api-20261009T153709Z / documentation capture

about-claude/model-deprecations Changed · +8 / -8 lines

from line 126

126126

127127| Retirement date | Deprecated model | Recommended replacement |

128128| --------------- | -------------------------- | ----------------------- |

129| June 15, 2026 | `claude-sonnet-4-20250514` | `claude-sonnet-4-6` |

129| June 15, 2026 | `claude-sonnet-4-20250514` | `claude-sonnet-5-5` |

130130| June 15, 2026 | `claude-opus-4-20250514` | `claude-opus-4-8` |

131131

132132### 2026-02-19: Claude Haiku 3 model

from line 163

163163

164164| Retirement date | Deprecated model | Recommended replacement |

165165| ----------------- | ---------------------------- | ----------------------- |

166| February 19, 2026 | `claude-3-7-sonnet-20250219` | `claude-sonnet-4-6` |

166| February 19, 2026 | `claude-3-7-sonnet-20250219` | `claude-sonnet-5-5` |

167167

168168### 2025-08-13: Claude Sonnet 3.5 models

169169

from line 175

175175

176176| Retirement date | Deprecated model | Recommended replacement |

177177| ---------------- | ---------------------------- | ----------------------- |

178| October 28, 2025 | `claude-3-5-sonnet-20240620` | `claude-sonnet-4-6` |

179| October 28, 2025 | `claude-3-5-sonnet-20241022` | `claude-sonnet-4-6` |

178| October 28, 2025 | `claude-3-5-sonnet-20240620` | `claude-sonnet-5-5` |

179| October 28, 2025 | `claude-3-5-sonnet-20241022` | `claude-sonnet-5-5` |

180180

181181### 2025-06-30: Claude Opus 3 model

182182

from line 202

202202| --------------- | -------------------------- | ----------------------- |

203203| July 21, 2025 | `claude-2.0` | `claude-opus-4-8` |

204204| July 21, 2025 | `claude-2.1` | `claude-opus-4-8` |

205| July 21, 2025 | `claude-3-sonnet-20240229` | `claude-sonnet-4-6` |

205| July 21, 2025 | `claude-3-sonnet-20240229` | `claude-sonnet-5-5` |

206206

207207### 2024-09-04: Claude 1 and Instant models

208208

from line 226

226226

227227Anthropic occasionally deprecates request parameters that no longer apply to current models. How the API treats a deprecated parameter depends on the model, as the following table shows. Most SDKs keep deprecated parameters in their request types so existing code continues to type-check. The Python SDK (v1.0 and later) removes `temperature`, `top_p`, and `top_k`, so passing them raises a `TypeError`.

228228

230| ------------------------------- | -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |

231| `temperature`, `top_p`, `top_k` | Deprecated (Claude Opus 4.7 and later) | Returns a 400 error when set to a non-default value on Claude 4.7 and later models and [Claude Mythos Preview](https://anthropic.com/glasswing). | Omit and use [prompting](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices) to guide model behavior. |

230| ------------------------------- | ---------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------- |

231| `temperature`, `top_p`, `top_k` | Deprecated (Claude 4.7 and later models) | Returns a 400 error when set to a non-default value on Claude 4.7 and later models and [Claude Mythos Preview](https://anthropic.com/glasswing). | Omit and use [prompting](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claude-prompting-best-practices) to guide model behavior. |

232232

233233For migration steps, see the [migration guide](https://platform.claude.com/docs/en/about-claude/models/migration-guide).

234234

about-claude/models/choosing-a-model Changed · +5 / -1 lines

from line 11

1111* **Capabilities:** What specific features or capabilities will you need the model to have to meet your needs?

1212* **Speed:** How quickly does the model need to respond in your application? Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8 support [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) (research preview), which delivers up to 2.5x higher output speed at premium pricing.

1313* **Cost:** What's your budget for both development and production usage?

14* **Effort:** Several Claude models support an [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) that trades intelligence for latency and cost within a single model. Tuning effort is often a better lever than switching models. On Claude Fable 5.1 and Claude Opus 5, start with the default (`high`) and adjust up or down based on your evals. On Claude Opus 5.5 and Claude Haiku 5.5 the default is `medium`; start there and adjust the same way. On Claude Opus 4.8 and Claude Opus 4.7, the `xhigh` effort level, between `high` and `max`, is the best setting for most coding and agentic use cases.

14* **Effort:** Several Claude models support an [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) that trades intelligence for latency and cost within a single model. Tuning effort is often a better lever than switching models. On Claude Fable 5.1, Claude Opus 5, and Claude Sonnet 5.5, start with the default (`high`) and adjust up or down based on your evals. On Claude Opus 5.5 and Claude Haiku 5.5 the default is `medium`; start there and adjust the same way. On Claude Opus 4.8 and Claude Opus 4.7, the `xhigh` effort level, between `high` and `max`, is the best setting for most coding and agentic use cases.

1515

1616***

1717

from line 109

109109

110110 <Card title="What's new in Claude Sonnet 5.5" icon="sparkle" href="https://platform.claude.com/docs/en/models/sonnet-5-5/whats-new-sonnet-5-5">

111111 The latest Sonnet model: breaking changes, new features, and behavior differences

112 </Card>

113

114 <Card title="What's new in Claude Haiku 5.5" icon="sparkle" href="https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5">

115 The latest Haiku model: breaking changes, new features, and behavior differences

112116 </Card>

113117

114118 <Card title="Start building" icon="code" href="https://platform.claude.com/docs/en/get-started">

about-claude/models/optimizing-for-cost-and-intelligence Changed · +21 / -12 lines

from line 132

132132

133133Several things can break your cache during a task. Anything that changes per request, such as a timestamp or a queue position, placed ahead of the stable prefix turns every request into a full cache write: on the triage run in [Trim input and context tokens](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#trim-input-and-context-tokens), a 25-token status line at the front of the system prompt cost $4.24 USD per run instead of $0.59 USD, more than running with caching off. Keep per-request text in the newest user turn.

134134

135The cache is a byte-exact prefix match over the request in order (tools, then system prompt, then messages), so a change anywhere invalidates everything after it. Changing [`effort`](https://platform.claude.com/docs/en/build-with-claude/effort) or the thinking configuration between requests invalidates the cache from that point onward, and on some models the tools and system prompt ahead of it as well; any edit to the system prompt invalidates the cache from that point onward; setting or changing an output format invalidates the cache for the whole conversation; adding, removing, or reordering a tool definition invalidates all of it. The [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#what-invalidates-the-cache) page lists these cases, apart from the output format, which [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#prompt-modification-and-token-costs) covers. On the most recent models, change instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), a `{"role": "system"}` message appended to `messages`, instead of editing the top-level `system` field: the cached prefix stays intact. Check that page for which models support it. On models that support it, a [per-message effort change](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) leaves the cached prefix intact too. The stakes are highest on Claude Fable 5.1 and Claude Mythos 5.1, where a break re-writes the prefix at 1.25x the input price instead of reading it at 0.025x. On a 100,000-token prefix, one broken turn there costs $1.25 USD instead of $0.03 USD, 50 times the read; on Claude Opus 5.5 it costs $0.50 USD instead of $0.02 USD, and on Claude Sonnet 5.5 $0.25 USD instead of $0.01 USD, 25 times, and on the other current models 12.5 times.

135The cache is a byte-exact prefix match over the request in order (tools, then system prompt, then messages), so a change anywhere invalidates everything after it. Changing [`effort`](https://platform.claude.com/docs/en/build-with-claude/effort) or the thinking configuration between requests invalidates the cache from that point onward, and on some models the tools and system prompt ahead of it as well; any edit to the system prompt invalidates the cache from that point onward; setting or changing an output format invalidates the cache for the whole conversation; adding, removing, or reordering a tool definition invalidates all of it. The [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#what-invalidates-the-cache) page lists these cases, apart from the output format, which [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs#prompt-modification-and-token-costs) covers. On the most recent models, change instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), a `{"role": "system"}` message appended to `messages`, instead of editing the top-level `system` field: the cached prefix stays intact. Check that page for which models support it. A per-message effort change leaves the cached prefix intact too, but on fewer models: [Change effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#changing-effort-mid-conversation) lists them. The stakes are highest on Claude Fable 5.1 and Claude Mythos 5.1, where a break re-writes the prefix at 1.25x the input price instead of reading it at 0.025x. On a 100,000-token prefix, one broken turn there costs $1.25 USD instead of $0.03 USD, 50 times the read; on Claude Opus 5.5 it costs $0.50 USD instead of $0.02 USD, and on Claude Sonnet 5.5 $0.25 USD instead of $0.01 USD, 25 times, and on the other current models 12.5 times.

