Skip to content

Evaluation and modelsMethodology

Claude Fable 5.2 vs 5.1: what to re-test before you switch

Anthropic released Claude Fable 5.2 and Mythos 5.2 on Nov 9 at a lower per-token rate than 5.1. A lower rate is not a lower bill until output length, cache behavior and success rate hold on your own traffic. This is a re-test plan for teams on Fable 5.1 or Opus.

By INFRO Editorial

Published

9 min read

A single amber path on a dark ground forking into two glass branches of slightly different brightness

In short

Fable 5.2 lists at $8 input and $40 output per million tokens, against $10 and $50 for Fable 5.1, and fast mode is $16 and $80.1 Before switching, re-test the changes that can fail requests, then output tokens per task, cache hit rate, fast mode's real cost, and cost per successful task, not the rate card.

Key takeaways

  • Fable 5.2 is listed at $8/$40 per million tokens and $0.20 cache reads, each 20% below Fable 5.1, but that only helps if tokens per task and success rate hold.
  • Run the 400-error checks first: the prefix check now applies to every account, forced tool use fails, and the earlier computer use tool fails outside Bedrock.
  • Measure output tokens per task at the effort level you actually send; the API default is high, while Anthropic's efficiency claim is stated at medium.
  • Fast mode costs twice the standard rate, speeds output tokens per second rather than time to first token, and falling back to standard misses the prompt cache.
  • Decide on cost per successful task over a fixed task set, with Fable 5.1 and Opus 5.5 as baselines.

What changed, and what Anthropic has not told you

Anthropic released Claude Fable 5.2 and Claude Mythos 5.2 on November 9, 2026. It describes them as the same underlying model, with Fable open to all users and Mythos limited to verified organizations.1 The headline claims are an output speed up to 30% faster than Fable 5.1, a lower price, and an optional fast mode.1

Those are vendor claims on vendor benchmarks. They tell you where to look. They do not tell you what happens on your prompts, your tools and your success criteria. The rest of this article is the order in which to check.

ItemFable 5.1Fable 5.2
Input$10$8
Output$50$40
5-minute cache write$12.50$10
1-hour cache write$20$16
Cache read$0.25$0.20
Fast mode input / outputnot listed$16 / $80
Published differences between Fable 5.1 and Fable 5.2, USD per million tokens, from Anthropic's pricing and model pages.

The standard rows come from the pricing page2 and the fast mode row from the announcement.1 Context (1M tokens), maximum output (128K) and always-on adaptive thinking are unchanged, and Fable 5.2 is not retired sooner than November 9, 2027.3 These are list rates. If your contract carries different rates, test against those.

Step 1: run the checks that fail requests

Cost comparisons are meaningless if requests return 400. Anthropic's migration guide calls the move from 5.1 mostly drop-in, then lists four changes that can break code.4 Test each before you shift any traffic.

  • Prefix check on every account. Editing the system prompt, the tools or an earlier message after a thinking block was produced now returns a 400 on every account. On Fable 5.1 the same error applies by default only to accounts created on or after August 31, 2026, so older accounts can pass on 5.1 and fail on 5.2.5 Retrying the same body does not clear it.4
  • Thinking blocks are model-bound. Fable 5.2 reads Fable 5.1's blocks, but Fable 5.1 cannot read 5.2's. A router switch, client retry or refusal fallback away from 5.2 drops the blocks the next model cannot read. The request succeeds and dropped blocks are not billed, but the model works without that reasoning, which can raise cost and latency on the first turn after the switch.4
  • Computer use. The earlier computer_20251124 tool returns a 400 on every platform except Amazon Bedrock; use the computer_toolset_20260801 toolset.5
  • Advisor pairing. A Fable 5.2 executor accepts only Fable 5.2 or Mythos 5.2 as advisor.5

Three constraints carry over from 5.1 and matter if you arrive from Opus: forced tool use (tool_choice of any or tool) returns a 400, sampling parameters such as temperature must be omitted, and the model requires 30-day data retention and is unavailable under zero data retention unless Anthropic authorizes it.3 Neither model is supported on Priority Tier, and Fable 5.2 has its own rate limit, separate from the pool that Fable 5.1 and Fable 5 share.4

Step 2: measure output length at the effort you send

The announcement says Fable 5.2 can finish challenging tasks with fewer tokens than 5.1 at Medium effort, and that at High effort on FrontierCode 2.0 it scored about level with Opus 5.5 at Max effort (45.3% against 45.5%) for roughly half the cost per task.1 Read the qualifier: Medium is the default in Claude apps and Claude Code. The API default for Fable 5.2 is high, and Anthropic advises starting there and stepping up to xhigh only where you have measured a gain.5

So an efficiency claim made at medium may not describe your API traffic. Replay the same fixed task set against each candidate at each effort level you would actually ship, and record, per task:

  1. usage.output_tokens, split by task type and by whether the task succeeded.
  2. Stop reason, to count answers cut off by max_tokens.
  3. Number of tool-use turns for agent tasks, since a model that finishes in fewer turns changes input cost more than output cost.
  4. Wall-clock time and time to first token.

