Get started

Claude Fable 5.1 (batch)

Timed at 65.4 tok/s, scored 50.0 on the Intelligence Index, and on 15 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Anthropic/Claude Fable 5.1 (batch)USD per 1M tokens · as OpenRouter routes it
anthropic/claude-fable-5.1:batchAnthropic · batch variant · Claude tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$5.00per 1M tokens
Output$25.00per 1M tokens
Cached input$0.125per 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$6.25per 1M tokens
Cache write, 1 hour$10.00per 1M tokens
Web search$0.01per search
What the list says · the fields OpenRouter publishes for this id11 fields
AuthorAnthropic
Listed
Canonical idanthropic/claude-fable-5.1-20260831
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
Variantbatch
Other listingbase listing

Measured speed

1,399 requests · 4 endpoints · 30-minute window
Throughput65.4 tok/sMedian output rate, weighted across the 4 endpoints serving it by the requests each answered.the speed board
First token3.95sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread50 to 68.5The 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

3 priced · 4 timed · cheapest first
  1. Anthropicanthropic$10.00$50.00$0.25not declared128k64.5 tok/s434.24s419 req99.74%
  2. Azureazure$10.00$50.00$0.25not declared128k64 tok/s434.22s477 req99.86%
  3. Googlegoogle-vertex/global$10.00$50.00$0.25not declared128k68.5 tok/s513.46s478 req100%
  4. Amazon Bedrockno priceno priceno priceno offerno offer50 tok/s343.29s25 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: 3 of the 4 timed routes are slower than it, and the middle route runs at 64.3 tok/s. The widest median-to-p90 gap is Anthropic's, 1.5x.

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: Azure at 83.33% on 2 Nov 2026 and Anthropic at 97.27% 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 · 3 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 3not Anthropic and Google

10 of these 11 are accepted by every one of the 3 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 $10.00 per million tokens, 3 in to 1 out: cheaper than 16 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 Index50.0Position 10 of 58, above 83% of the models scored.the intelligence leaderboard
Coding Index80.7Position 1 of 118, above 99% of the models scored.the coding leaderboard
Agentic Index57.2Position 1 of 94, above 99% of the models scored.the agentic leaderboard
  1. Full stack · Agents1300 Elowin rate 57.1% · source rank 4the board, 44 ranked
  2. Godot game development · Agents1296 Elowin rate 60.7% · source rank 1the board, 34 ranked
  3. HTML slides · Agents1391 Elowin rate 56.5% · source rank 1the board, 25 ranked
  4. Mobile apps · Agents1253 Elowin rate 56.3% · source rank 9the board, 49 ranked
  5. python-pptx slides · Agents1319 Elowin rate 62.1% · source rank 1the board, 29 ranked
  6. spreadsheet · Agents1344 Elowin rate 58.8% · source rank 3the board, 32 ranked
  7. Web apps · Agents1319 Elowin rate 58.2% · source rank 1the board, 47 ranked
  8. 3D scenes · Models1388 Elowin rate 63.1% · source rank 9the board, 113 ranked
  9. ASCII art · Models1307 Elowin rate 65.0% · source rank 7the board, 67 ranked
  10. Code · Models1329 Elowin rate 57.5% · source rank 11the board, 120 ranked
  11. Data visualisation · Models1344 Elowin rate 62.4% · source rank 5the board, 110 ranked
  12. Game development · Models1364 Elowin rate 59.5% · source rank 7the board, 120 ranked
  13. SVG · Models1292 Elowin rate 56.6% · source rank 11the board, 83 ranked
  14. UI components · Models1330 Elowin rate 59.9% · source rank 13the board, 116 ranked
  15. Websites · Models1304 Elowin rate 55.2% · source rank 15the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index167.1164.4 to 170.1
Position8 of 258above 97% of the models placed
Results behind it25benchmark results
As Epoch names itClaude Fable 5.1released 1 Sep 2026

Position 8 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 5.1 (batch) 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.