136136

137137Anthropic measured this on the triage agent's long sessions[18](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs). An effort change and an added tool made mid-session rewrote 39,000 and 60,000 cached tokens, and those sessions cost $0.95 USD per session. The same two changes on the first request after compaction cost $0.75 USD, and on the request that triggered the compaction $0.92 USD, because the compaction's summarization pass then re-processed the 81,000-token context at the cache-write price: that summarization pass cost $0.21 USD, against $0.04 USD when the same changes came one request later, with accuracy within run-to-run noise in every arm:

138138

from line 302

302302

303303On harder work the gap widens. On Terminal-Bench 3[20](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-intelligence#refs), where the tasks are hard enough that pass rate rather than tokens sets the bill, Claude Opus 4.7, Opus 4.8, and Opus 5 each spend $8 USD to $15 USD per task but solve 7%, 15%, and 41% of tasks, so cost per solved task falls from $183 USD to $63 USD to $28 USD up the ladder. The 21% premium Claude Opus 5 carries over Opus 4.8 on the saturated coding subset becomes a 56% saving on Terminal-Bench 3, where the older model mostly fails: the more your workload defeats the old model, the more the upgrade saves per result.

304304

305Compare on cost per solved task, not per token: the same text costs about 30% more tokens on Claude Opus 4.7 and later, so a per-token comparison makes the newer models look more expensive by construction.

305Compare on cost per solved task, not per token: the same text costs about 30% more tokens on Claude 4.7 and later models, so a per-token comparison makes the newer models look more expensive by construction.

306306

307307### Tune effort

308308

from line 602

602602

603603The numbers on this page reflect list prices at the time of measurement and will drift as models and prices change. Your escalation rate, how cleanly tasks split, and transcript length move them too. The method stays the same:

604604

6051. Pull a few tasks from production logs, weighted like real traffic, and [write outcome checks](https://platform.claude.com/docs/en/test-and-evaluate/develop-tests) for each: tests pass, ticket closed, row count correct. Record cost per task beside the score: price the five priced token counts in each response's `usage` at their own rates (uncached input, 5-minute and 1-hour cache writes at 1.25x and 2x the input price, cache reads, and output), summed across the task's requests (the [Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api) reports the aggregate).

6051. Pull a few tasks from production logs, weighted like real traffic, and [write outcome checks](https://platform.claude.com/docs/en/test-and-evaluate/develop-tests) for each: tests pass, ticket closed, row count correct. Record cost per task beside the score: price the five priced token counts in each response's `usage` at their own rates (uncached input, 5-minute and 1-hour cache writes at 1.25x and 2x the input price, cache reads, and output), summed across the task's requests (the [Usage and Cost API](https://platform.claude.com/docs/en/manage-claude/usage-cost-api) reports the aggregate). On a model priced by prompt length, such as Claude Haiku 5.5, price each request at the rates for its prompt length: a request whose prompt, cache reads and writes included, is over the model's threshold pays the higher prices for all of its tokens (see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing)).

6066062. Baseline the model tiers across effort levels, not only the default, and plot score against spend. A multi-model configuration must beat the single model's whole curve.

6076073. If the curve shows a gap effort can't close, add the multi-model strategy that fits and re-run the suite.

6086084. Run the winner in shadow on a traffic slice before cutover, then keep the suite running.

from line 611

611611

612612<CodeGroup>

613613 ```bash cURL

614 # Per-million-token prices from the pricing page; change these three for another model.

614 # Per-million-token prices from the pricing page; change these for another model.

615 # A model priced by prompt length, such as Claude Haiku 5.5, charges its long-prompt prices over its threshold.

615616 INPUT_PER_MTOK=4.00 # Claude Opus 5.5

616617 CACHE_READ_PER_MTOK=0.20 # 0.05x the input price on Claude Opus 5.5; the multiplier differs by model

617618 OUTPUT_PER_MTOK=20.00

from line 639

638639 ```

639640

640641 ```bash CLI

641 # Per-million-token prices from the pricing page; change these three for another model.

642 # Per-million-token prices from the pricing page; change these for another model.

643 # A model priced by prompt length, such as Claude Haiku 5.5, charges its long-prompt prices over its threshold.

642644 INPUT_PER_MTOK=4.00 # Claude Opus 5.5

643645 CACHE_READ_PER_MTOK=0.20 # 0.05x the input price on Claude Opus 5.5; the multiplier differs by model

644646 OUTPUT_PER_MTOK=20.00

from line 662

660662 ```

661663

662664 ```python Python

663 # Per-million-token prices from the pricing page; change these three for another model.

665 # Per-million-token prices from the pricing page; change these for another model.

666 # A model priced by prompt length, such as Claude Haiku 5.5, charges its long-prompt prices over its threshold.

664667 INPUT_PER_MTOK = 4.00 # Claude Opus 5.5

665668 # 0.05x the input price on Claude Opus 5.5; the multiplier differs by model

666669 CACHE_READ_PER_MTOK = 0.20

from line 691

688691 ```

689692

690693 ```typescript TypeScript

691 // Per-million-token prices from the pricing page; change these three for another model.

694 // Per-million-token prices from the pricing page; change these for another model.

695 // A model priced by prompt length, such as Claude Haiku 5.5, charges its long-prompt prices over its threshold.

692696 const INPUT_PER_MTOK = 4.0; // Claude Opus 5.5

693697 const CACHE_READ_PER_MTOK = 0.2; // 0.05x the input price on Claude Opus 5.5; the multiplier differs by model

694698 const OUTPUT_PER_MTOK = 20.0;

from line 715

711715 ```

712716

713717 ```csharp C#

714 // Per-million-token prices from the pricing page; change these three for another model.

718 // Per-million-token prices from the pricing page; change these for another model.

719 // A model priced by prompt length, such as Claude Haiku 5.5, charges its long-prompt prices over its threshold.

715720 const double InputPerMtok = 4.00; // Claude Opus 5.5

716721 const double CacheReadPerMtok = 0.20; // 0.05x the input price on Claude Opus 5.5; the multiplier differs by model

717722 const double OutputPerMtok = 20.00;

from line 743

738743 ```

739744

740745 ```go Go

741 // Per-million-token prices from the pricing page; change these three for another model.

746 // Per-million-token prices from the pricing page; change these for another model.

747 // A model priced by prompt length, such as Claude Haiku 5.5, charges its long-prompt prices over its threshold.

742748 const (

743749 inputPerMTok = 4.00 // Claude Opus 5.5

744750 cacheReadPerMTok = 0.20 // 0.05x the input price on Claude Opus 5.5; the multiplier differs by model

from line 775

769775 ```

770776

771777 ```java Java

772 // Per-million-token prices from the pricing page; change these three for another model.

778 // Per-million-token prices from the pricing page; change these for another model.

779 // A model priced by prompt length, such as Claude Haiku 5.5, charges its long-prompt prices over its threshold.

773780 static final double INPUT_PER_MTOK = 4.00; // Claude Opus 5.5

774781 static final double CACHE_READ_PER_MTOK = 0.20; // 0.05x the input price on Claude Opus 5.5; the multiplier differs by model

775782 static final double OUTPUT_PER_MTOK = 20.00;

from line 803

796803 ```

797804

798805 ```php PHP

799 // Per-million-token prices from the pricing page; change these three for another model.

806 // Per-million-token prices from the pricing page; change these for another model.

807 // A model priced by prompt length, such as Claude Haiku 5.5, charges its long-prompt prices over its threshold.

800808 const INPUT_PER_MTOK = 4.00; // Claude Opus 5.5

801809 const CACHE_READ_PER_MTOK = 0.20; // 0.05x the input price on Claude Opus 5.5; the multiplier differs by model

802810 const OUTPUT_PER_MTOK = 20.00;

from line 827

819827 ```

820828

821829 ```ruby Ruby

822 # Per-million-token prices from the pricing page; change these three for another model.

