---
title: Claude Fable 5 on AWS (June 2026): Mythos-Class Models, Safeguards, and What Changes for Bedrock Teams
description: On September 1, 2026 AWS GA’d Claude Fable 5.1: 1M-token context, 128K output, Covered Model with 30-day retention. Fable 5 (June 9) remains the prior pin. This post covers the fit decision.
url: https://www.joinhorizon.co/blog/claude-fable-5-aws-bedrock-mythos-class-guide-2026/
datePublished: 2026-06-10T00:00:00.000Z
dateModified: 2026-10-28T00:00:00.000Z
author: palaniappan-p
category: AI Agents
tags: amazon-bedrock, claude, anthropic, foundation-models, generative-ai, aws, ai-agents
---

# Claude Fable 5 on AWS (June 2026): Mythos-Class Models, Safeguards, and What Changes for Bedrock Teams

> On September 1, 2026 AWS GA’d Claude Fable 5.1: 1M-token context, 128K output, Covered Model with 30-day retention. Fable 5 (June 9) remains the prior pin. This post covers the fit decision.

> **AWS lifecycle notice (June 30, 2026):** Amazon Bedrock Agents is now **Bedrock Agents Classic**, in maintenance for new customers after **July 30, 2026**. Net-new agent builds should use [Bedrock AgentCore](https://www.joinhorizon.co/blog/amazon-bedrock-agentcore-production/). Full matrix: [lifecycle roundup](https://www.joinhorizon.co/blog/aws-service-lifecycle-updates-june-2026/).

## Successor: Claude Fable 5.1 (September 1, 2026)

AWS GA'd Fable 5.1 as a [Covered Model](https://support.claude.com/en/articles/15425695-covered-models) with **1M** context, **128K** output, and adaptive thinking on by default. Plan for a data-retention and refusal-handling change; the new model ID is not a drop-in swap.

**Previous approach:** Fable 5 GA on **June 9, 2026**: opt-in before first invoke, refusal as a primary code path, long-horizon jobs behind a queue rather than a synchronous Lambda.

**What AWS changed:** on **September 1, 2026**, [Claude Fable 5.1 reached GA on AWS](https://aws.amazon.com/about-aws/whats-new/2026/09/claude-fable-5-1-aws/) via Amazon Bedrock and Claude Platform on AWS. Official [model card](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-fable-5-1.html): **1M-token** context, **128K** max output, knowledge cutoff **June 2026**, adaptive thinking always on (effort low / medium / **high default** / xhigh / max). Model IDs: `anthropic.claude-fable-5-1`, geo `us.anthropic.claude-fable-5-1`, global `global.anthropic.claude-fable-5-1`. Anthropic designated Fable 5.1 a Covered Model (August 31, 2026), with **30-day minimum** retention of prompts and completions; **ZDR is not the default**. Live Fable 5 and 5.1 cards require Data Retention API mode **`aws_review`** (not the `provider_data_share` string this post used at June launch). **Claude Mythos 5.1** is the same underlying model with full cyber and bio capability and stays **limited access**. **Enterprise Frontier Safeguards (EFS)**, which keeps Covered-Model monitoring data in cloud you control, rolls out in phases beginning **fall 2026**; it is not generally available today. Eligible customers may get a limited-time ZDR transition toward EFS; Anthropic or AWS contacts those orgs directly.

AWS and Anthropic describe 5.1 as better on the hardest reasoning vs Fable 5, with better judgement on ambiguous work, fewer confident wrong answers, and a habit of saying when it is stuck instead of reporting success. Those are **their** claims, and we did not independently re-run the Fable 5 modeled pilot on 5.1.

**When it matters:** multi-hour coding or research jobs that already justified Fable 5, once legal accepts Covered Model retention / `aws_review` (or an eligible EFS/ZDR transition Anthropic or AWS offered you in writing).

**When it does not:** chat, classification, latency SLOs, or any workload that still meets quality on [Sonnet 5](https://www.joinhorizon.co/blog/claude-sonnet-5-aws-bedrock-2026/), [Opus 5](https://www.joinhorizon.co/blog/claude-opus-5-aws-bedrock-2026/) (ZDR default on Bedrock), or Nova. Do not move those lanes for the version number, and do not architect production on Mythos 5.1.

