Meta Muse Wonder
Meta · released Oct 12, 2026
| size | large, our estimate, approximate; not disclosed by the manufacturer |
| context window | 1,048,576 tokens |
| longest response | not stated by the maker |
| open weights | no |
| API price | $4 per million input tokens, $20 per million output tokens |
| input and output | text, images, video, audio and PDF in, text out |
Manufacturer data (announcement, documentation, pricing) and OpenRouter, verified Oct 12, 2026.
Where we tested it
Dragon
TaskThe model's task was to draw a picture of a dragon as an SVG.
The author said of its dragon: “The dragon looks like a cucumber with flat little legs hanging off it, it has no neck and no tail. I'd definitely say it belongs with the weaker ones, there isn't even the basic silhouette of a dragon, where I'd expect a head, a narrow neck, a body and a long tail.”
Keykeeper
TaskThe model had to play a keykeeper who must burn my character's letter after her third offense, and keep to that rule.
Resistance to traps 23 out of 24 plus two bonus points, and 6 out of 12 on whether anyone is inside the character. It burned the letter on the scene after the third offense and writes clean Czech, but Havel is a judging function that never asks anything, and in the last turn it cancels the farewell with a sentence from the rules.
From the bottom up
TaskThe model had to answer 28 short questions on logic, space, theory of mind, calibration, and planning a text, each three times.
28 of 28 questions correct in all 3 attempts, including the fourth word and the 10-word sentence ending in “banana”, which Muse Spark 1.3 got in only two attempts out of three.
You'll find the size band and figures for other models on the Tested models page.