830 # Per-million-token prices from the pricing page; change these for another model.

831 # A model priced by prompt length, such as Claude Haiku 5.5, charges its long-prompt prices over its threshold.

823832 INPUT_PER_MTOK = 4.00 # Claude Opus 5.5

824833 CACHE_READ_PER_MTOK = 0.20 # 0.05x the input price on Claude Opus 5.5; the multiplier differs by model

825834 OUTPUT_PER_MTOK = 20.00

about-claude/pricing Changed · +13 / -12 lines

from line 68

6868 Starting with Claude Sonnet 4.5, Haiku 4.5, and Opus 4.5:

6969

7070 * **Bedrock** offers two endpoint types: global endpoints (dynamic routing for maximum availability) and regional endpoints (guaranteed data routing through specific geographic regions).

71 * **Google Cloud** offers three endpoint types: global endpoints, multi-region endpoints (dynamic routing within a geographic area), and regional endpoints.

71 * **Google Cloud** offers global endpoints and multi-region endpoints (dynamic routing within a geographic area) for these models, and regional endpoints for Claude Sonnet 4.6 and earlier models.

7272

7373 Regional and multi-region endpoints include a 10% premium over global endpoints. The Claude API (first-party) is global by default; for first-party data residency options and pricing, see [Data residency pricing](https://platform.claude.com/docs/en/about-claude/pricing#data-residency-pricing).

7474

from line 157

157157

158158### Data residency pricing

159159

160For Claude 4.6 and later models, specifying US-only inference through the `inference_geo` parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads. Global routing (the default) uses standard pricing.

160For Claude 4.6 and later models, specifying US-only inference through the `inference_geo` parameter incurs a 1.1x multiplier on all token pricing categories, including input tokens, output tokens, cache writes, and cache reads. On Claude Haiku 5.5, the multiplier also applies to the higher prices for prompts over 100,000 tokens (see [Long context pricing](https://platform.claude.com/docs/en/about-claude/pricing#long-context-pricing)). Global routing (the default) uses standard pricing.

161161

162162This applies to the Claude API (first-party) and Claude Platform on AWS. On Claude in Microsoft Foundry, the same 1.1x multiplier applies to deployments that use the US Data Zone Standard deployment type (see [Inference geography](https://platform.claude.com/docs/en/about-claude/pricing#foundry-inference-geography)). Partner-operated platforms (Bedrock and Google Cloud) have independent regional pricing. See [Bedrock](https://aws.amazon.com/bedrock/pricing/) and [Google Cloud](https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models) for details. Earlier models do not support the `inference_geo` parameter and always use standard pricing; requests that include the parameter on these models return a 400 error.

163163

from line 276

276276

277277The bash tool definition adds the following input tokens to your request. This is in addition to the per-model [tool use system prompt](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing) that applies whenever any tool is present.

278278

279| Model | Additional input tokens |

280| --------------------------------------------------- | ----------------------- |

281| Claude Opus 5, Claude Opus 4.8, and Claude Opus 4.7 | 325 tokens |

282| Claude Opus 4.6, Claude Sonnet 4.6, and earlier | 244 tokens |

279| Model | Additional input tokens |

280| ----------------------------------------------------- | ----------------------- |

281| Claude 4.7 and later models and Claude Mythos Preview | 325 tokens |

282| Claude 4.6 and earlier models | 244 tokens |

283283

284284Additional tokens are consumed by:

285285

from line 320

320320

321321In addition to the base tokens, the following additional input tokens are needed for the text editor tool:

322322

323| Tool | Additional input tokens |

324| ----------------------------------- | ----------------------- |

325| `text_editor_20250429` (Claude 4.x) | 700 tokens |

323| Tool | Additional input tokens |

324| ------------------------------------------------------------------------------ | ----------------------- |

325| `text_editor_20250728` (Claude 4.7 and later models and Claude Mythos Preview) | 974 tokens |

326| `text_editor_20250728` (Claude 4.6 and earlier models) | 745 tokens |

326327

327328See [tool use pricing](https://platform.claude.com/docs/en/about-claude/pricing#tool-use-pricing) for complete pricing details.

328329

from line 381

380381

381382Computer use follows the standard [tool use pricing](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the computer use tool:

382383

383**Toolset definition overhead:** Declaring `computer_toolset_20260801` with its default members adds about 4,500 input tokens to a request (about 4,520 on Claude Fable 5, Claude Mythos 5, Claude Opus 5, and Claude Opus 4.8, and about 4,590 on Claude Sonnet 5), which covers the member tool definitions and the tool use system prompt. Disabling `zoom` with `configs` removes about 410 of those tokens. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).

384**Toolset definition overhead:** Declaring `computer_toolset_20260801` with its default members adds about 4,500 input tokens to a request (about 4,590 on Claude Sonnet 5 and about 4,520 on the other supported models), which covers the member tool definitions and the tool use system prompt. Disabling `zoom` with `configs` removes about 410 of those tokens. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).

384385

385386**Earlier tool versions:** The following figures apply to the `computer_20251124` and `computer_20250124` tool versions, not to `computer_toolset_20260801`:

386387

from line 401

400401

401402Browser use follows the standard [tool use pricing](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the browser use tool:

402403

403**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request (about 6,610 on Claude Fable 5, Claude Mythos 5, Claude Opus 5, and Claude Opus 4.8, and about 6,670 on Claude Sonnet 5), which covers the member tool definitions and the tool use system prompt. Enabling all four optional members adds about 880 tokens, and disabling members with `configs` reduces the count. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).

404**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request (about 6,670 on Claude Sonnet 5 and about 6,610 on the other supported models), which covers the member tool definitions and the tool use system prompt. Enabling all four optional members adds about 880 tokens, and disabling members with `configs` reduces the count. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).

404405

405406**Additional token consumption:**

406407

from line 519

518519

519520### How is token usage calculated?

520521

521Tokens are pieces of text that models process. As a rough estimate, 1 token is approximately 4 characters or 0.75 words in English. The exact count varies by language and content type.

522Tokens are pieces of text that models process. How many tokens the same text produces depends on the model's tokenizer, the language, and the type of content. Claude 4.7 and later models and Claude Mythos Preview use a newer tokenizer that produces approximately 30 percent more tokens for the same text than earlier models. To see how many tokens a request uses on a specific model, count it with [token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) and that model's ID.

522523

523524### Are there free tiers or trials?

524525

agents-and-tools/tool-use/advisor-tool Changed · +32 / -30 lines

from line 735

735735

736736### Mid-conversation nudge for under-calling executors

737737

738If a Haiku executor has not called the advisor in its first assistant turn, append a short reminder as an additional user message before the second assistant turn. In Anthropic's internal behavioral evaluation this raised task pass rates by roughly 7 percentage points on Haiku executors. On Sonnet executors, the plain-text nudge had no measurable effect in Anthropic's testing. The call-timing considerations that follow are especially relevant for Sonnet. Do not apply the nudge to Opus executors: On Opus it slightly lowered pass rates.

738If a Haiku executor has not called the advisor in its first assistant turn, append a short reminder as an additional user message before the second assistant turn. In Anthropic's internal behavioral evaluation on Claude Haiku 4.5 executors, this raised task pass rates by roughly 7 percentage points. On Sonnet executors, the plain-text nudge had no measurable effect in Anthropic's testing. The call-timing considerations that follow are especially relevant for Sonnet. Do not apply the nudge to Opus executors: On Opus it slightly lowered pass rates.

739739

740740With the default `NUDGE_TURN` of 2, the reminder typically arrives after the model has oriented on the task but before it has committed to an approach.