This post keeps the June Fable 5 field notes below. Pin `anthropic.claude-fable-5-1` only after the governance path below is signed.

---

On **June 9, 2026**, AWS [announced](https://aws.amazon.com/about-aws/whats-new/2026/06/claude-fable-5-aws/) general availability of **Claude Fable 5** on [Amazon Bedrock](https://aws.amazon.com/bedrock/) and [Claude Platform on AWS](https://aws.amazon.com/claude-platform/), Anthropic's first **Mythos-class** model available to all customers, with safeguards designed for broader enterprise use. The [AWS News Blog post](https://aws.amazon.com/blogs/aws/anthropic-claude-fable-5-on-aws-mythos-class-capabilities-with-built-in-safeguards-now-available/) frames it as a step-change in long-running knowledge work, software engineering, and vision rather than another incremental Sonnet refresh.

If you run production GenAI on Bedrock today, the announcement changes three things a feature bullet list will not show: **(1)** you must opt into data retention review before the first invoke, **(2)** refusal handling becomes a primary code path, and **(3)** the unit of work shifts from "one API call" to "one autonomous job that may run for hours." This post covers what Fable 5 is, how it differs from Mythos 5 and Claude 4.6, which workloads should move first, and (as of September 2026) how Fable 5.1 changes the governance gate.

> **Benchmark pattern (Fable 5-era, not a cited client, not a 5.1 bakeoff):** Modeled a compliance-heavy B2B SaaS: ~180 multi-page PDF contracts/month through a Bedrock extraction pipeline, previously **Claude 3.5 Sonnet** at ~**$3,900/mo** inference (mix of on-demand + partial prompt cache). A two-week Fable 5 pilot on the vision-heavy path (nested tables in exhibits) cut human rework from **~11 hrs/week → ~3 hrs/week** on a 12-document sample, at roughly **2.1×** per-document inference cost vs Sonnet on the same corpus. Net: positive ROI on the document lane only; the chat/classification lane stayed on Nova Lite. We have not re-measured that corpus on Fable 5.1.

---

## What "Mythos-class" means in practice

Prior Claude generations were optimized for strong single-turn and short multi-turn reasoning. **Mythos-class** (Anthropic's term for the capability tier Fable 5 brings to GA) targets a different failure mode: models that lose the thread on **long-horizon** work: multi-file refactors, research synthesis across dozens of sources, or document pipelines where the model must plan, execute, self-check, and continue without a human re-prompting every ten minutes.

Per the [Bedrock model card](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-fable-5.html), Fable 5 ships with:

| Spec             | Value                             | Why it matters architecturally                                                                |
| ---------------- | --------------------------------- | --------------------------------------------------------------------------------------------- |
| Context window   | **1M tokens**                     | Whole codebases + doc corpora in one session, but you still pay for what you send            |
| Max output       | **128K tokens**                   | Long generated artifacts (specs, migration plans) without chunking; watch streaming timeouts |
| Knowledge cutoff | **January 2026**                  | Newer than Sonnet 4.6 family for recent AWS/Anthropic features                                |
| Reasoning        | **Adaptive thinking (always on)** | Cannot disable; adds latency vs "fast mode" Sonnet calls                                      |
| Input modalities | Text + **image**                  | Diagrams, charts, nested PDF tables; the vision story AWS highlights for finance/legal       |
| Launch date      | **June 9, 2026**                  | Standard inference tier; Priority/Flex/Reserved not listed at launch                          |

The capabilities AWS emphasizes in the announcement, namely **long-running asynchronous execution**, **advanced vision**, and **proactive self-verification** (updating skills, building evaluation harnesses, checking its own output), imply your orchestration layer must support **checkpointing, idempotent retries, and human-in-the-loop gates** on jobs that outlive a single Lambda timeout or API Gateway limit.

---

## Fable vs Mythos: the safeguard split

AWS and Anthropic ship two names for nearly the same frontier capability, now in two generations:

- **Claude Fable 5 / Fable 5.1:** GA on Bedrock. Includes **safeguards**: in sensitive domains (cybersecurity, biology, chemistry, health), harmful prompts may be refused or receive a response from a **less capable fallback** instead of full Fable capability. Blocking classifiers also return `stop_reason: "refusal"` for dual-use content. Both are **Covered Models**.
- **Claude Mythos 5 / Mythos 5.1:** Same underlying capability **without** those Fable limits. **Limited access** (approved partners). Mythos 5.1 retains full cyber and bio capability. Do not architect production on it.

