Metaが新モデル「Muse Spark」を発表、meta.aiチャットに注目ツールを追加

Meta announced Muse Spark today, their first model release since Llama 4 almost exactly a year ago. It's hosted, not open weights, and the API is currently "a private API preview to select users", but you can try it out today on meta.ai (Facebook or Instagram login required).

Meta's self-reported benchmarks show it competitive with Opus 4.6, Gemini 3.1 Pro, and GPT 5.4 on selected benchmarks, though notably behind on Terminal-Bench 2.0. Meta themselves say they "continue to invest in areas with current performance gaps, such as long-horizon agentic systems and coding workflows".

The model is exposed as two different modes on meta.ai - "Instant" and "Thinking". Meta promise a "Contemplating" mode in the future which they say will offer much longer reasoning time and should behave more like Gemini Deep Think or GPT-5.4 Pro.

A couple of pelicans

I prefer to run my pelican test via API to avoid being influenced by any invisible system prompts, but since that's not an option I ran it against the chat UI directly.

Here's the pelican I got for "Instant":

And this one for "Thinking":

Both SVGs were rendered inline by the Meta AI interface. Interestingly, the Instant model output an SVG directly (with code comments) whereas the Thinking model wrapped it in a thin HTML shell with some unused Playables SDK v1.0.0 JavaScript libraries.

Which got me curious...

Poking around with tools

Clearly Meta's chat harness has some tools wired up to it - at the very least it can render SVG and HTML as embedded frames, Claude Artifacts style.

But what else can it do?

I asked it:

what tools do you have access to?

And then:

I want the exact tool names, parameter names and tool descriptions, in the original format

It spat out detailed descriptions of 16 different tools. You can see the full list I got back here - credit to Meta for not telling their bot to hide these, since it's far less frustrating if I can get them out without having to mess around with jailbreaks.

Here are highlights derived from that response:

• Browse and search. browser.search can run a web search through an undisclosed search engine, browser.open can load the full page from one of those search results and browser.find can run pattern matches against the returned page content.

• Meta content search. meta_1p.content_search can run "Semantic search across Instagram, Threads, and Facebook posts" - but only for posts the user has access to view which were created since 2025-01-01. This tool has some powerful looking parameters, including author_ids, key_celebrities, commented_by_user_ids, and liked_by_user_ids.

• "Catalog search" - meta_1p.meta_catalog_search can "Search for products in Meta's product catalog", presumably for the "Shopping" option in the Meta AI model selector.

• Image generation. media.image_gen generates images from prompts, and "returns a CDN URL and saves the image to the sandbox". It has modes "artistic" and "realistic" and can return "square", "vertical" or "landscape" images.

• container.python_execution - yes! It's Code Interpreter, my favourite feature of both ChatGPT and Claude.

Execute Python code in a remote sandbox environment. Python 3.9 with pandas, numpy, matplotlib, plotly, scikit-learn, PyMuPDF, Pillow, OpenCV, etc. Files persist at /mnt/data/.

Python 3.9 is EOL these days but the library collection looks useful.

I prompted "use python code to confirm sqlite version and python version" and got back Python 3.9.25 and SQLite 3.34.1 (from January 2021).

• container.create_web_artifact - we saw this earlier with the HTML wrapper around the pelican: Meta AI can create HTML+JavaScript files in its container which can then be served up as secure sandboxed iframe interactives. "Set kind to html for websites/apps or svg for vector graphics."

• container.download_meta_1p_media is interesting: "Download media from Meta 1P sources into the sandbox. Use post_id for Instagram/Facebook/Threads posts, or catalog_search_citation_id for catalog product images". So it looks like you can pull in content from other parts of Meta and then do fun Code Interpreter things to it in the sandbox.

• container.file_search - "Search uploaded files in this conversation and return relevant excerpts" - I guess for digging through PDFs and similar?

• Tools for editing files in the container - container.view, container.insert (with new_str and insert_line), container.str_replace. These look similar to Claude's text editor tool commands - these are becoming a common pattern across any file-equipped agent harness.

• container.visual_grounding - see below, this one is fun.

• subagents.spawn_agent - the sub-agent as a tool pattern. "Spawn an independent sub-agent for research, analysis, or delegation. It returns its final text response."

• third_party.link_third_party_account - "Initiate account linking for a third-party service", currently Google Calendar, Outlook Calendar, Gmail, or Outlook.

Image analysis in the container

Let's talk about that container.visual_grounding one. Here's the description in full:

Description: Visual grounding tool that analyzes the image, identifies and labels objects, locates regions, or counts objects.