741741

from line 775

775775

776776 for turn in range(1, MAX_TURNS + 1):

777777 response = client.beta.messages.create(

778 model="claude-haiku-4-5",

778 model="claude-haiku-5-5",

779779 max_tokens=4096,

780780 betas=["advisor-tool-2026-03-01"],

781781 tools=tools,

from line 786

786786 block.type == "server_tool_use" and block.name == "advisor"

787787 for block in response.content

788788 )

789 if response.stop_reason == "end_turn":

790 break

791789 if response.stop_reason == "pause_turn":

792790 continue # server tool pending; re-send to let the API complete it

791 if response.stop_reason != "tool_use":

792 break # end_turn, or a stop such as max_tokens that needs handling (see below)

793793

794794 results = run_your_tools(response.content) # list of tool_result blocks

795795 if results:

from line 832

832832

833833 for (let turn = 1; turn <= MAX_TURNS; turn++) {

834834 const response = await client.beta.messages.create({

835 model: "claude-haiku-4-5",

835 model: "claude-haiku-5-5",

836836 max_tokens: 4096,

837837 betas: ["advisor-tool-2026-03-01"],

838838 tools,

from line 844

844844 response.content.some(

845845 (block) => block.type === "server_tool_use" && block.name === "advisor"

846846 );

847 if (response.stop_reason === "end_turn") {

848 break;

849 }

850847 if (response.stop_reason === "pause_turn") {

851848 continue; // server tool pending; re-send to let the API complete it

852849 }

850 if (response.stop_reason !== "tool_use") {

851 break; // end_turn, or a stop such as max_tokens that needs handling (see below)

852 }

853853

854854 const results = runYourTools(response.content); // list of tool_result blocks

855855 if (results.length > 0) {

from line 906

906906 {

907907 var response = await client.Beta.Messages.Create(new MessageCreateParams

908908 {

909 Model = Messages::Model.ClaudeHaiku4_5,

909 Model = Messages::Model.ClaudeHaiku5_5,

910910 MaxTokens = 4096,

911911 Tools = tools,

912912 Messages = messages,

from line 923

923923 block.TryPickServerToolUse(out var serverToolUse)

924924 && serverToolUse.Name.Value() == Name.Advisor

925925 );

926 if (response.StopReason == BetaStopReason.EndTurn)

927 {

928 break;

929 }

930926 if (response.StopReason == BetaStopReason.PauseTurn)

931927 {

932928 continue; // server tool pending; re-send to let the API complete it

933929 }

930 if (response.StopReason != BetaStopReason.ToolUse)

931 {

932 break; // end_turn, or a stop such as max_tokens that needs handling (see below)

933 }

934934

935935 var results = RunYourTools(response.Content); // list of tool_result blocks

936936 if (results.Count > 0)

from line 982

982982

983983 for turn := 1; turn <= maxTurns; turn++ {

984984 response, err := client.Beta.Messages.New(context.TODO(), anthropic.BetaMessageNewParams{

985 Model: anthropic.ModelClaudeHaiku4_5,

985 Model: anthropic.ModelClaudeHaiku5_5,

986986 MaxTokens: 4096,

987987 Tools: tools,

988988 Messages: messages,

from line 1001

10011001 advisorCalled = true

10021002 }

10031003 }

1004 if response.StopReason == anthropic.BetaStopReasonEndTurn {

1005 break

1006 }

10071004 if response.StopReason == anthropic.BetaStopReasonPauseTurn {

10081005 continue // server tool pending; re-send to let the API complete it

10091006 }

1007 if response.StopReason != anthropic.BetaStopReasonToolUse {

1008 break // end_turn, or a stop such as max_tokens that needs handling (see below)

1009 }

10101010

10111011 results := runYourTools(response.Content) // list of tool_result blocks

10121012 if len(results) > 0 {

from line 1076

10761076

10771077 for (int turn = 1; turn <= MAX_TURNS; turn++) {

10781078 BetaMessage response = client.beta().messages().create(MessageCreateParams.builder()

1079 .model(Model.CLAUDE_HAIKU_4_5)

1079 .model(Model.CLAUDE_HAIKU_5_5)

10801080 .maxTokens(4096L)

10811081 .tools(tools)

10821082 .messages(messages)

from line 1092

10921092 block.isServerToolUse()

10931093 && block.asServerToolUse().name().equals(BetaServerToolUseBlock.Name.ADVISOR));

10941094 BetaStopReason stopReason = response.stopReason().orElse(null);

1095 if (BetaStopReason.END_TURN.equals(stopReason)) {

1096 break;

1097 }

10981095 if (BetaStopReason.PAUSE_TURN.equals(stopReason)) {

10991096 continue; // server tool pending; re-send to let the API complete it

11001097 }

1098 if (!BetaStopReason.TOOL_USE.equals(stopReason)) {

1099 break; // end_turn, or a stop such as max_tokens that needs handling (see below)

1100 }

11011101

11021102 List<BetaContentBlockParam> results = runYourTools(response.content()); // list of tool_result blocks

11031103 if (!results.isEmpty()) {

from line 1154

11541154 $response = $client->beta->messages->create(

11551155 maxTokens: 4096,

11561156 messages: $messages,

1157 model: 'claude-haiku-4-5',

1157 model: 'claude-haiku-5-5',

11581158 tools: $tools,

11591159 betas: ['advisor-tool-2026-03-01'],

11601160 );

from line 1164

11641164 $advisorCalled = true;

11651165 }

11661166 }

1167 if ($response->stopReason === 'end_turn') {

1168 break;

1169 }

11701167 if ($response->stopReason === 'pause_turn') {

11711168 continue; // server tool pending; re-send to let the API complete it

11721169 }

1170 if ($response->stopReason !== 'tool_use') {

1171 break; // end_turn, or a stop such as max_tokens that needs handling (see below)

1172 }

11731173

11741174 $results = runYourTools($response->content); // list of tool_result blocks

11751175 if ($results !== []) {

from line 1210

12101210

12111211 (1..MAX_TURNS).each do |turn|

12121212 response = client.beta.messages.create(

1213 model: "claude-haiku-4-5",

1213 model: "claude-haiku-5-5",

12141214 max_tokens: 4096,

12151215 tools: tools,

12161216 messages: messages,

from line 1220

12201220 advisor_called ||= response.content.any? do |block|

12211221 block.type == :server_tool_use && block.name == :advisor

12221222 end

1223 break if response.stop_reason == :end_turn

12241223 next if response.stop_reason == :pause_turn # server tool pending; re-send to let the API complete it

1224 break unless response.stop_reason == :tool_use # end_turn, or a stop such as max_tokens that needs handling (see below)

12251225

12261226 results = run_your_tools(response.content) # list of tool_result blocks

12271227 messages << { role: "user", content: results } unless results.empty?

from line 1231

12311231 ```

12321232</CodeGroup>

12331233

1234Append the nudge as its own user message after the tool results rather than as a sibling block in the same message. Consecutive user messages are valid. In Anthropic's testing on Haiku and Sonnet executors they behaved equivalently to a sibling block. The separate-message shape also keeps the reminder clearly distinct from tool output.

1234The loop ends on any stop reason other than `tool_use` or `pause_turn`. If `max_tokens` cuts a response off, drop the truncated assistant turn from `messages` and [retry with a higher `max_tokens`](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons#max-tokens). When that turn contains no `tool_use` block, you can instead keep it and [continue the response](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons#ensuring-complete-responses) with a new user message. Re-sending the truncated assistant turn as the last message is a [prefill](https://platform.claude.com/docs/en/api/errors#prefill-not-supported), which Claude 4.6 and later models reject.

12351235

1236Append the nudge as its own user message after the tool results rather than as a sibling block in the same message. Consecutive user messages are valid. In Anthropic's testing on Claude Haiku 4.5 and Sonnet executors they behaved equivalently to a sibling block. The separate-message shape also keeps the reminder clearly distinct from tool output.

1237

12361238**Trade-offs:** The nudge raises the call rate, which can push trivially simple tasks into an unnecessary consult. If your workload mixes simple and complex tasks, consider raising `NUDGE_TURN` to 3 so two-turn tasks complete before the nudge fires, or gate the nudge on a task-complexity signal you already compute. If your system prompt already contains restraint language ("reserve the advisor for genuine uncertainty"), skip the nudge entirely, because the two instructions conflict.