**We recommend Fable 5.1** (or a pinned Fable 5 until legal signs `aws_review`) for any long-horizon workload that touches production customer data or faces external auditors. Mythos 5 and **Mythos 5.1** are research and red-team surfaces, not a default production route. If your security team asks "can we get the unrestricted model," the honest answer is: not through normal enterprise procurement, and you probably should not want it on a customer-facing path.

---

## Two front doors on AWS: Bedrock vs Claude Platform on AWS

![Architecture diagram of an application choosing Amazon Bedrock or Claude Platform on AWS](../../assets/images/blog/claude-fable-5-aws-bedrock-mythos-class-guide-2026-doors.webp)

_Figure: the two front doors in the article. Bedrock keeps IAM, SCPs, CloudTrail, and Guardrails. Claude Platform on AWS keeps Anthropic-native UX with AWS billing. Pick one path per workload. No model prices are shown. [Open the draw.io source](https://www.joinhorizon.co/examples/architecture-blog-2026/claude-fable-5-aws-bedrock-mythos-class-guide-2026/doors.drawio)._

| Concern        | Amazon Bedrock                                                         | Claude Platform on AWS                                                                                       |
| -------------- | ---------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------ |
| Governance     | IAM, SCPs, CloudTrail, PrivateLink                                     | AWS billing + auth; Anthropic-native UX                                                                      |
| Composition    | Guardrails, Knowledge Bases, Agents, Flows                             | Anthropic platform features first                                                                            |
| API surface    | Converse, Invoke, Messages API on `bedrock-runtime` / `bedrock-mantle` | Claude Platform APIs (see [docs](https://docs.aws.amazon.com/claude-platform/latest/userguide/welcome.html)) |
| Data residency | Regional inference profiles (in-region / geo / global)                 | Confirm per Claude Platform on AWS guidance                                                                  |

**Pick Bedrock** when the app already lives inside your AWS compliance boundary. **Pick Claude Platform on AWS** when the buyer is a team that wants Anthropic's native experience but needs AWS procurement. Do not pick it if you need to compose with an existing Bedrock RAG stack without re-plumbing.

For invoke patterns, AWS documents both the **Anthropic Messages API** on `bedrock-mantle` and the **Converse API** on `bedrock-runtime`:

```python
# Converse API — boto3, us-east-1, Fable 5.1 (Sep 2026). Swap to anthropic.claude-fable-5 if still pinned.
import boto3

bedrock = boto3.client("bedrock-runtime", region_name="us-east-1")
response = bedrock.converse(
    modelId="global.anthropic.claude-fable-5-1",
    messages=[{"role": "user", "content": [{"text": "Your prompt"}]}],
    inferenceConfig={"maxTokens": 4096},
)
print(response["output"]["message"]["content"][0]["text"])
```

Model IDs and regional endpoints are in the [Fable 5.1 model card](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-fable-5-1.html). Pin `anthropic.claude-fable-5-1` for strict in-region, or `global.anthropic.claude-fable-5-1` when residency allows global routing. Fable 5 IDs remain valid for prior pins.

---

## The gate most teams miss: data retention opt-in

You cannot invoke Fable 5 or **Fable 5.1** until you opt in via the **Data Retention API**. Live [Fable 5](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-fable-5.html) and [Fable 5.1](https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-anthropic-claude-fable-5-1.html) model cards require mode **`aws_review`**. (June 2026 launch copy used `provider_data_share`. That string is stale; do not copy it into new runbooks.)

```bash
curl -X PUT "https://bedrock-mantle.us-east-1.api.aws/v1/data_retention" \
  -H "x-api-key: <your-bedrock-api-key>" \
  -H "Content-Type: application/json" \
  -d '{"mode": "aws_review"}'
```

Both models are **Covered Models**: Anthropic requires **30-day minimum retention** of inputs and outputs plus safety review. **ZDR is not the default.** That trade suits frontier safety at scale, and it is a **hard stop** for some regulated workloads until legal signs off. We have seen security reviews stall here while engineering already merged the model ID into staging.