Parameters:

object_names (array, required)

image_path (string, default "")

format_type ("bbox"|"point"|"count"|null, default "bbox")

title (string|null)[string]

So it can take an image path, optional object names and return things in format bbox, point or count.

Sounds to me like Meta's Segment Anything. I decided to take it for a spin.

Prompt:

generate a photo of a raccoon sitting on a trash can wearing trash as a hat

Response:

Here you go — king of the alley, in full regalia:

Coffee cup crown, banana peel brim, newspaper feather. Peak raccoon fashion. Want me to make a wilder version — maybe night-vision, or wearing sunglasses too?

My guess is that image generation in Meta AI is powered by their Emu model, or an updated version of it. This is the same pattern as ChatGPT and Gemini image generation, where images are generated by a tool call (here that's to media.image_gen).

The image_gen tool description said that it "saves the image to the sandbox", so my guess was that I'd then be able to run Python code against it. I tried:

use python OpenCV to analyze that image and find out neat things about it

Annoyingly it did *not* show me the code it ran, but it did create this image:

Pretty neat! We can both generate images and then use them with Python tools.

Next, the visual_grounding tool. Knowing the names of the tools makes it easy to refer to them in prompts:

Now try the container.visual_grounding tool

The response (full response here):

Done — visual_grounding pinpointed every piece of the outfit with pixel-level precision:

[...]

Want me to run it in bbox mode next to draw boxes around the fur texture, or count mode to see how many individual whiskers it can detect?

Once again, Meta AI wrapped the results from the tool in a custom HTML visualization. That's clearly point mode, but how about the others?

I prompted:

yes draw bounding boxes, can it do masks too?

Response:

Yes — bounding boxes work great. Masks? Not directly in visual_grounding; it only returns three formats: point, bbox, and count. No pixel-level segmentation masks.

Here's the bbox output:

What you’re seeing:

raccoon: big box from (270,240) to (892,845) — covers 62% of the width, basically the whole animal

coffee cup: (424,115)-(610,273) — sits highest, 158px tall in the 0-1000 space

banana peel: (472,215)-(667,291) — overlaps the cup's base, confirming it's draped over the side

newspaper: (305,223)-(548,315) — left ear coverage

trash can lid: (107,800)-(1000,998) — spans almost the full image width at the bottom

face: (305,283)-(750,537) — tight crop around the mask

eyes: both ~40×37 pixel boxes, perfectly level at y=379

Notice how the boxes nest: face is inside raccoon, eyes inside face, hat pieces overlap each other but stay above the face box. The tool is doing real object localization, not just guessing centers.

About masks: since visual_grounding doesn't output them, I can fake them with OpenCV in the container. Two quick options:

GrabCut — I give it the raccoon bbox, it iteratively segments fur from background and returns a binary mask

SAM-style color threshold — use the bbox plus k-means to isolate the coffee cup or banana peel

Want me to generate an actual alpha mask for the raccoon (cut it out from the alley), or for the trash hat pieces separately? Takes about 10 seconds and I can give you a transparent PNG.

Here's the HTML for that bbox visualization.

Finally I had it dump out the raw JSON for point mode, bbox mode and count mode. You can see that all here. The count mode is particularly interesting - here's that in full:

[

{

"object_name": "raccoon whisker",

"points": [

{"x": 403, "y": 445},

{"x": 397, "y": 458},

{"x": 392, "y": 472},

{"x": 391, "y": 485},

{"x": 398, "y": 497},

{"x": 415, "y": 512},

{"x": 618, "y": 446},

{"x": 622, "y": 461},

{"x": 625, "y": 475},

{"x": 628, "y": 488},

{"x": 635, "y": 501},

{"x": 651, "y": 518}

],

"count": 12

},

{

"object_name": "raccoon paw claw",

"points": [

{"x": 406, "y": 845},

{"x": 424, "y": 847},

{"x": 441, "y": 842},

{"x": 473, "y": 833},

{"x": 596, "y": 830},

{"x": 635, "y": 844},

{"x": 660, "y": 843},

{"x": 679, "y": 838}

],

"count": 8

},

{

"object_name": "trash item on head",

"points": [

{"x": 514, "y": 191},

{"x": 568, "y": 263},

{"x": 392, "y": 274}

],

"count": 3

},

{

"object_name": "eye",

"points": [

{"x": 462, "y": 395},

{"x": 582, "y": <span class="pl