12371239

1238The plain-text nudge is highly salient on Haiku and Sonnet executors: 74 percent (Sonnet) to 98 percent (Haiku) of nudged attempts in Anthropic's testing called the advisor immediately at turn 2. If that lands before your executor has read the problem or gathered context, the resulting advisor call is low-context and can displace a better-timed later call. Measure your executor's baseline first-call turn before adding the nudge. If the executor already calls the advisor reliably and its first call typically lands at turn N, set `NUDGE_TURN` greater than N. In Anthropic's testing, a turn-2 nudge on workloads where the baseline first call was turn 7 or later correlated with a 3 to 4 percentage-point task-performance drop. On a browse workload where the baseline call rate was 86 percent, the same nudge raised engagement with no task-performance cost.

1240The plain-text nudge is highly salient on Claude Haiku 4.5 and Sonnet executors: 74 percent (Sonnet) to 98 percent (Claude Haiku 4.5) of nudged attempts in Anthropic's testing called the advisor immediately at turn 2. If that lands before your executor has read the problem or gathered context, the resulting advisor call is low-context and can displace a better-timed later call. Measure your executor's baseline first-call turn before adding the nudge. If the executor already calls the advisor reliably and its first call typically lands at turn N, set `NUDGE_TURN` greater than N. In Anthropic's testing, a turn-2 nudge on workloads where the baseline first call was turn 7 or later correlated with a 3 to 4 percentage-point task-performance drop. On a browse workload where the baseline call rate was 86 percent, the same nudge raised engagement with no task-performance cost.

12391241

12401242To force a consult on a specific request instead of nudging, set `tool_choice` to `{"type": "tool", "name": "advisor"}`, subject to the constraints in [Forcing tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/define-tools#forcing-tool-use). Forcing tool use cannot be combined with manual extended thinking (`thinking: {type: "enabled"}`): the API returns a `400 invalid_request_error` if you enable both. Adaptive thinking supports forced tool use. Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and Claude Mythos 5.1 executors reject `tool_choice` types `tool` and `any`, so use the prompt nudge on those models instead.

12411243

from line 1403

14011403**Keep it consistent:** Set `caching` once and leave it for the whole conversation. Toggling it off and on mid-conversation causes cache misses.

14021404

14031405<Warning>

1404 [`clear_thinking`](https://platform.claude.com/docs/en/build-with-claude/context-editing) with a `keep` value other than `"all"` shifts the advisor's quoted transcript each turn, causing advisor-side cache misses. This is a cost degradation only. Advice quality is unaffected. When extended thinking is enabled without explicit `clear_thinking` configuration, the API defaults to `keep: {type: "thinking_turns", value: 1}`, which triggers this behavior (the default on earlier Opus/Sonnet models and Haiku models through Claude Haiku 4.5, whereas on Opus 4.5+, Sonnet 4.6+, and Haiku 5.5 the default is to keep all turns). Set `keep: "all"` to preserve advisor cache stability.

1406 [`clear_thinking`](https://platform.claude.com/docs/en/build-with-claude/context-editing) with a `keep` value other than `"all"` shifts the advisor's quoted transcript each turn, causing advisor-side cache misses. This is a cost degradation only. Advice quality is unaffected. When thinking is on without explicit `clear_thinking` configuration, the API defaults to `keep: {type: "thinking_turns", value: 1}`, which triggers this behavior (the default on earlier Opus and Sonnet models and on Haiku models through Claude Haiku 4.5; on Claude Opus 4.5 and later Opus models, Claude Sonnet 4.6 and later Sonnet models, and Claude Haiku 5.5, the default is to keep all turns). Set `keep: "all"` to preserve advisor cache stability.

14051407</Warning>

14061408

14071409## Combining with other tools

agents-and-tools/tool-use/bash-tool Changed · +4 / -4 lines

from line 1920

19201920

19211921The bash tool definition adds the following input tokens to your request. This is in addition to the per-model [tool use system prompt](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing) that applies whenever any tool is present.

19221922

1923| Model | Additional input tokens |

1924| --------------------------------------------------- | ----------------------- |

1925| Claude Opus 5, Claude Opus 4.8, and Claude Opus 4.7 | 325 tokens |

1926| Claude Opus 4.6, Claude Sonnet 4.6, and earlier | 244 tokens |

1923| Model | Additional input tokens |

1924| ----------------------------------------------------- | ----------------------- |

1925| Claude 4.7 and later models and Claude Mythos Preview | 325 tokens |

1926| Claude 4.6 and earlier models | 244 tokens |

19271927

19281928Additional tokens are consumed by:

19291929

agents-and-tools/tool-use/browser-use-tool Changed · +1 / -4 lines

from line 20

2020 - claude-haiku-5-5

2121 supportedPlatforms:

2222 Claude API: ga

23 Claude Platform on AWS: not available

24 Amazon Bedrock: not available

2523 Google Cloud: ga

26 Microsoft Foundry: not available

2724---

2825

2926The browser use tool lets Claude navigate, read, and interact with webpages in a browser that your application runs. Claude works with the page both through its structure (the accessibility tree, elements, forms, and tabs) and through screenshots and viewport coordinates.

from line 1567

15701567

15711568Browser use follows the standard [tool use pricing](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the browser use tool:

15721569

1573**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request (about 6,610 on Claude Fable 5, Claude Mythos 5, Claude Opus 5, and Claude Opus 4.8, and about 6,670 on Claude Sonnet 5), which covers the member tool definitions and the tool use system prompt. Enabling all four optional members adds about 880 tokens, and disabling members with `configs` reduces the count. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).

1570**Toolset definition overhead:** Declaring `browser_toolset_20260801` with its default members adds about 6,600 input tokens to a request (about 6,670 on Claude Sonnet 5 and about 6,610 on the other supported models), which covers the member tool definitions and the tool use system prompt. Enabling all four optional members adds about 880 tokens, and disabling members with `configs` reduces the count. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).

15741571

15751572**Additional token consumption:**

15761573

agents-and-tools/tool-use/computer-use-tool Changed · +5 / -5 lines

from line 25

2525 Google Cloud: ga

2626 Microsoft Foundry: beta

2727 details:

28 - On the Claude API and Google Cloud, Claude 5.5 and later models support computer use only through the `computer_toolset_20260801` toolset and return an error for the earlier `computer_20251124` tool version. To move an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124).

29 - On Amazon Bedrock, Claude Opus 5.5 and Claude Sonnet 5.5 accept the earlier `computer_20251124` tool version as Claude Opus 5 and Claude Sonnet 5 do.

28 - On the Claude API and Google Cloud, Claude 5.5 and later models support computer use only through the `computer_toolset_20260801` toolset and return an error for the earlier `computer_20251124` and `computer_20250124` tool versions. To move an existing integration, see [Migrate from `computer_20251124`](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#migrate-from-computer-20251124). To move from `computer_20250124`, see [Move computer use to the toolset](https://platform.claude.com/docs/en/models/haiku-5-5/migration-guide#computer-use-toolset) in the Claude Haiku 5.5 migration guide.

29 - On Amazon Bedrock, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 accept the earlier `computer_20251124` tool version as Claude Opus 5 and Claude Sonnet 5 do.

3030 - Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5 support computer use only through the earlier `computer_20251124` tool version, which requires a beta header; see [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).

3131 - Platforms other than the Claude API and Google Cloud currently offer only the [earlier beta tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions).

3232---

from line 2119

21192119

21202120## Migrate from `computer_20251124`

21212121

2122Upgrading from `computer_20251124` to the toolset is optional: the models listed for `computer_20251124` under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) keep accepting it with its beta header, so an existing integration keeps working until you change it. Claude 5.5 and later models are the exception on the Claude API and Google Cloud: there they accept only the toolset. Upgrade an integration before you move it to one of them. On Amazon Bedrock, Claude Opus 5.5 and Claude Sonnet 5.5 keep accepting `computer_20251124`. To upgrade, make the following changes together:

2122Upgrading from `computer_20251124` to the toolset is optional: the models listed for `computer_20251124` under [Earlier tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool#earlier-tool-versions) keep accepting it with its beta header, so an existing integration keeps working until you change it. Claude 5.5 and later models are the exception on the Claude API and Google Cloud: there they accept only the toolset. Upgrade an integration before you move it to one of them. On Amazon Bedrock, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 accept `computer_20251124`. To upgrade, make the following changes together:

21232123

212421241. **Remove the beta header.** Drop `anthropic-beta: computer-use-2025-11-24` from your requests. With the SDK, remove `betas` (python, typescript, php, ruby; csharp, go: `Betas`; java: `.addBeta()`) and call the Messages API through the standard client rather than the beta namespace.