**Enterprise Frontier Safeguards (EFS)** (AWS + Anthropic) is meant to let eligible customers keep Covered-Model monitoring data in cloud they control. It **rolls out in phases beginning fall 2026**, so treat it as upcoming and not live for every Bedrock account. A limited-time ZDR option for eligible orgs is a **transition toward EFS**, not a standing Bedrock default (contrast with [Opus 5](https://www.joinhorizon.co/blog/claude-opus-5-aws-bedrock-2026/), which is ZDR by default on Bedrock).

> **Reproduce this:** Copy [`data-retention-opt-in.sh`](https://www.joinhorizon.co/examples/architecture-blog-2026/claude-fable-5-bedrock/data-retention-opt-in.sh) and [`refusal-handler-example.py`](https://www.joinhorizon.co/examples/architecture-blog-2026/claude-fable-5-bedrock/refusal-handler-example.py) from `examples/architecture-blog-2026/claude-fable-5-bedrock/`. Run the opt-in script in a sandbox account after security review; run the Python handler to see refusal fallback wiring.

If your org already runs [HIPAA-eligible Bedrock](https://www.joinhorizon.co/blog/hipaa-compliant-ai-aws-bedrock/) workloads, treat Fable as a **new sub-process**. The BAA covers Bedrock; **Covered Model retention** is an additional disclosure decision.

---

## Refusals are not errors, so redesign your response path

![Architecture diagram of a Bedrock refusal routed to a fallback model or a person](../../assets/images/blog/claude-fable-5-aws-bedrock-mythos-class-guide-2026-refuse.webp)

_Figure: refusal handling in the article. Classifiers return 200 with stop_reason refusal. Prompt-stage blocks are not billed. Mid-generation refusals need a fallback model or a person, not another blind retry. [Open the draw.io source](https://www.joinhorizon.co/examples/architecture-blog-2026/claude-fable-5-aws-bedrock-mythos-class-guide-2026/refuse.drawio)._

The model card is explicit: Fable 5's refusal rates are **materially higher** than previous Claude models. Classifiers return HTTP **200** with `stop_reason: "refusal"` and a `stop_details` category, not `4xx`.

| Refusal timing                          | Billing                        | What your app should do                                               |
| --------------------------------------- | ------------------------------ | --------------------------------------------------------------------- |
| Prompt-stage (blocked before inference) | Not billed                     | Log, route to human review or approved fallback model                 |
| Mid-stream (partial output then block)  | Billed for tokens before block | Persist partial output if safe; do not blindly retry identical prompt |

> **What broke:** In the modeled pilot, **4 of 120** contract prompts (security-addendum language touching vulnerability disclosure) returned `refusal` on Fable 5 where Sonnet had completed normally. Downstream JSON schema validation failed because the handler treated 200 + refusal as success. Fix: branch on `stopReason` before parsing; queue refusals to a paralegal review bucket instead of retry loops. Retry loops would have doubled cost on mid-stream refusals.

We recommend **Bedrock Guardrails** ([production setup guide](https://www.joinhorizon.co/blog/how-to-set-up-amazon-bedrock-guardrails-production/)) _in addition to_ Fable's built-in classifiers, for defense in depth on PII and prompt injection. They do not replace refusal handling.

---

## When to move workloads and when to stay on Sonnet or Nova

Use the decision matrix in [`model-selection-decision-matrix.md`](https://www.joinhorizon.co/examples/architecture-blog-2026/claude-fable-5-bedrock/model-selection-decision-matrix.md). Short version:

**Move first to Fable 5.1** (or keep a Fable 5 pin until legal signs):

- Long-horizon **coding agents** (multi-file refactors, test harness generation) where [Claude Code-style skills](https://www.joinhorizon.co/blog/terraform-claude-skill-aws-production-guide/) already proved value but hit context ceilings
- **Vision-heavy document** pipelines (financial statements, legal exhibits, architecture diagrams in PDFs)
- **Async research** jobs orchestrated through [Bedrock AgentCore](https://www.joinhorizon.co/blog/amazon-bedrock-agentcore-production/) or Step Functions with checkpointing

**Stay on Claude Sonnet 5 / Haiku or [Nova](https://www.joinhorizon.co/blog/aws-bedrock-nova-models-guide/):**

- Customer chat under **500 ms p99** latency pressure
- High-volume classification and moderation
- Workloads where **Covered Model retention / `aws_review`** is not approved
- Cost-sensitive token volumes: Fable is frontier-priced; [token budget discipline](https://www.joinhorizon.co/blog/aws-bedrock-cost-optimization-token-budgets-model-selection/) still applies. Verify live rates on [Bedrock pricing](https://aws.amazon.com/bedrock/pricing/); we do not quote an unpublished Fable 5.1 $/MTok here.

