Get started

Claude Fable 5.2

Sold by 4 sellers, timed at 84.9 tok/s, scored 64.6 on the Intelligence Index, and on 10 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Anthropic/Claude Fable 5.2USD per 1M tokens · as OpenRouter routes it
anthropic/claude-fable-5.2Anthropic · base listing · Claude tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$8.00per 1M tokens
Output$40.00per 1M tokens
Cached input$0.20per 1M tokens
Context1M1,000,000 tokens
The other meters · every further rate the list publishes for this id, in the unit it states3 meters
Cache write$10.00per 1M tokens
Cache write, 1 hour$16.00per 1M tokens
Web search$0.01per search
What the list says · the fields OpenRouter publishes for this id10 fields
AuthorAnthropic
Listed
Canonical idanthropic/claude-fable-5.2-20261109
Context1,000,000 tokens
Max output128,000 tokens
Modalitiestext, image, file → text
TokenizerClaude
Reasoningalways on · effort max, xhigh, high, medium, low, high by default
Moderationmoderated by OpenRouter
Other listingbatch variant

What sellers charge

4 sellers · 2x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $8.00 at Anthropic to $16.00 at Anthropic. The $8.00 listed is the cheapest on offer; 1 seller is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

12,305 requests · 5 endpoints · 30-minute window
Throughput84.9 tok/sMedian output rate, weighted across the 5 endpoints serving it by the requests each answered.the speed board
First token4.71sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread70 to 220The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

4 priced · 5 timed · cheapest first
  1. Anthropicanthropic · listed$8.00$40.00$0.20not declared128knot matchednonenonenot matched100%
  2. Azureazure · listed$8.00$40.00$0.20not declared128k85 tok/s525.27s4,010 req100%
  3. Googlegoogle-vertex/global · listed$8.00$40.00$0.20not declared128k81 tok/s444.22s1,820 req100%
  4. Anthropicanthropic/fast$16.00$80.00$0.40not declared128knot matchednonenonenot matched100%
  5. Amazon Bedrockno priceno priceno priceno offerno offer70 tok/s474.51s16 reqno offer
  6. Anthropicnot matchednot matchednot matchednot matchedno offer85 tok/s484.52s6,408 reqno offer
  7. Anthropicnot matchednot matchednot matchednot matchedno offer220 tok/s1251.9s51 reqno offer

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 2 of the 5 timed routes are slower than it, and the middle route runs at 85 tok/s. The widest median-to-p90 gap is Google's, 1.84x.

Anthropic publishes 2 offers and had 2 routes timed. The two documents share no route id, so those offers and routes are printed apart rather than paired.

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 2 of the 4 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Anthropic (anthropic) at 97.43% on 13 Nov 2026 and Azure at 97.81% on 13 Nov 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

11 parameters · 4 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. reasoning_effortevery seller
  5. response_formatevery seller
  6. stopevery seller
  7. structured_outputsevery seller
  8. tool_choiceevery seller
  9. toolsevery seller
  10. verbosityevery seller
  11. max_completion_tokens1 of 4not Anthropic (anthropic), Anthropic (anthropic/fast), and Google

10 of these 11 are accepted by every one of the 4 sellers that publish a list; the other 1 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $16.00 per million tokens, 3 in to 1 out: cheaper than 11 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board

Each mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.

Intelligence Index64.6Position 1 of 58, above 98% of the models scored.the intelligence leaderboard
Coding Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard
  1. codetovideo · Agents1445 Elowin rate 81.3% · source rank 1the board, 26 ranked
  2. Full stack · Agents1397 Elowin rate 72.6% · source rank 1the board, 44 ranked
  3. Mobile apps · Agents1318 Elowin rate 65.6% · source rank 2the board, 49 ranked
  4. pdf · Agents1351 Elowin rate 72.5% · source rank 1the board, 36 ranked
  5. spreadsheet · Agents1429 Elowin rate 74.9% · source rank 1the board, 32 ranked
  6. 3D scenes · Models1498 Elowin rate 73.2% · source rank 1the board, 113 ranked
  7. Code · Models1374 Elowin rate 62.5% · source rank 3the board, 120 ranked
  8. Game development · Models1401 Elowin rate 64.7% · source rank 5the board, 120 ranked
  9. UI components · Models1378 Elowin rate 63.2% · source rank 3the board, 116 ranked
  10. Websites · Models1350 Elowin rate 60.4% · source rank 3the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index173.4170.0 to 177.2
Position1 of 258above 100% of the models placed
Results behind it21benchmark results
As Epoch names itClaude Fable 5.2released 9 Nov 2026

Position 1 of the 258 models Epoch has placed, which is not the population of either board above, on a scale anchored at Claude 3.5 Sonnet 130 and GPT-5 150. Epoch states that absolute values are meaningless by themselves and that comparisons between models are what the index is for, that values are not linearly related to benchmark accuracy, and that a highly specialised model may score low while being capable in its own domain.

Benchmark results

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Claude Fable 5.2 under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: the Epoch AI Capabilities Index (epoch.ai/eci), as of 20 Nov 2026. 258 models placed over 2917 benchmark results.
Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
Vitna ran none of these evaluations and adjusted none of these figures.