How is Fable 5.2 different from Fable 5.1?

Official input and output prices are 20% lower than on Fable 5.1, and comparative latency moves from Slower to Moderate. On the API, the thinking-block prefix check now applies to every account regardless of creation date; only Fable 5.2 and Mythos 5.2 read Fable 5.2 thinking blocks; computer_20251124 is rejected outside Bedrock in favor of computer_toolset_20260801; and a Fable 5.2 executor requires a Fable 5.2 or Mythos 5.2 advisor.

Should I choose Fable 5.2 or Opus 5.5?

Anthropic recommends starting most workloads on Opus 5.5 and moving to Fable 5.2 for demanding reasoning, multi-hour agent sessions, or when evals on Opus 5.5 at higher effort still fall short. Both models share a 1M-token context window, 128K max output, always-on adaptive thinking, and Moderate comparative latency.

What should I check when migrating from Fable 5.1?

Keep conversation history strictly append-only so you do not trip the universal prefix check (or set thinking.block_binding.prefix_mismatch_behavior to "drop_block" as a temporary stopgap); replace computer_20251124 with computer_toolset_20260801; update any advisor tool model to claude-fable-5-2; and lower the effort parameter for easy turns rather than relying on prompt lines asking the model not to think.

Claude Fable 5.2

Save 65%Official

anthropic/claude-fable-5-2

Anthropic's latest Fable — November 2026 successor to Fable 5.1, Mythos-class, cache reads at 2.5%.

Get an API key View code sample

Live model playground

Try Claude Fable 5.2 here

Tune the request, see the current price ceiling, and inspect the real response without leaving this model page.

streamchat

1Configure input

Prompt

0 / 20,000

Add images

Maximum estimated cost—

2Live result

Your result will appear here

Enter an input on the left. The same RouteMux Playground execution and billing path powers this embedded test.

Context window: 1M
Max output: 128K
Input modalities: TextImage
Output modalities: Text
Capabilities: Vision · Reasoning · Tool calling · Coding · Prompt cache · Paid cache writes
Upstream release: 2026-11-09
RouteMux name: anthropic/claude-fable-5-2

What is Claude Fable 5.2

Claude Fable 5.2 was released by Anthropic on November 9, 2026, succeeding Claude Fable 5.1 alongside Claude Mythos 5.2, which offers the same specifications and pricing only to verified organizations (such as the Cyber Verification Program). Anthropic builds Fable 5.2 for demanding reasoning and long-horizon agentic work—agent sessions that run for hours, multistep deep research, and analysis carried through to a finished document, spreadsheet, or deck. Its comparative latency improves from Slower on Fable 5.1 to Moderate, and retirement is not sooner than November 9, 2027. For most workloads, Anthropic recommends starting on Claude Opus 5.5 and moving to Fable 5.2 when evals on Opus at higher effort still fall short.

Fable 5.2 keeps a 1M-token context window (default and maximum), a 128K-token output limit, text and image input, a June 2026 knowledge cutoff, and the Opus 4.7 tokenizer. Adaptive thinking is always on and cannot be disabled, controlled through five effort levels: low, medium, high (default), xhigh, and max. Anthropic lowered official base input and output prices by 20% compared with Fable 5.1 ($8 / $40 vs. $10 / $50 per 1M tokens), while cache reads remain at 2.5% (0.025x) of the base input rate.

Four API changes from Fable 5.1 can break existing integrations: the preserved-thinking prefix check now applies to every account (editing system, tools, or earlier messages before a thinking block returns a 400 unless prefix_mismatch_behavior is set to "drop_block"); only Fable 5.2 and Mythos 5.2 can read Fable 5.2 thinking blocks; the legacy computer_20251124 tool returns a 400 outside Amazon Bedrock (use computer_toolset_20260801 instead); and with the advisor tool, a Fable 5.2 executor requires a Fable 5.2 or Mythos 5.2 advisor. Forced tool use (tool_choice "any" or "tool") and non-default sampling parameters (temperature, top_p, top_k) continue to return a 400 error.

Through RouteMux, Fable 5.2 costs $2.8 per 1M input tokens against Anthropic's $8, $14 per 1M output tokens against $40, and $0.07 per 1M cache-read tokens against $0.2.