212521252. **Change the `tools` entry.** Set `type` to `computer_toolset_20260801` and delete `name`, `display_width_px`, `display_height_px`, `display_number`, and `enable_zoom`. The toolset rejects each of these fields.

from line 2181

21812181

21832183| ------------------- | ------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------- |

2184| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5; on Amazon Bedrock, also Claude Opus 5.5 and Claude Sonnet 5.5 | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |

2184| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 4.6, and Claude Opus 4.5; on Amazon Bedrock, also Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |

21852185| `computer_20250124` | `computer-use-2025-01-24` | Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Haiku 4.5, Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claude Sonnet 4 ([retired, except on Bedrock and Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)), and Claude Opus 4 ([retired, except on Google Cloud](https://platform.claude.com/docs/en/about-claude/model-deprecations)) | [API reference](https://platform.claude.com/docs/en/api/beta/messages/create) |

21862186

21872187***

from line 2209

22092209

22102210Computer use follows the standard [tool use pricing](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing). When using the computer use tool:

22112211

2212**Toolset definition overhead:** Declaring `computer_toolset_20260801` with its default members adds about 4,500 input tokens to a request (about 4,520 on Claude Fable 5, Claude Mythos 5, Claude Opus 5, and Claude Opus 4.8, and about 4,590 on Claude Sonnet 5), which covers the member tool definitions and the tool use system prompt. Disabling `zoom` with `configs` removes about 410 of those tokens. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).

2212**Toolset definition overhead:** Declaring `computer_toolset_20260801` with its default members adds about 4,500 input tokens to a request (about 4,590 on Claude Sonnet 5 and about 4,520 on the other supported models), which covers the member tool definitions and the tool use system prompt. Disabling `zoom` with `configs` removes about 410 of those tokens. The exact count for a request is reported in the response `usage`, and you can estimate it in advance with the [token counting endpoint](https://platform.claude.com/docs/en/build-with-claude/token-counting).

22132213

22142214**Earlier tool versions:** The following figures apply to the `computer_20251124` and `computer_20250124` tool versions, not to `computer_toolset_20260801`:

22152215

agents-and-tools/tool-use/define-tools Changed · +6 / -4 lines

from line 558

558558

559559Not every model and setting supports forced tool use. Where it isn't supported, `tool_choice: {"type": "any"}` and `tool_choice: {"type": "tool", "name": "..."}` fail, while `tool_choice: {"type": "auto"}` (the default) and `tool_choice: {"type": "none"}` still work:

560560

561| Model or setting | Restriction | What to use instead |

562| --------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

563| Manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) (`thinking: {type: "enabled"}`) | `any` and `tool` are not supported and result in an error | `auto` or `none`. [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) itself doesn't block forced tool use (Claude Opus 5 and Claude Haiku 5.5 support it with thinking on); the models in the next row reject forced tool use regardless of thinking settings |

564| Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) | `any` and `tool` return a [400 error](https://platform.claude.com/docs/en/api/errors#forced-tool-use-not-supported) | `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) to guarantee schema-valid tool inputs, or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) when you need a response in a fixed JSON shape. Prompting still influences which tool `auto` picks. `none` is also supported |

561| Model or setting | Restriction | What to use instead |

562| --------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

563| Manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) (`thinking: {type: "enabled"}`) | `any` and `tool` are not supported and result in an error | `auto` or `none`. [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) itself doesn't block forced tool use (models with thinking on by default, such as Claude Opus 5 and Claude Haiku 5.5, accept it, but a forced call skips thinking: the response starts with the tool call and has no `thinking` block); the models in the next row reject forced tool use regardless of thinking settings |

564| Claude Opus 5.5, Claude Sonnet 5.5, Claude Fable 5.1, and [Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) | `any` and `tool` return a [400 error](https://platform.claude.com/docs/en/api/errors#forced-tool-use-not-supported) | `auto` with [strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-use) to guarantee schema-valid tool inputs, or [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs) when you need a response in a fixed JSON shape. Prompting still influences which tool `auto` picks. `none` is also supported |

565565

566566On models that support it, the highlighted lines are the only difference from a standard tool use request:

567567

from line 862

862862Note that when you have `tool_choice` as `any` or `tool`, the API prefills the assistant message to force a tool to be used. This means that the models will not emit a natural language response or explanation before `tool_use` content blocks, even if explicitly asked to do so.

863863

864864Testing has shown that this should not reduce performance. If you would like the model to provide natural language context or explanations while still requesting that the model use a specific tool, you can use `{"type": "auto"}` for `tool_choice` (the default) and add explicit instructions in a `user` message. For example: `What's the weather like in London? Use the get_weather tool in your response.`

865

866Forcing a tool also skips thinking on every model that accepts forced tool use: the response starts with the `tool_use` block and has no `thinking` block. To let the model think before it calls the tool, use `auto` with a prompt instruction in the same way.

865867

866868<Tip>

867869 **Guaranteed tool calls with strict tools**

agents-and-tools/tool-use/text-editor-tool Changed · +4 / -3 lines

from line 2238

22382238

22392239In addition to the base tokens, the following additional input tokens are needed for the text editor tool:

22402240

2241| Tool | Additional input tokens |

2242| ----------------------------------- | ----------------------- |

2243| `text_editor_20250429` (Claude 4.x) | 700 tokens |

2241| Tool | Additional input tokens |

2242| ------------------------------------------------------------------------------ | ----------------------- |

2243| `text_editor_20250728` (Claude 4.7 and later models and Claude Mythos Preview) | 974 tokens |

2244| `text_editor_20250728` (Claude 4.6 and earlier models) | 745 tokens |

22442245

22452246For more detailed information about tool pricing, see [Tool use pricing](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview#pricing).

22462247

agents-and-tools/tool-use/troubleshooting-tool-use Changed · +1 / -1 lines

## JSON escaping differences between model versions ## JSON escaping differences (Opus 4.6+)

from line 56

5656| -------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

5757| Claude refuses to act on a tool result, or asks the user to confirm instructions that came from it | Your own instructions are being delivered inside the `tool_result` content | Claude is trained to treat instructions inside tool results as potentially untrusted third-party content. Move your instructions out of the tool result: send them in a `user` turn after the `tool_result` block, or, on supported models, in a [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages). Keep the tool result to just the data. See [Mitigate jailbreaks and prompt injections](https://platform.claude.com/docs/en/test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks#indirect-prompt-injection). |

5858

59## JSON escaping differences (Opus 4.6+)

59## JSON escaping differences between model versions

6060

6161| Symptom | Cause | Fix |

6262| -------------------------------------------------------- | ----------------------------------------------------------------- | ---------------------------------------------------------------------------------------------- |

api/beta Changed · +1120 / -0 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 477

477477

478478#### Headers

479479

480- `"anthropic-version": optional string`

481

482 The version of the Claude API you want to use.

483

484 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

485

480486- `"anthropic-beta": optional array of AnthropicBeta`

481487

482488 Optional header to specify the beta version(s) you want to use.

from line 949

943949

944950#### Headers

945951

952- `"anthropic-version": optional string`

953

954 The version of the Claude API you want to use.

955

956 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

957

946958- `"anthropic-beta": optional array of AnthropicBeta`

947959

948960 Optional header to specify the beta version(s) you want to use.

from line 1400

13881400

13891401#### Headers

13901402

1403- `"anthropic-version": optional string`

1404

1405 The version of the Claude API you want to use.

1406

1407 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

1408

13911409- `"anthropic-beta": optional array of AnthropicBeta`

13921410

13931411 Optional header to specify the beta version(s) you want to use.

from line 7753

77357753

77367754 - `strict: optional boolean`

77377755

7738 When true, guarantees schema validation on tool names and inputs

7739

7740 - `BetaToolTextEditor20250429 object`

7741

7742 - `type: "text_editor_20250429"`

7743

7744 - `name: "str_replace_based_edit_tool"`

7745

7746 Name of the tool.

7747

7748 This is how the tool will be called by the model and in `tool_use` blocks.

7749

7750 - `allowed_callers: optional array of "direct" or "code_execution_20250825" or "code_execution_20260120" or "code_execution_20260521"`