Anthropic also says testers found Fable 5.2 communicates more clearly.1 That may change visible answer length in either direction. Anthropic's own guidance for shorter responses is to adjust the prompt toward the length you want,6 so check whether a prompt tuned for 5.1's verbosity still gives the length your UI, parser or downstream token budget expects.

Step 3: check tokens, but do not assume a tokenizer shift

Anthropic's pricing page says Claude 4.7 and later models use a newer tokenizer that produces approximately 30% more tokens for the same text, with Sonnet 4.6 and earlier on the previous one.2 Fable 5.2 uses the tokenizer introduced with Opus 4.7.5 By that wording, Fable 5.1, Opus 5.5 and Fable 5.2 all sit in the "4.7 and later" group, so a tokenizer-driven jump between them is not what the docs describe. The pages I read give no model-by-model token counts, so verify rather than assume.

The check is cheap: count tokens for a sample of your real prompts, including system prompt, tool definitions and a long conversation, on both model ids, and compare against the usage.input_tokens you are billed. If you are coming from a model that predates 4.7, the roughly 30% effect applies and the rate cut will not offset it by itself; switching models changes the tokenizer covers that method.

Step 4: re-price the cache, then test it cold

Cache reads fall from $0.25 to $0.20 per million tokens and writes fall 20% with the input rate.2 Reads are 2.5% of the input price on both models, so the ratio of read to write cost is unchanged. Per the pricing page, a 5-minute write pays back after one read and a 1-hour write after two.2 Your break-even is therefore the same; only the dollar amounts move.

What to test is behavior, not the rate:

  • Cold start. Anthropic's caching docs describe the cache as keyed on the prefix of tools, system and messages, in that order.7 Plan for the first requests on a new model id to write the cache from scratch, and watch the write-token share for the first hour of a canary.
  • Lifetime. The default lifetime is five minutes, measured from the start of the request that writes or reads the entry, not the end of its response. A four-minute response leaves about a minute for the next request to reuse the prefix.7 Long-thinking agent turns on 5.2 can push you past this; measure hit rate by turn.
  • Prefix edits. Mid-conversation tool changes edit tools, which sits at the front of the prefix. Anything that mutates tools or the system prompt between turns costs you both a cache miss and, on 5.2, the prefix check described above.5
  • Mixed speeds. Requests at different speeds do not share cached prefixes.8

Step 5: price fast mode on the whole request, not the headline

Fast mode runs the same model with a faster inference configuration at premium pricing. Anthropic lists $16 per million input and $80 per million output tokens for Fable 5.2,1 twice the standard rate. You opt in per request with speed: "fast", and the gain is up to 2.5x output tokens per second, not time to first token.8 If your latency problem is a slow first token, fast mode does not address it.

Check these before turning it on:

  • Fast mode has its own rate limit, separate from standard limits. Exceeding it returns a 429 with retry-after, and a capacity problem can return a 529; the SDK retries 429s twice by default.8
  • Falling back to standard speed is a prompt cache miss, because speeds do not share prefixes.8 A fallback that fires under load re-writes your whole prefix at the standard write rate.
  • usage.speed reports fast or standard. Log it per request, or you cannot tell which requests paid the premium.8
  • On Microsoft Foundry fast mode is a separate model id, claude-fable-5-2-fast, and a deployment without -fast rejects a speed parameter.8

Decide per step, not per product. Fast mode earns its premium where a person or a blocking pipeline waits on a long streamed output; it does not where a batch job runs overnight. Ultrafast mode in an agent loop walks through that split for another provider's tier.

Step 6: decide on cost per successful task

Per-token rates, output length, cache hit rate and success rate multiply together. Only one number combines them: total provider cost for the task set divided by the number of tasks that passed your grader. Anthropic's efficiency figures are cost per task on its benchmarks; yours must come from your grader.1 Cost per successful task covers the metric, and calibrating an LLM judge covers trusting the pass/fail.

cost_per_success.py
# Rates in USD per million tokens, from Anthropic's list prices.
# Fast mode: cache rates not entered on purpose; fill them in before use.
RATES = {
    "claude-fable-5-1": {"in": 10, "out": 50, "write": 12.5, "read": 0.25},
    "claude-fable-5-2": {"in": 8,  "out": 40, "write": 10,   "read": 0.20},
    "claude-fable-5-2:fast": {"in": 16, "out": 80},
}

def request_cost(model_key, usage):
    r = RATES[model_key]
    cost = usage.input_tokens * r["in"] + usage.output_tokens * r["out"]
    cache_w = getattr(usage, "cache_creation_input_tokens", 0) or 0
    cache_r = getattr(usage, "cache_read_input_tokens", 0) or 0
    if cache_w or cache_r:
        cost += cache_w * r["write"] + cache_r * r["read"]  # KeyError if unpriced
    return cost / 1_000_000   # assumes 5-minute cache writes

def cost_per_success(rows):
    # rows: [(cost_usd, passed_bool), ...] for the whole task set, retries included
    total = sum(c for c, _ in rows)
    passed = sum(1 for _, ok in rows if ok)
    return total / passed if passed else float("inf")

Run three arms, not two: Fable 5.1 (your current baseline), Fable 5.2 at the effort you plan to ship, and Opus 5.5 at its own tuned effort. Anthropic still recommends starting with Opus 5.5 for most workloads and moving to Fable when your evaluations on Opus at higher effort fall short.6 Fable 5.2 lists at twice Opus 5.5's per-token rate,2 so the half-the-cost-per-task claim is exactly the one to confirm or reject on your data.