**Opinionated take:** Fable is a **job runner**, not a Sonnet upgrade. If your architecture diagram still shows "API Gateway → Lambda → Bedrock" as a single synchronous box, Fable belongs behind a **queue and worker** (SQS + ECS/Lambda with extended timeout, or [AgentCore](https://www.joinhorizon.co/blog/amazon-bedrock-agentcore-production/) for managed agent runtime) and not in the hot request path.

---

## Composing with the Bedrock stack you already have

Fable 5 inherits the Bedrock features you use for other Anthropic models, with launch caveats on service tiers:

- **[Knowledge Bases](https://www.joinhorizon.co/blog/how-to-build-rag-pipeline-amazon-bedrock-knowledge-bases/):** sensible for long document grounding; pair with prompt caching (1,024-token minimum checkpoint, up to 4 checkpoints, 5 min / 1 hr TTL per model card)
- **Guardrails:** still your app-level PII/topic policy; Fable adds model-level classifiers underneath
- **Agents and Flows:** natural fit for multi-step jobs; ensure tool-use loops have spend caps
- **Cross-region inference:** use geo/global profiles for throughput; re-check [data residency](https://www.joinhorizon.co/blog/aws-data-residency-sovereignty-guide-2026/) if prompts contain regulated data

With [OpenAI models now on Bedrock](https://www.joinhorizon.co/blog/amazon-bedrock-openai-models-codex-managed-agents/), Fable 5.1 completes a "**route by job shape**" portfolio: OpenAI for Codex-style coding surfaces, Fable for long autonomous Anthropic work (Covered Model gate), Sonnet 5 / Opus 5 / Nova for volume and ZDR-sensitive lanes.

---

## What to do this week

1. **Legal/security review** of Covered Model retention and **`aws_review`** before any staging invoke. Do not assume ZDR; EFS is fall 2026, not generally available.
2. **Enable opt-in** in a sandbox account using the Data Retention API (script in artifacts folder).
3. **Bake off Fable 5 vs 5.1 on one long-horizon job**, not your highest-QPS API. Measure refusal rate, cost per completed job, and human rework hours saved. Do not promote on the version number.
4. **Add `stop_reason: refusal` handling** to your Bedrock client wrapper, as a first-class outcome.
5. **Pin model IDs** per environment (`anthropic.claude-fable-5-1` vs `global.anthropic.claude-fable-5-1`) and document the residency implication. Keep Fable 5 IDs if that lane is still pinned.
6. **Leave chat/classification on Sonnet 5, Opus 5, or Nova** until the pilot proves ROI on the document or agent lane.

**If you only do one thing:** Run the `aws_review` and refusal-handling review **before** you change the model ID in production config. The model works on day one; the governance and client-code paths are what break.

---

## What this post does not cover

- **On-demand pricing per million tokens:** verify live rates on [Bedrock pricing](https://aws.amazon.com/bedrock/pricing/); we do not quote unpublished Fable 5.1 list rates.
- **Claude Mythos 5 / Mythos 5.1 access:** limited / approved-partner only. No enterprise architecture should depend on them.
- **Enterprise Frontier Safeguards (EFS)** implementation details: fall 2026 rollout; confirm with AWS/Anthropic when your account is eligible. Do not treat EFS as generally available.
- **Claude Platform on AWS** feature parity with anthropic.com: we focused on Bedrock because that is where most AWS-native apps compose.
- **Fable 5.1 bakeoff numbers:** AWS cites Anthropic's internal evals; we did not independently re-run the Fable 5 modeled pilot on 5.1. The hours and cost figures above are Fable 5-era.