7751

7752 - `"direct"`

7753

7754 - `"code_execution_20250825"`

7755

7756 - `

7756 When true,

api/beta/agents Changed · +12 / -0 lines

This page is larger than the 256 KiB this site keeps, so one side of the diff below stops where the stored text does.

from line 13

1313

1414### Headers

1515

16- `"anthropic-version": optional string`

17

1618- `"anthropic-beta": optional array of AnthropicBeta`

1719

1820 Optional header to specify the beta version(s) you want to use.

from line 1755

17531755

17541756### Headers

17551757

1758- `"anthropic-version": optional string`

1759

17561760- `"anthropic-beta": optional array of AnthropicBeta`

17571761

17581762 Optional header to specify the beta version(s) you want to use.

from line 2652

26482652

26492653### Headers

26502654

2655- `"anthropic-version": optional string`

2656

26512657- `"anthropic-beta": optional array of AnthropicBeta`

26522658

26532659 Optional header to specify the beta version(s) you want to use.

from line 3532

35263532

35273533### Headers

35283534

3535- `"anthropic-version": optional string`

3536

35293537- `"anthropic-beta": optional array of AnthropicBeta`

35303538

35313539 Optional header to specify the beta version(s) you want to use.

from line 5249

52415249

52425250### Headers

52435251

5252- `"anthropic-version": optional string`

5253

52445254- `"anthropic-beta": optional array of AnthropicBeta`

52455255

52465256 Optional header to specify the beta version(s) you want to use.

from line 8081

80718081

80728082 - `enabled: optional boolean or null`

80738083

8074 Whether this tool is enabled and available to Claude. Overrides the default_config setting.

8075

8076 - `permission_policy: optional BetaManagedAgentsAlwaysAllowPolicy or BetaManagedAgentsAlwaysAskPolicy or BetaManagedAgentsAutoPolicy or null`