Before you choose

How is Fable 5.2 different from Fable 5.1?: Official input and output prices are 20% lower than on Fable 5.1, and comparative latency moves from Slower to Moderate. On the API, the thinking-block prefix check now applies to every account regardless of creation date; only Fable 5.2 and Mythos 5.2 read Fable 5.2 thinking blocks; computer_20251124 is rejected outside Bedrock in favor of computer_toolset_20260801; and a Fable 5.2 executor requires a Fable 5.2 or Mythos 5.2 advisor.
Should I choose Fable 5.2 or Opus 5.5?: Anthropic recommends starting most workloads on Opus 5.5 and moving to Fable 5.2 for demanding reasoning, multi-hour agent sessions, or when evals on Opus 5.5 at higher effort still fall short. Both models share a 1M-token context window, 128K max output, always-on adaptive thinking, and Moderate comparative latency.
What should I check when migrating from Fable 5.1?: Keep conversation history strictly append-only so you do not trip the universal prefix check (or set thinking.block_binding.prefix_mismatch_behavior to "drop_block" as a temporary stopgap); replace computer_20251124 with computer_toolset_20260801; update any advisor tool model to claude-fable-5-2; and lower the effort parameter for easy turns rather than relying on prompt lines asking the model not to think.

Claude Fable 5.2 API pricing

Prices verified 2026-11-11

InputOfficial $8 / M tokens

$2.8/ M tokensSave 65%

OutputOfficial $40 / M tokens

$14/ M tokensSave 65%

Cache read $0.07/M · Cache write $3.5/M

Estimate cost

Input tokensOutput tokens

Estimated cost$0.042

Key capabilities

20% lower official price, cache reads at 0.025x: Anthropic cut base input and output pricing by 20% compared with Fable 5.1 while keeping cache hits and refreshes at 0.025 times (2.5%) the base input rate. Long-horizon agents that repeatedly read large codebases or documents benefit from both reductions.
Always-on adaptive thinking with five effort levels: Adaptive thinking is always on; budget_tokens and thinking disabled both return a 400. Choose from low, medium, high (default), xhigh, and max—start at high and step up to xhigh for your hardest long-running coding and agentic tasks.
Universal prefix check and append-only history tools: Editing system, tools, or messages before an earlier thinking block returns a 400 on every account. Use compaction on demand (compact-2026-09-04 beta) and mid-conversation tool changes (inline-tools-2026-09-15 beta) to keep conversations append-only.
Moderate comparative latency: Anthropic's models overview rates Fable 5.2's comparative latency as Moderate—up from Slower on Fable 5.1 and matching Opus 5.5—while retaining the full 1M-token context window and 128K output ceiling.

Limited time10% extra Credits on your first top-up — up to 200 bonus Credits

Applies to your first top-up within 72 hours of signing up. Minimum $20, once per account.

Interface and protocols

Anthropic MessagesStreaming

Use any of these IDs to call this model via the API.

RouteMux nameanthropic/claude-fable-5-2

Replace the ROUTEMUX_KEY placeholder with your API key. Create one →

from anthropic import Anthropic

client = Anthropic(
    base_url="https://api.routemux.com/anthropic",
    api_key="<ROUTEMUX_KEY>",
)

message = client.messages.create(
    model="anthropic/claude-fable-5-2",
    max_tokens=1024,
    messages=[{"role": "user", "content": "What is the meaning of life?"}],
)
print(message.content[0].text)

base_url: https://api.routemux.com/anthropic

Performance (last 30 days)

56 requests · last 30 days

Total usage3.32M

P50 first-token latency11.91s

Avg throughput31 tok/s

Success rate100.0%

Uptime · 24htested via anthropic_messages

100.00%

Success rate · 60d · from real requests

Claude Fable 5.2 FAQ

›What is Claude Fable 5.2?

Anthropic's latest Fable — November 2026 successor to Fable 5.1, Mythos-class, cache reads at 2.5%.

›How large is the context window of Claude Fable 5.2?

Claude Fable 5.2 supports a context window of up to 1M tokens, with up to 128K output tokens per request.

›How much does the Claude Fable 5.2 API cost?

Through RouteMux, Claude Fable 5.2 costs $2.8 for input and $14 for output (USD per 1M tokens), below the official list price.

›How do I call Claude Fable 5.2 via API?

Claude Fable 5.2 is OpenAI-compatible: point your base URL at RouteMux and set the model field to anthropic/claude-fable-5-2 — no code changes needed.

›Which input and output modalities does Claude Fable 5.2 support?

Claude Fable 5.2 accepts text, image as input and produces text as output.

›When was Claude Fable 5.2 released?

Claude Fable 5.2 was released on November 9, 2026.

Sources

Reviewed by the RouteMux team on 2026-11-11

View as Markdown