**Related:** [Bedrock vs OpenAI API for enterprise](https://www.joinhorizon.co/blog/aws-bedrock-vs-openai-api-enterprise/) · [Bedrock cost optimization](https://www.joinhorizon.co/blog/aws-bedrock-cost-optimization-token-budgets-model-selection/) · [Building Bedrock Agents Classic with tool use](https://www.joinhorizon.co/blog/how-to-build-amazon-bedrock-agent-tool-use-2026/) · [Generative AI on AWS consulting](https://www.joinhorizon.co/services/generative-ai-on-aws/)

## Related reading

- [How to Set Up Amazon Q for Business with SharePoint and S3](https://www.joinhorizon.co/blog/how-to-set-up-amazon-q-for-business-sharepoint-s3/)

## FAQ

### What is Claude Fable 5.1 and how is it different from Fable 5 and Mythos 5.1?
Claude Fable 5.1 is Anthropic’s current generally available Mythos-class model on AWS (announced September 1, 2026). AWS positions it as a step up from Fable 5 (June 9, 2026) on hard reasoning, ambiguous work, and fewer confident wrong answers. It has a 1M-token context, up to 128K output, and adaptive thinking always on. Both Fable 5 and Fable 5.1 are Covered Models: 30-day minimum retention of prompts and completions. Claude Mythos 5.1 is the same underlying model with full cyber and bio capability retained; AWS limits it to approved partners. For most enterprises, Fable 5.1 is the production path; do not architect on Mythos 5.1.

### What do I have to do before I can invoke Claude Fable 5 or 5.1 on Bedrock?
You must opt in via the Bedrock Data Retention API with mode aws_review (the live Fable 5 and 5.1 model cards require this, not provider_data_share). Anthropic designates both as Covered Models: 30-day minimum retention of inputs and outputs, plus safety review. Zero data retention is not the default. Enterprise Frontier Safeguards (EFS), which keeps monitoring data in cloud you control, rolls out in phases beginning fall 2026; it is not generally available today. If legal has not approved Covered Model retention, do not route production traffic yet.

### How do refusals work on Claude Fable 5 and Fable 5.1?
Both include blocking classifiers for dual-use content (cybersecurity and life sciences on 5.1). When a classifier fires, the API returns HTTP 200 with stop_reason "refusal" rather than an error code. Refusal rates are materially higher than on prior Claude models. Prompt-stage refusals are not billed; mid-stream refusals bill tokens generated before the block. Production apps must handle refusal as a primary response path, with logging and a defined fallback or human-review route.

### Should we replace Claude Sonnet 5 or Opus 5 with Fable 5.1 for all Bedrock workloads?
No. Fable 5.1 is for long-running, document-heavy, or vision-intensive work where prior models lose coherence or need constant human steering. Short chat, classification, and high-QPS APIs should stay on Sonnet 5, Haiku-class models, or Nova for cost and latency. Fable 5.1 also requires Covered Model retention that Sonnet and Opus 5 (ZDR default on Bedrock) may not. Route by workload shape, not by "newest model."

### Bedrock or Claude Platform on AWS — which should we use?
Use Amazon Bedrock when you need IAM, PrivateLink, regional data residency, and composition with Guardrails, Knowledge Bases, and Agents inside your existing AWS governance. Use Claude Platform on AWS when teams want Anthropic’s native platform experience (projects, Claude-style workflows) with unified AWS billing. Same model family; different control plane and developer UX. Covered Model policies follow the model onto both paths.

### When should we NOT adopt Claude Fable 5.1 yet?
Skip or delay if: (1) legal has not approved Covered Model 30-day retention and aws_review, (2) you were counting on ZDR, which is not the Fable default; EFS is fall 2026 and not generally available, (3) you have not measured refusal rates on your real prompt distribution, (4) the workload is a drop-in Sonnet or Opus 5 replacement on short prompts, or (5) prompts in security/bio domains need predictable frontier capability, since Fable classifiers may refuse or fall back.

### What are the Bedrock model IDs for Claude Fable 5.1?
Base ID is anthropic.claude-fable-5-1. Cross-region: us.anthropic.claude-fable-5-1 (geo) and global.anthropic.claude-fable-5-1 (global). Confirm the live model card before designing for strict in-region residency. Fable 5 IDs (anthropic.claude-fable-5 and global.anthropic.claude-fable-5) remain valid for pinned prior traffic.

---

*Source: https://www.joinhorizon.co/blog/claude-fable-5-aws-bedrock-mythos-class-guide-2026/*