8077

8078 Permission policy for this tool. Control

8084 Whether this tool is enabled and available to Claude. Overrides the default_conf

api/beta/deployments Changed · +16 / -0 lines

from line 13

1313

1414### Headers

1515

16- `"anthropic-version": optional string`

17

1618- `"anthropic-beta": optional array of AnthropicBeta`

1719

1820 Optional header to specify the beta version(s) you want to use.

from line 1199

11971199

11981200### Headers

11991201

1202- `"anthropic-version": optional string`

1203

12001204- `"anthropic-beta": optional array of AnthropicBeta`

12011205

12021206 Optional header to specify the beta version(s) you want to use.

from line 1932

19281932

19291933### Headers

19301934

1935- `"anthropic-version": optional string`

1936

19311937- `"anthropic-beta": optional array of AnthropicBeta`

19321938

19331939 Optional header to specify the beta version(s) you want to use.

from line 2656

26502656

26512657### Headers

26522658

2659- `"anthropic-version": optional string`

2660

26532661- `"anthropic-beta": optional array of AnthropicBeta`

26542662

26552663 Optional header to specify the beta version(s) you want to use.

from line 3790

37823790

37833791### Headers

37843792

3793- `"anthropic-version": optional string`

3794

37853795- `"anthropic-beta": optional array of AnthropicBeta`

37863796

37873797 Optional header to specify the beta version(s) you want to use.

from line 4515

45054515

45064516### Headers

45074517

4518- `"anthropic-version": optional string`

4519

45084520- `"anthropic-beta": optional array of AnthropicBeta`

45094521

45104522 Optional header to specify the beta version(s) you want to use.

from line 4902

48904902

48914903### Headers

48924904

4905- `"anthropic-version": optional string`

4906

48934907- `"anthropic-beta": optional array of AnthropicBeta`

48944908

48954909 Optional header to specify the beta version(s) you want to use.

from line 5626

56125626 Unique identifier of the deployment to unpause.

56135627

56145628### Headers

5629

5630- `"anthropic-version": optional string`

56155631

56165632- `"anthropic-beta": optional array of AnthropicBeta`

56175633

api/beta/dreams Changed · +10 / -0 lines

from line 17

1717

1818### Headers

1919

20- `"anthropic-version": optional string`

21

2022- `"anthropic-beta": optional array of AnthropicBeta`

2123

2224 Optional header to specify the beta version(s) you want to use.

from line 598

596598

597599### Headers

598600

601- `"anthropic-version": optional string`

602

599603- `"anthropic-beta": optional array of AnthropicBeta`

600604

601605 Optional header to specify the beta version(s) you want to use.

from line 1012

10081012

10091013### Headers

10101014

1015- `"anthropic-version": optional string`

1016

10111017- `"anthropic-beta": optional array of AnthropicBeta`

10121018

10131019 Optional header to specify the beta version(s) you want to use.

from line 1421

14151421

14161422### Headers

14171423

1424- `"anthropic-version": optional string`

1425

14181426- `"anthropic-beta": optional array of AnthropicBeta`

14191427

14201428 Optional header to specify the beta version(s) you want to use.

from line 1830

18221830 The ID of the dream to archive (`drm_...`).

18231831

18241832### Headers

1833

1834- `"anthropic-version": optional string`

18251835

18261836- `"anthropic-beta": optional array of AnthropicBeta`

18271837

api/beta/environments Changed · +84 / -0 lines

from line 13

1313

1414### Headers

1515

16- `"anthropic-version": optional string`

17

18 The version of the Claude API you want to use.

19

20 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

21

1622- `"anthropic-beta": optional array of AnthropicBeta`

1723

1824 Optional header to specify the beta version(s) you want to use.

from line 488

482488

483489### Headers

484490

491- `"anthropic-version": optional string`

492

493 The version of the Claude API you want to use.

494

495 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

496

485497- `"anthropic-beta": optional array of AnthropicBeta`

486498

487499 Optional header to specify the beta version(s) you want to use.

from line 819

807819

808820### Headers

809821

822- `"anthropic-version": optional string`

823

824 The version of the Claude API you want to use.

825

826 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

827

810828- `"anthropic-beta": optional array of AnthropicBeta`

811829

812830 Optional header to specify the beta version(s) you want to use.

from line 1141

11231141

11241142### Headers

11251143

1144- `"anthropic-version": optional string`

1145

1146 The version of the Claude API you want to use.

1147

1148 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

1149

11261150- `"anthropic-beta": optional array of AnthropicBeta`

11271151

11281152 Optional header to specify the beta version(s) you want to use.

from line 1585

15611585

15621586### Headers

15631587

1588- `"anthropic-version": optional string`

1589

1590 The version of the Claude API you want to use.

1591

1592 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

1593

15641594- `"anthropic-beta": optional array of AnthropicBeta`

15651595

15661596 Optional header to specify the beta version(s) you want to use.

from line 1750

17201750

17211751### Headers

17221752

1753- `"anthropic-version": optional string`

1754

1755 The version of the Claude API you want to use.

1756

1757 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

1758

17231759- `"anthropic-beta": optional array of AnthropicBeta`

17241760

17251761 Optional header to specify the beta version(s) you want to use.

from line 2542

25062542

25072543#### Headers

25082544

2545- `"anthropic-version": optional string`

2546

2547 The version of the Claude API you want to use.

2548

2549 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

2550

25092551- `"anthropic-beta": optional array of AnthropicBeta`

25102552

25112553 Optional header to specify the beta version(s) you want to use.

from line 2804

27622804

27632805#### Headers

27642806

2807- `"anthropic-version": optional string`

2808

2809 The version of the Claude API you want to use.

2810

2811 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

2812

27652813- `"anthropic-beta": optional array of AnthropicBeta`

27662814

27672815 Optional header to specify the beta version(s) you want to use.

from line 3052

30043052

30053053#### Headers

30063054

3055- `"anthropic-version": optional string`

3056

3057 The version of the Claude API you want to use.

3058

3059 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

3060

30073061- `"anthropic-beta": optional array of AnthropicBeta`

30083062

30093063 Optional header to specify the beta version(s) you want to use.

from line 3307

32533307

32543308#### Headers

32553309

3310- `"anthropic-version": optional string`

3311

3312 The version of the Claude API you want to use.

3313

3314 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

3315

32563316- `"anthropic-beta": optional array of AnthropicBeta`

32573317

32583318 Optional header to specify the beta version(s) you want to use.

from line 3495

34353495

34363496#### Headers

34373497

3498- `"anthropic-version": optional string`

3499

3500 The version of the Claude API you want to use.

3501

3502 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

3503

34383504- `"anthropic-beta": optional array of AnthropicBeta`

34393505

34403506 Optional header to specify the beta version(s) you want to use.

from line 3765

36993765

37003766#### Headers

37013767

3768- `"anthropic-version": optional string`

3769

3770 The version of the Claude API you want to use.

3771

3772 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

3773

37023774- `"anthropic-beta": optional array of AnthropicBeta`

37033775

37043776 Optional header to specify the beta version(s) you want to use.

from line 4018

39464018

39474019#### Headers

39484020

4021- `"anthropic-version": optional string`

4022

4023 The version of the Claude API you want to use.

4024

4025 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

4026

39494027- `"anthropic-beta": optional array of AnthropicBeta`

39504028

39514029 Optional header to specify the beta version(s) you want to use.

from line 4275

41974275- `environment_id: string`

41984276

41994277#### Headers

4278

4279- `"anthropic-version": optional string`

4280

4281 The version of the Claude API you want to use.

4282

4283 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

42004284

42014285- `"anthropic-beta": optional array of AnthropicBeta`

42024286

api/beta/environments/archive Changed · +6 / -0 lines

from line 15

1515

1616## Headers

1717

18- `"anthropic-version": optional string`

19

20 The version of the Claude API you want to use.

21

22 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

23

1824- `"anthropic-beta": optional array of AnthropicBeta`

1925

2026 Optional header to specify the beta version(s) you want to use.

api/beta/environments/create Changed · +6 / -0 lines

from line 11

1111

1212## Headers

1313

14- `"anthropic-version": optional string`

15

16 The version of the Claude API you want to use.

17

18 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

19

1420- `"anthropic-beta": optional array of AnthropicBeta`

1521

1622 Optional header to specify the beta version(s) you want to use.

api/beta/environments/delete Changed · +6 / -0 lines

from line 15

1515

1616## Headers

1717

18- `"anthropic-version": optional string`

19

20 The version of the Claude API you want to use.

21

22 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

23

1824- `"anthropic-beta": optional array of AnthropicBeta`

1925

2026 Optional header to specify the beta version(s) you want to use.

api/beta/environments/list Changed · +6 / -0 lines

from line 29

2929

3030## Headers

3131

32- `"anthropic-version": optional string`

33

34 The version of the Claude API you want to use.

35

36 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

37

3238- `"anthropic-beta": optional array of AnthropicBeta`

3339

3440 Optional header to specify the beta version(s) you want to use.

api/beta/environments/retrieve Changed · +6 / -0 lines

from line 15

1515

1616## Headers

1717

18- `"anthropic-version": optional string`

19

20 The version of the Claude API you want to use.

21

22 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

23

1824- `"anthropic-beta": optional array of AnthropicBeta`

1925

2026 Optional header to specify the beta version(s) you want to use.

api/beta/environments/update Changed · +6 / -0 lines

from line 15

1515

1616## Headers

1717

18- `"anthropic-version": optional string`

19

20 The version of the Claude API you want to use.

21

22 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

23

1824- `"anthropic-beta": optional array of AnthropicBeta`

1925

2026 Optional header to specify the beta version(s) you want to use.

api/beta/environments/work Changed · +48 / -0 lines

from line 21

2121

2222### Headers

2323

24- `"anthropic-version": optional string`

25

26 The version of the Claude API you want to use.

27

28 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

29

2430- `"anthropic-beta": optional array of AnthropicBeta`

2531

2632 Optional header to specify the beta version(s) you want to use.

from line 283

277283

278284### Headers

279285

286- `"anthropic-version": optional string`

287

288 The version of the Claude API you want to use.

289

290 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

291

280292- `"anthropic-beta": optional array of AnthropicBeta`

281293

282294 Optional header to specify the beta version(s) you want to use.

from line 531

519531

520532### Headers

521533

534- `"anthropic-version": optional string`

535

536 The version of the Claude API you want to use.

537

538 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

539

522540- `"anthropic-beta": optional array of AnthropicBeta`

523541

524542 Optional header to specify the beta version(s) you want to use.

from line 786

768786

769787### Headers

770788

789- `"anthropic-version": optional string`

790

791 The version of the Claude API you want to use.

792

793 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

794

771795- `"anthropic-beta": optional array of AnthropicBeta`

772796

773797 Optional header to specify the beta version(s) you want to use.

from line 974

950974

951975### Headers

952976

977- `"anthropic-version": optional string`

978

979 The version of the Claude API you want to use.

980

981 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

982

953983- `"anthropic-beta": optional array of AnthropicBeta`

954984

955985 Optional header to specify the beta version(s) you want to use.

from line 1244

12141244

12151245### Headers

12161246

1247- `"anthropic-version": optional string`

1248

1249 The version of the Claude API you want to use.

1250

1251 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

1252

12171253- `"anthropic-beta": optional array of AnthropicBeta`

12181254

12191255 Optional header to specify the beta version(s) you want to use.

from line 1497

14611497

14621498### Headers

14631499

1500- `"anthropic-version": optional string`

1501

1502 The version of the Claude API you want to use.

1503

1504 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

1505

14641506- `"anthropic-beta": optional array of AnthropicBeta`

14651507

14661508 Optional header to specify the beta version(s) you want to use.

from line 1754

17121754- `environment_id: string`

17131755

17141756### Headers

1757

1758- `"anthropic-version": optional string`

1759

1760 The version of the Claude API you want to use.

1761

1762 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

17151763

17161764- `"anthropic-beta": optional array of AnthropicBeta`

17171765

api/beta/environments/work/ack Changed · +6 / -0 lines

from line 19

1919

2020## Headers

2121

22- `"anthropic-version": optional string`

23

24 The version of the Claude API you want to use.

25

26 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

27

2228- `"anthropic-beta": optional array of AnthropicBeta`

2329

2430 Optional header to specify the beta version(s) you want to use.

api/beta/environments/work/heartbeat Changed · +6 / -0 lines

from line 29

2929

3030## Headers

3131

32- `"anthropic-version": optional string`

33

34 The version of the Claude API you want to use.

35

36 Read more about versioning and our version history [here](https://platform.claude.com/docs/en/api/versioning).

37

3238- `"anthropic-beta": optional array of AnthropicBeta`

3339

3440 Optional header to specify the beta version(s) you want to use.

One read of Claude Developer Platformapi-20261009T153709Z

What this read moved

about-claude/model-deprecations Changed · +8 / -8 lines

about-claude/models/choosing-a-model Changed · +5 / -1 lines

about-claude/models/optimizing-for-cost-and-intelligence Changed · +21 / -12 lines

about-claude/pricing Changed · +13 / -12 lines

agents-and-tools/tool-use/advisor-tool Changed · +32 / -30 lines

agents-and-tools/tool-use/bash-tool Changed · +4 / -4 lines

agents-and-tools/tool-use/browser-use-tool Changed · +1 / -4 lines

agents-and-tools/tool-use/computer-use-tool Changed · +5 / -5 lines

agents-and-tools/tool-use/define-tools Changed · +6 / -4 lines

agents-and-tools/tool-use/text-editor-tool Changed · +4 / -3 lines

agents-and-tools/tool-use/troubleshooting-tool-use Changed · +1 / -1 lines

api/beta Changed · +1120 / -0 lines

api/beta/agents Changed · +12 / -0 lines

api/beta/deployments Changed · +16 / -0 lines

api/beta/dreams Changed · +10 / -0 lines

api/beta/environments Changed · +84 / -0 lines

api/beta/environments/archive Changed · +6 / -0 lines

api/beta/environments/create Changed · +6 / -0 lines

api/beta/environments/delete Changed · +6 / -0 lines

api/beta/environments/list Changed · +6 / -0 lines

api/beta/environments/retrieve Changed · +6 / -0 lines

api/beta/environments/update Changed · +6 / -0 lines

api/beta/environments/work Changed · +48 / -0 lines

api/beta/environments/work/ack Changed · +6 / -0 lines

api/beta/environments/work/heartbeat Changed · +6 / -0 lines