Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations: changedmodels/fable-5-1/migration-guide
Nearest release: v2.1.318, published 4 hours before this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.
Recorded here
Lines+6added
Lines−6removed
From line
66
where the diff opens
First seen
1 Sep 2026
this site's first read of the page
Recorded edits35to this page, all time
The whole hunk
from line 66, old and new numbered
/
from line 66
6666 curl -sS https://api.anthropic.com/v1/messages \
6767 -H "content-type: application/json" \
6868 -H "x-api-key: $ANTHROPIC_API_KEY" \
69 -H "anthropic-version: 2023-06-01" \
69 -H "anthropic-version: 2026-10-21" \
7070 -d '{
7171 "model": "claude-fable-5",
7272 "max_tokens": 16000,
from line 304
304304 curl -sS https://api.anthropic.com/v1/messages \
305305 -H "content-type: application/json" \
306306 -H "x-api-key: $ANTHROPIC_API_KEY" \
307 -H "anthropic-version: 2023-06-01" \
307 -H "anthropic-version: 2026-10-21" \
308308 -d '{
309309 "model": "claude-fable-5-1",
310310 "max_tokens": 16000,
from line 574
574574 curl -sS https://api.anthropic.com/v1/messages \
575575 -H "content-type: application/json" \
576576 -H "x-api-key: $ANTHROPIC_API_KEY" \
577 -H "anthropic-version: 2023-06-01" \
577 -H "anthropic-version: 2026-10-21" \
578578 -d '{
579579 "model": "claude-fable-5-1",
580580 "max_tokens": 16000,
from line 939
939939 ```bash cURL
940940 curl https://api.anthropic.com/v1/messages \
941941 -H "x-api-key: $ANTHROPIC_API_KEY" \
942 -H "anthropic-version: 2023-06-01" \
942 -H "anthropic-version: 2026-10-21" \
943943 -H "anthropic-beta: thinking-binding-controls-2026-08-01" \
944944 -H "content-type: application/json" \
945945 -d '{
from line 1234
12341234 # Effort-only system message: the new level takes effect from the next user turn.
12351235 curl https://api.anthropic.com/v1/messages \
12361236 -H "x-api-key: $ANTHROPIC_API_KEY" \
1237 -H "anthropic-version: 2023-06-01" \
1237 -H "anthropic-version: 2026-10-21" \
12381238 -H "anthropic-beta: mid-conversation-output-config-2026-07-01" \
12391239 -H "content-type: application/json" \
12401240 -d '{
from line 1497
14971497
14981498 Placed between an `assistant` turn and the next `user` turn, as here, the message takes effect from that `user` turn. Placed directly after a `user` turn with new input, it sets the level for Claude’s reply to that turn. A `user` turn that holds only tool results doesn’t count as new input: the change waits for the next `user` turn with new input. The level then holds until another `role: "system"` message changes it. Only the named levels are accepted (`low`, `medium`, `high`, `xhigh`, `max`), and the `mid-conversation-output-config-2026-07-01` beta header is required. See [Per-message effort](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta).
14991499
15002. **Change instructions and tools with mid-conversation system messages:** To change instructions or tools partway through a session, append a [`role: "system"` message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), with `tool_addition` and `tool_removal` blocks for tool changes. On the Claude API, Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed), send the beta header `inline-tools-2026-09-15` for tool changes. A `tool_addition` block can name a tool declared in `tools` at session start or [carry the tool’s full definition](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta), so a tool that is unknown at session start doesn’t need to be in `tools`. This preserves prompt cache hits on earlier turns and keeps the conversation history append-only. The older `mid-conversation-tool-changes-2026-07-01` header still works for changes that name a tool by reference, on the Claude API, Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed), and Claude Models on Google Cloud (Google managed). The same message replaces forced `tool_choice` when a specific tool must run on the current turn (see [Breaking changes](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-breaking-changes)). For a reminder that applies to one turn only, send it as a separate text-only `role: "system"` message with `clear_at: "next_user_message"` ([turn-scoped system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages), beta header `mid-conversation-system-clear-at-2026-08-21`) and leave it in the history: it stops rendering after the next user message and costs no tokens once cleared. A message that carries `tool_addition` or `tool_removal` blocks can’t be turn-scoped.
15002. **Change instructions and tools with mid-conversation system messages:** To change instructions or tools partway through a session, append a [`role: "system"` message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages), with `tool_addition` and `tool_removal` blocks for tool changes. On the Claude API, Claude Platform on AWS, and Claude Models on Google Cloud (Anthropic managed), send the beta header `inline-tools-2026-09-15` for tool changes. A `tool_addition` block can name a tool declared in `tools` at session start or [carry the tool’s full definition](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#define-tools-in-a-message-beta), so a tool that is unknown at session start doesn’t need to be in `tools`. This preserves prompt cache hits on earlier turns and keeps the conversation history append-only. The `mid-conversation-tool-changes-2026-07-01` header works for changes that name a tool by reference, on the Claude API, Amazon Bedrock, Claude Platform on AWS, Claude Models on Google Cloud (Anthropic managed), and Claude Models on Google Cloud (Google managed). The same message replaces forced `tool_choice` when a specific tool must run on the current turn (see [Breaking changes](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#fable-5-1-breaking-changes)). For a reminder that applies to one turn only, send it as a separate text-only `role: "system"` message with `clear_at: "next_user_message"` ([turn-scoped system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages#turn-scoped-system-messages), beta header `mid-conversation-system-clear-at-2026-08-21`) and leave it in the history: it stops rendering after the next user message and costs no tokens once cleared. A message that carries `tool_addition` or `tool_removal` blocks can’t be turn-scoped.
15011501
150215023. **Use `fallbacks: "default"` for refusals:** Keep handling `stop_reason: "refusal"` and reading `stop_details.category` before response content. To re-run refused requests on another model automatically, set `fallbacks: "default"` (beta, `server-side-fallback-2026-07-01` header). `"default"` 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 (`claude-opus-4-8`) and Claude Opus 5 (`claude-opus-5`). An explicit `fallbacks` list may name either. The fallback model doesn’t receive Claude Fable 5.1’s thinking blocks. The `fallbacks` parameter isn’t available on Amazon Bedrock, Claude Models on Google Cloud (Google managed), or Microsoft Foundry. On those platforms, use [client-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#client-side-fallback) instead. If you build the retry yourself, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fallback-credit) applies on the same terms as Claude Fable 5. See [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback).
15031503
No line in this hunk matches that.