Roll it out as a canary with a rollback you can price

Once the task set favors 5.2, ship it as a weighted split rather than a cutover, and decide the rollback trigger in advance: cost per success, cut-off rate or first-token latency past a threshold. Keep the rollback path honest. Moving a live conversation back to 5.1 loses 5.2's reasoning, so route by conversation and not by request.4

If you route through INFRO, weighted routes over your own Anthropic connection can carry the split, and per-request records of model, token counts and estimated provider cost give you the output-length and cost columns above. Traffic changes flags longer answers, a lost prompt cache and answers cut off by the length limit, with an estimated weekly cost change; it sees request metadata, not answers, so quality still comes from your grader. Negotiated rates entered as custom rates make the estimates use your contract, not the list rates quoted here.

Questions readers ask

Is Mythos 5.2 a different model from Fable 5.2?
Anthropic describes Fable and Mythos as the same underlying model. Fable carries strong cybersecurity and biology safeguards and is open to all users; Mythos is for organizations verified through Anthropic's Cyber or Life Sciences verification programs.1 They share specifications and pricing.3
Can a conversation move from Fable 5.2 back to Fable 5.1 as a fallback?
The request succeeds, but Fable 5.1 cannot read Fable 5.2's thinking blocks, so the API drops them and the model works without that reasoning. Anthropic notes this can raise cost and latency on the first turn after the switch.4

From the team that builds it

Where this shows up in INFRO

INFRO is a control plane in front of the provider accounts you already hold. The capabilities below are the parts of it this article touches, each with the documentation that defines its behaviour.

  • Usage and cost per request

    Available with a plan

    Every request records its model, latency, token or unit counts, and estimated provider cost, queryable by project and key.

    Read the documentation for Usage and cost per request
  • Traffic changes

    Available with a plan

    Changes in your traffic that come with no error: a model answered by a new snapshot, longer answers, a lost prompt cache, more fallbacks, answers cut off by the length limit, slower responses or a new error mix. Each finding names the likely cause and the estimated weekly change in provider cost. INFRO sees request metadata, not answers, so it does not judge answer quality.

    Read the documentation for Traffic changes
  • Health-aware routing

    Available with a plan

    Named routes use priority or weighted targets over your own connections, with health checks, retries and failover.

    Read the documentation for Health-aware routing
  • Negotiated provider rates

    Available with a plan

    Enter the rates your contracts actually carry, per model and optionally per provider, so estimated cost uses them before the vendor's list rate. Included on every plan.

    Read the documentation for Negotiated provider rates

INFRO accounts are self-serve. Provider usage is billed to you by your providers; INFRO charges a software subscription and takes 0% of model spend. See plans.

Sources

Numbered in order of first citation. Each was opened and checked against the claim on the date shown.

  1. 1.Introducing Claude Fable 5.2 and Claude Mythos 5.2 (opens in a new tab) — Anthropic. Accessed Nov 10, 2026.
  2. 2.Pricing - Claude Platform Docs (opens in a new tab) — Anthropic. Accessed Nov 10, 2026.
  3. 3.Claude Fable 5.2 - Claude Platform Docs (opens in a new tab) — Anthropic. Accessed Nov 10, 2026.
  4. 4.Claude Fable 5.2 and Claude Mythos 5.2 migration guide (opens in a new tab) — Anthropic. Accessed Nov 10, 2026.
  5. 5.What's new in Claude Fable 5.2 (opens in a new tab) — Anthropic. Accessed Nov 10, 2026.
  6. 6.Models overview - Claude Platform Docs (opens in a new tab) — Anthropic. Accessed Nov 10, 2026.
  7. 7.Prompt caching - Claude Platform Docs (opens in a new tab) — Anthropic. Accessed Nov 10, 2026.
  8. 8.Fast mode - Claude Platform Docs (opens in a new tab) — Anthropic. Accessed Nov 10, 2026.

About this article

Read on 2026-11-10: Anthropic's Fable 5.2 and Mythos 5.2 announcement, the pricing, models overview, Fable 5.2 overview, what's-new, migration guide, fast mode and prompt caching pages in the Claude Platform docs. Anthropic's benchmark figures are cited as vendor claims; no independent measurements were available, so all cost examples use illustrative figures.

Last checked against its sources on . The next review is due by . No separate named reviewer is recorded for this article.

How articles are written, sourced and corrected is set out in the editorial standards.