You wired up claude-fable-5, shipped your integration, and then every call started failing. The model isn't broken — it's switched off, and the reason has nothing to do with your code.

Why Is Fable 5 Offline? The Export-Control Directive Explained

Fable 5 is currently unavailable because U.S. export-control authorities ordered Anthropic to suspend it. In mid-June 2026 the directive required Anthropic to cut off Fable 5 and Mythos 5 for any foreign national, inside or outside the US, on national-security grounds . Anthropic could not filter foreign nationals from US users in real time, so it disabled both models globally — for every customer, and even its own foreign-national employees .

Quick Answer: Fable 5 and Mythos 5 launched June 9, 2026 and were suspended around June 13 after a U.S. export-control directive. Anthropic disabled both models for all customers globally — there is no restoration date. Opus 4.8, Sonnet, and Haiku stay live and unaffected.

The two models went live on June 9, 2026 and were pulled roughly four days later . Anthropic told Business Insider the directive's "net effect" was to "abruptly disable" the models for all customers, and said it disputed both the risk characterization and the process .

Treat the legal basis with care: no BIS, Commerce, or White House page confirming the order has surfaced publicly. The outage is reported by TechCrunch, CNBC, MarkTechPost, and Business Insider — while Anthropic's own platform docs still list Fable 5 as generally available. Only Fable 5 and Mythos 5 are suspended; Opus 4.8, Sonnet, and Haiku remain online . So you can build and test the integration patterns below, but don't depend on Fable 5 in production until Anthropic confirms restoration.

What You Need Ready

Setup is the standard Claude onboarding — no special account tier exists for Fable 5. Create a Console account at console.anthropic.com, generate an API key, and you have everything the integration needs . If you already call any Claude model, your existing credentials work unchanged.

Install an official SDK to skip raw HTTP. TypeScript/JS uses npm install @anthropic-ai/sdk; Python uses pip install anthropic; Go, Java, and C# SDKs are also published .

The model ID changes by surface: claude-fable-5 on the Claude API and Vertex AI, and anthropic.claude-fable-5 on Amazon Bedrock . These are pinned snapshot IDs, not evergreen aliases — new weights ship under new ID strings, so hard-coding one will not silently upgrade.

Mythos 5 is not self-serve. Access is brokered through Project Glasswing via an Anthropic, AWS, or Google Cloud account team; there is no public signup path . Treat it as controlled-access and build against Fable 5.

Sending a Fable 5 Request

A Fable 5 call is an ordinary Messages API request: set model: "claude-fable-5", a max_tokens value (up to 128,000 output tokens), and a messages array — the same shape as any Claude call. The model rides a 1M-token context window, and pricing runs $10 per million input tokens and $50 per million output tokens — roughly double Opus 4.8. Prompt caching is metered separately.

• 5-minute cache writes: $12.50/MTok
• 1-hour cache writes: $20/MTok
• Cache hits and refreshes: $1/MTok

Three behaviors break habits from older models. First, adaptive thinking is always on — it is the only thinking mode. Passing thinking: {"type": "disabled"} is unsupported and errors, and there are no manual extended-thinking budgets. You set depth through the effort parameter instead . Second, raw chain-of-thought is never returned: thinking.display resolves to "summarized" or "omitted". In a multi-turn conversation, pass thinking blocks back unchanged within the same Fable 5 session — but strip them when you switch to a different model mid-conversation, or the request will reject.

One compliance note before you build: both Fable 5 and Mythos 5 are Covered Models with mandatory 30-day data retention. Zero-data-retention agreements are unavailable for either, so workloads that contractually require ZDR cannot use these models — though the docs state the retained data is not used for training or any non-safety purpose .

Refusal Handling and the 200 OK Trap

When Fable 5's safety classifier declines a request, the API returns a successful HTTP 200 carrying stop_reason: "refusal" — not a 4xx or 5xx . Any error handler that only catches HTTP failures will pass the refusal straight through as if it were a normal completion, leaving you with empty content and no signal. Branch on stop_reason directly — not on response content, and not on stop_details, which can be null .

