Home Docs Claude Developer Platform

One capture · api

One read of Claude Developer Platformapi-20260924T220709Z

7 pages moved out of 637 read.

Pages moved 7 significant first

Pages read 637 in this capture

Captured 24 Sep 2026 22:07 UTC

Corpus hash 50afa88b94b4 corpus-hash

What this read moved

1-7 of 7

build-with-claude/refusals-and-fallback Changed · +9 / -17 lines

from line 180

180180* `category` and `explanation` are both `null` when the refusal does not map to a named category. That `null` is a normal, permanent value, not a placeholder.

181181* `stop_details` itself is `null` for every stop reason other than `refusal`.

182182

183| `category` | What it means | Billed before any output |

184| ------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------ |

185| `"cyber"` | The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. | No |

186| `"bio"` | The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. | Yes |

187| `"frontier_llm"` | The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger this category. | Yes |

188| `"reasoning_extraction"` | The request asks the model to reproduce its internal reasoning in the response text. To get reasoning in a structured form instead, use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking). | Yes |

189| `"general_harms"` | The request falls under a usage-policy area outside the four named categories. Benign work can also trigger this category. | No |

183| `category` | What it means |

185| `"cyber"` | The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category. |

186| `"bio"` | The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category. |

189| `"general_harms"` | The request falls under a usage-policy area outside the four named categories. Benign work can also trigger this category. |

190190

191191A refusal can arrive before any output, or mid-stream after partial output. In either case, treat any partial output as incomplete and discard it.

192192

193193## How refusals are billed

194194

195These billing rules apply on every platform: the Claude API, Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry.

195You are not billed for a refusal that arrives before any output. `content` is empty, and token counts appear in `usage` but are not charged. The request still counts against your rate limits. A mid-stream refusal bills the input tokens and the output already streamed at normal rates.

196196

197**Refusals before any output:** To disrupt attempts to circumvent Anthropic's safeguards at scale, a refusal that arrives before any output is billed when its `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. These are the categories where Anthropic measures low volumes of false positives, as of September 2026. These refusals are billed like any other request, at the rates of the model that ran it. A refusal before any output in any other category, or with a `null` category, is not billed. Either way, `content` is empty and token counts appear in `usage`. The request still counts against your rate limits.

198

199**Mid-stream refusals:** A mid-stream refusal bills the input tokens and the output already streamed at normal rates.

200

201**Fallback:** When you use fallback, the refusal that triggered it is billed, in addition to the fallback request, when it arrived mid-stream or is in one of the billed categories. [Fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) compensates for the fallback request's prompt-cache miss, so you don't pay to cache the conversation twice. For how server-side fallback reports each attempt, see [Billing and rate limits](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#billing-and-rate-limits).

202

203The billed categories may change as Anthropic keeps measuring and refining its safeguards' false positive rates. The **Billed before any output** column in the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) lists the billed categories.

204

205197## Picking a fallback approach

206198

207199There are three ways to retry a refused request on another model. The right one depends on where you are running and how much control you need.

from line 737

745737

746738### Billing and rate limits

747739

748Each attempt follows the rules in [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed), at the rates of the model that ran it. An attempt that declined before producing any output is billed only when its refusal category is billed, and its tokens are reported on its `usage.iterations` entry either way. Every attempt that produced output, including one that declined partway through its response, is billed separately. The `usage.iterations` array is the per-attempt record of what you're billed. The top-level `usage` counts describe only the attempt that produced the returned message. Tokens from different models are never summed into one field.

740An attempt that declined before producing any output is not billed: its tokens are reported on its `usage.iterations` entry but not charged. Every attempt that produced output, including one that declined partway through its response, is billed separately at the rates of the model that ran it. The `usage.iterations` array is the per-attempt record of what you're billed. The top-level `usage` counts describe only the attempt that produced the returned message. Tokens from different models are never summed into one field.

749741

750742Every attempt that runs, including one that declined, counts against its own model's rate limits.

751743

release-notes/overview Changed · +0 / -4 lines

### September 24, 2026

from line 12

1212 For updates to Claude Code, see the [complete CHANGELOG.md](https://github.com/anthropics/claude-code/blob/main/CHANGELOG.md) in the `claude-code` repository.

1313</Tip>

1414

15### September 24, 2026

17* We're expanding which refusals are billed to include refusals that arrive before any output when `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`, the categories where we measure low volumes of false positives. Mid-stream refusals were already billed. The newly billed refusals are charged like any other request, at the rates of the model that ran it. Refusals before any output in other categories are still not billed, and fallback credit is unchanged. This change applies on all platforms. See [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).

