Developer Platform · in the page build-with-claude/vision-coordinates …width / 28⌉ × ⌈height / 28⌉` does not exceed the model's visual token budget (1,568 tokens on the standard tier, 4,784 on the high-resolution tier). See [Resolution and token cost](https://platform.c… working-with-messages Claude Developer Platform · in the page build-with-claude/working-with-messages …ema-validated JSON output from Claude. </Card> <Card title="Task budgets" icon="gauge" href="https://platform.claude.com/docs/en/build-with-claude/task-budgets"> Set an advisory token budget…