AI at Meta

We’re excited to introduce Muse Spark 1.1, a significant upgrade from the first Muse Spark model we released earlier this year. Along with this release, we are launching a public preview of the new Meta Model API where developers can access Muse Spark 1.1. The model is also available now in "Thinking" mode in the Meta AI app and on meta.ai. Learn more: go.meta.me/ff8e2c

@IamEmily2050 Thanks for the feedback! We're cooking 😉

@ajayyy_k @Meta Now its time to build 😎

wait this is crazy pricing form @Meta , is this best frontier model price per intelligence right now ?

We gave a few leaders early access to Muse Spark 1.1, here's what they had to say:

muse spark 1.1 just built minecraft for me inside julius link below if you want to try

@Aryan_Ali_Pro Looks awesome! Thanks for sharing.

Muse Spart 1.1, @AIatMeta Cooked on Front-end capability of this model!

AI developers - we’ve published a technical guide covering how to get started with Muse Spark on Meta Model API. Muse Spark is a multimodal reasoning model built for agentic tasks, coding, computer use and long-context workflows. See what you can build 👉 bit.ly/4vWMkZx

@Ved_CJ We're just getting started!

@AIatMeta Lmfao i did NOT except meta to drop a SOTA model

We’re excited to introduce Muse Spark 1.1, a significant upgrade from the first Muse Spark model we released earlier this year. Along with this release, we are launching a public preview of the new Meta Model API where developers can access Muse Spark 1.1. The model is also available now in "Thinking" mode in the Meta AI app and on meta.ai. Learn more: go.meta.me/ff8e2c

@danielamitay You obviously have taste as well 🤝

Not many benchmarks measure aesthetic “taste,” but I’ve used enough different models and families to know it’s rare. Muse Spark has taste.

Meta made a “minor” release to Muse Spark, there’s nothing minor about it. Lots to parse here: - This model is so fucking cheap I almost don’t believe it. In practice we see it’s 1/10 the cost of both Fable and GPT 5.5. If you thought OS models would compete away margins, just wait till you see this. It’s somehow cheaper to use MS 1.1 than host your own OS model… - Coding improvements are significant. This was a real shortcoming in 1.0. But 1.1 sees a ~50% improvement in VibeCodeBench and ~10% improvement in SWE Bench. Not quite SOTA, but at this cost/latency it is still incredibly compelling. - Speaking of latency, wow this model is fast. Across our benchmarks, we find it to be 1/4 the latency of Opus 4.8 and 1/2 the latency of GPT 5.5. I would expect Meta to have incredible web infra, but really don’t know what witchcraft they’re pulling to host the model for such fast inference at high rate limits. - There is a public API. This is the first time Meta has released a model through a hosted API. I’m expecting lots of AI natives to hot-swap and rapidly test this model as a replacement. We’ll soon see if it's performant enough for those production uses. - Speaking of AI natives, it’s been a wild week for Harvey’s legal benchmark. Grok 4.5 held the SOTA position for ~24 hours at 12% before MS 1.1 unseated it with a big jump up to ~20%. I suspect many internal evals will see surprising results like this. Glad to collab with @harvey @gabepereyra @nikogrupen @ItsJulioPereyra on this eval. - Intelligence is more jagged than ever, even within individual domains like legal and coding. Every application and user benefits from staying dynamic. There an edge in picking the right model/system for each task.

@Box We appreciate you testing the model and sharing your findings! We're just getting started. 🚀

@OpenHandsDev We appreciate your testing and feedback! Let's keep building together. 🚀

OpenHands would like to congratulate @AIatMeta Superintelligence Labs on the public preview launch of their new model, Muse Spark. Were fortunate to get early-access and we’re loving what we’re seeing so far! As part of our commitment to offering a global array of LLMs for #agenticSDLC workflows, Muse Spark will be fully supported on OpenHands. Learn more here. 👇 hubs.la/Q04p29_B0

@mark_k 🚀🚀

AI enthusiasts are eating well this week! Meta just released Muse Spark 1.1, and it's a big surprise to say the least. Excellent benchmark results for agentic coding, but also for other real-life usage. Very strong release. @AIatMeta is back in the frontier AI game!

Muse Spark 1.1 is #4 on the overall vals index eval and fastest model in top 10!

if you wanna try computer use for yourself on your own machine, use this code! github.com/meta-models/me…

@WorldsByMike @whylifeis4 Find the Meta Model API here: developer.meta.com/ai/products/me…

@AIatMeta @whylifeis4 wtf wow this is awesome. What is pricing like and where is the api?

Today we are launching Muse Spark 1.1, an upgrade to muse spark 1 that greatly improves agentic, coding, multimodal, and computer use capabilities. We're also launching the Meta Model API in public preview. ai.meta.com/blog/introduci…

1/ muse spark 1.1 is an industry-competitive agentic and coding model. across many agentic evals it rivals gpt-5.5 and opus-4.8. available now through the new meta model api and in meta ai. 🧵

Muse Spark 1.1 also excels in perception and multimodal reasoning, inspecting visual and audio inputs, preserving details across long workflows, and acting on them in real execution environments. It shows particular strengths in visual-to-code generation, rich image/video captioning, and agentic computer use. In this demo, using video shot from a smartphone, Muse Spark 1.1 extracts useful photos and reasons about the product to operate a user's browser and make a Facebook Marketplace listing on the user's behalf.

Muse Spark 1.1 is used across Meta in coding and research workflows, scoring competitively with leading models on Meta's internal coding benchmark. Our researchers are now automating model development and evaluation tasks by leveraging Muse Spark 1.1 in their workflows.