Get started

Muse Wonder

Timed at 108 tok/s, scored 43.6 on the Intelligence Index, and on 13 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Meta/Muse WonderUSD per 1M tokens · as OpenRouter routes it
meta/muse-wonderMeta · base listing · Other tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$4.00per 1M tokens
Output$20.00per 1M tokens
Cached input$0.20per 1M tokens
Context1.05M1,048,576 tokens
The other meters · every further rate the list publishes for this id, in the unit it states1 meter
Web search$0.01per search
What the list says · the fields OpenRouter publishes for this id9 fields
AuthorMeta
Listed
Canonical idmeta/muse-wonder-20261012
Context1,048,576 tokens
Max output943,718 tokens
Modalitiestext, image, video, file, audio → text
TokenizerOther
Reasoningalways on · effort max, xhigh, high, medium, low, minimal, medium by default
Moderationnot moderated by OpenRouter

Measured speed

2,859 requests · 2 endpoints · 30-minute window
Throughput108 tok/sMedian output rate, weighted across the 2 endpoints serving it by the requests each answered.the speed board
First token3.06sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread81 to 119The 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

2 priced · 2 timed · cheapest first
  1. Googlegoogle-vertex/global · listed$4.00$20.00$0.20not declared944k119 tok/s593.04s1,992 req100%
  2. Metameta · listed$4.00$20.00$0.20not declared944k81 tok/s353.09s867 req99.42%

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: 1 of the 2 timed routes are slower than it, and the middle route runs at 100 tok/s. The widest median-to-p90 gap is Meta's, 2.31x.

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 2 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Google at 73.47% on 11 Nov 2026 and Meta at 97.49% on 11 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

13 parameters · 2 sellers
  1. include_reasoningevery seller
  2. max_tokensevery seller
  3. reasoningevery seller
  4. reasoning_effortevery seller
  5. response_formatevery seller
  6. structured_outputsevery seller
  7. temperatureevery seller
  8. tool_choiceevery seller
  9. toolsevery seller
  10. top_pevery seller
  11. repetition_penalty1 of 2not Google
  12. seed1 of 2not Meta
  13. top_k1 of 2not Google

10 of these 13 are accepted by every one of the 2 sellers that publish a list; the other 3 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 $8.00 per million tokens, 3 in to 1 out: cheaper than 23 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 Index43.6Position 14 of 58, above 76% 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. blender3d · Agents1124 Elowin rate 35.9% · source rank 10the board, 25 ranked
  2. codetovideo · Agents1218 Elowin rate 55.6% · source rank 10the board, 26 ranked
  3. HTML slides · Agents1126 Elowin rate 14.1% · source rank 7the board, 25 ranked
  4. Mobile apps · Agents1258 Elowin rate 55.1% · source rank 7the board, 49 ranked
  5. pdf · Agents1234 Elowin rate 57.3% · source rank 12the board, 36 ranked
  6. python-pptx slides · Agents1033 Elowin rate 14.7% · source rank 30the board, 29 ranked
  7. spreadsheet · Agents1232 Elowin rate 43.4% · source rank 12the board, 32 ranked
  8. 3D scenes · Models1432 Elowin rate 60.8% · source rank 4the board, 113 ranked
  9. Code · Models1391 Elowin rate 62.5% · source rank 1the board, 120 ranked
  10. Data visualisation · Models1285 Elowin rate 53.9% · source rank 15the board, 110 ranked
  11. Game development · Models1414 Elowin rate 62.0% · source rank 2the board, 120 ranked
  12. UI components · Models1363 Elowin rate 61.2% · source rank 5the board, 116 ranked
  13. Websites · Models1378 Elowin rate 63.8% · source rank 1the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index161.7159.4 to 164.3
Position17 of 258above 94% of the models placed
Results behind it13benchmark results
As Epoch names itMuse Wonderreleased 12 Oct 2026

Position 17 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 Muse Wonder 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.