1915### September 23, 2026

2016

2117* [Cache diagnostics](https://platform.claude.com/docs/en/build-with-claude/cache-diagnostics) is out of beta on the Claude API and no longer requires the `cache-diagnosis-2026-04-07` beta header. Include the `diagnostics` object on a Messages request to opt in; requests that still send the header work as before. Responses from `POST /v1/messages` now always include the `diagnostics` field, which is `null` when the request did not include the `diagnostics` object.

models/fable-5-1/whats-new-fable-5-1 Changed · +1 / -1 lines

from line 403

403403

404404* **Refusals:** a declined request returns HTTP 200 with `stop_reason: "refusal"` and a [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) object naming the policy area that fired.

405405* **Fallback:** retry a refused request on another model with [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback), the [SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback), or your own retry. `fallbacks: "default"` (beta) retries a declined request on the model Anthropic recommends for that category. The permitted fallback targets for Claude Fable 5.1 are Claude Opus 4.8 and Claude Opus 5.

406* **Billing:** a refusal that arrives before any output is billed when it's in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale ([How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed)). Before September 24, 2026, these refusals weren't billed. A mid-stream refusal bills the input tokens and the output already streamed at normal rates. For Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching models.

406* **Billing:** you aren't billed for a refusal that arrives before any output, and, for Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching models.

407407

408408## Pricing

409409

models/fable-5/introducing-claude-fable-5-and-claude-mythos-5 Changed · +1 / -1 lines

from line 48

4848

4949### Billing

5050

51A refusal that arrives before any output is billed when it is in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale. Before September 24, 2026, these refusals were not billed. A mid-stream refusal bills the input tokens and the output already streamed at normal rates. For the billed categories, see [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed). When you retry on another model, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching, so you avoid paying that cost twice.

51You are not billed for a request that is refused before any output is generated. When you retry on another model, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) refunds the prompt-cache cost of switching, so you avoid paying that cost twice.

5252

5353## Availability

5454

models/fable-5/migration-guide Changed · +1 / -1 lines

from line 680

680680

6816815. **Safety classifiers and the `refusal` stop reason (Claude Fable 5 only):** `claude-fable-5` runs safety classifiers on requests and during response generation. Claude Mythos 5 does not include these classifiers. When a classifier declines a request, the Messages API returns `stop_reason: "refusal"` as a successful HTTP 200 response, not an error. The `stop_details.category` field reports which classifier fired, with categories such as `"cyber"`, `"bio"`, and `"reasoning_extraction"`, or `null` when the refusal maps to no named category. See the [refusal category table](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) for the full set.

682682

683 A refusal that arrives before any output is billed when its category is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. A refusal before any output in any other category, or with a `null` category, is not billed ([How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed)). Before September 24, 2026, no refusal before any output was billed on Claude Fable 5. When a classifier fires mid-stream, the input and already-streamed output are billed; discard the partial output.

683 You are not billed for the input tokens of a request refused before any output is generated. When a classifier fires mid-stream, the input and already-streamed output are billed; discard the partial output.

684684

685685 To re-run refused requests on another model automatically, pass the opt-in `fallbacks` parameter, which is in beta on the Claude API. The parameter is not available on the Message Batches API or on Amazon Bedrock, Google Cloud, and Microsoft Foundry; on those three platforms, run the retry client-side or use the SDK refusal-fallback middleware. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).

686686

models/opus-5-5/whats-new-opus-5-5 Changed · +1 / -1 lines

from line 88

8888

8989## Refusals and fallback

9090

91Claude Opus 5.5 ships with safety classifiers, and everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies. A declined request returns HTTP 200 with `stop_reason: "refusal"` and a [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response) object naming the policy area, so handle refusals and configure fallback: retry on another model with [server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-side-fallback) (`fallbacks: "default"`, in beta, retries on the model Anthropic recommends for that category), the [SDK middleware](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback), or your own retry. Whether a refusal that arrives before any output is billed depends on its refusal category, and it counts against your rate limits either way; see [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).

9292

9393## Pricing

9494

test-and-evaluate/strengthen-guardrails/handle-streaming-refusals Changed · +3 / -1 lines

from line 45

4545When you receive **`stop_reason`: `refusal`**, you must reset the conversation context before continuing. You can remove or rephrase the turn that triggered the refusal, or clear the conversation history entirely. Attempting to continue without resetting will result in continued refusals.

4646

4747<Note>

48 Usage metrics are still provided in the response, even when the response is refused. Whether a refused request is billed depends on when the refusal arrives and its category; see [How refusals are billed](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#how-refusals-are-billed).

48 Usage metrics are still provided in the response, even when the response is refused.

50 When a refusal arrives before Claude generates any output, you are not billed for the request on the Claude API, and the usage counts in that response are informational only. When Claude generates output before the refusal, you are billed for that request.

4951</Note>

5052

5153<Tip>