The snippet below is verified — it runs and demonstrates the trap. A naive handler that only calls raise_for_status() returns None; the refusal-aware version inspects the message and surfaces the decline.

import json


class Response:
    status_code = 200

    def json(self):
        return {
            "model": "fable-5",
            "choices": [
                {
                    "message": {
                        "role": "assistant",
                        "refusal": "I can't help with that request.",
                        "content": None,
                    },
                    "finish_reason": "stop",
                }
            ],
        }

    def raise_for_status(self):
        if self.status_code >= 400:
            raise RuntimeError(f"HTTP {self.status_code}")


def naive_handler(resp):
    resp.raise_for_status()
    return resp.json()["choices"][0]["message"].get("content")


def refusal_aware_handler(resp):
    resp.raise_for_status()
    msg = resp.json()["choices"][0]["message"]
    if msg.get("refusal"):
        raise ValueError(f"model refused: {msg['refusal']}")
    return msg.get("content")


resp = Response()
print("HTTP status:", resp.status_code)
print("naive handler returned:", naive_handler(resp))
try:
    refusal_aware_handler(resp)
except ValueError as exc:
    print("refusal-aware handler caught:", exc)

Refusals fall into four documented categories: cyber (exploit and agentic hacking), bio (dual-use bio/chem), frontier_llm (model distillation), and reasoning_extraction . Anthropic reports safeguards trigger in fewer than 5% of sessions , so this is an edge case — but a silent one. Billing follows the timing: a refusal before any output is streamed is not billed and does not count against rate limits, while a mid-stream refusal bills input tokens plus already-streamed output, and your handler should discard that partial output .

This handling is Fable 5-specific. Mythos 5 ships without safety classifiers, so stop_reason: "refusal" never applies to it . If you route across both models, gate the refusal branch on the model ID so you are not checking for a state that cannot occur.

Tuning Effort and Wiring Fallback

Once refusals are handled, the two knobs that shape Fable 5 in production are effort and fallback. Fable 5's adaptive thinking is always on, so there are no manual extended-thinking budgets — you control depth with the effort parameter instead . high is the default; low and medium suit routine or latency-sensitive jobs, xhigh targets long-horizon agentic work, and max is reserved for the hardest tasks . Higher effort means longer latency and higher output cost, billed at $50 per million output tokens .

For fallback, the cleanest path is server-side: pass fallbacks: ['claude-opus-4-8'] with the beta header server-side-fallback-2026-06-01. It works on the Claude API and Claude Platform on AWS only — not Message Batches, Bedrock, Vertex AI, or Microsoft Foundry, which need SDK middleware or manual retry . Add the fallback-credit-2026-06-01 header to refund the prompt-cache write cost when switching, so you do not pay to prime the same prompt's cache twice .

Because hard tasks can run for many minutes and autonomous runs for hours, set long timeouts, stream responses for progress feedback, and avoid synchronous blocking harnesses . The takeaway: build the full path now — effort tuning, refusal branching, and clean fallback to claude-opus-4-8 — but treat live Fable 5 traffic as blocked until Anthropic confirms restoration .

Frequently asked questions

When will Fable 5 and Mythos 5 come back online?

There is no official restoration date. Anthropic complied with the mid-June 2026 export-control directive that ordered it to suspend access for any foreign national, but it disputed both the risk characterization and the process used . Until Anthropic confirms otherwise, monitor the platform model docs and Anthropic's announcement channels for a restoration notice. Build your integration now, but do not depend on live traffic.

Why did Anthropic disable Fable 5 globally instead of just blocking foreign nationals?

Because it could not selectively filter foreign nationals from U.S. users in real time. The directive ordered suspension for any foreign national, inside or outside the U.S., so the only way to comply was to disable both models globally — for every customer, and even Anthropic's own foreign-national employees . Business Insider reported Anthropic's framing that the directive's "net effect" was to abruptly disable the models for all customers .

What is stop_reason: "refusal" and how does it differ from an API error?

It is a successful HTTP 200 response where Fable 5's safety classifier declined the request — not an HTTP error . Standard error handlers that only check status codes or call raise_for_status() will pass it through silently and hand your application empty content. Branch explicitly on stop_reason rather than on content or stop_details, since stop_details can be null. Documented refusal categories are cyber, bio, frontier_llm, and reasoning_extraction, and Anthropic reports safeguards trigger in fewer than 5% of sessions .

Does the suspension affect Opus 4.8, Sonnet, or Haiku?

No. The directive covered only Fable 5 and Mythos 5. All other Anthropic models — Opus 4.8, Sonnet, and Haiku — remained online and unaffected throughout the outage . This is why claude-opus-4-8 is the recommended fallback target: it is the nearest top-tier model still serving traffic, and your fallback path keeps working even while Fable 5 is blocked.

What is the difference between Fable 5 and Mythos 5?

They share the same underlying weights, a 1M-token context window, up to 128k output tokens, and identical pricing of $10 per million input tokens and $50 per million output tokens . The single difference is safety gating: Fable 5 (claude-fable-5) ships with safety classifiers, so stop_reason: "refusal" applies to it. Mythos 5 (claude-mythos-5) ships without those classifiers and is limited-availability through Project Glasswing — access is brokered via an Anthropic, AWS, or Google Cloud account team, not self-serve .