Skip to content

· 11 min read · Nadeera Silva

AI & Automation

Meta Muse Models Explained: Wonder, Spark, Ember and Glimmer

Meta Muse now covers Wonder, Spark 1.3, Ember, Glimmer and a device called Charm. Here is what each one is, what it costs and which to use.

Clay-style still life of four glowing gems in a row, a large teal crystal, a medium crystal with an amber spark, a small amber ember in a dish and a tiny crystal under a glass dome on a laptop, linked to one server, with a pocket charm keyring set apart, standing for the Meta Muse model lineup and the Muse Charm device

Meta Muse is no longer one model. In the last three months Meta has shipped Muse Wonder, Muse Spark 1.3, Muse Ember, an open-weight Muse Spark, a small local model called Muse Glimmer, and announced a gadget called Muse Charm. If you build with LLMs, the names alone make it hard to know what you can call from code, what you can download, and what is just a product. This guide maps the whole Meta Muse lineup from Meta's own docs and model cards, shows what each one costs, and gives a small router you can use to put the right model on each part of an agent.

What is Meta Muse?

Muse is Meta's brand for its current generation of AI: the Muse assistant app, the Muse agent, the Muse Code terminal coding agent, and the models behind them. For developers, the important split is between three kinds of thing that all carry the Muse name:

  1. Hosted reasoning models you call through the Meta Model API: Muse Wonder, Muse Spark and Muse Ember.
  2. Open-weight models you download and run yourself: Muse Spark Open and Muse Glimmer.
  3. Products built on top of the models: the Muse app, Muse Code, and the Muse Charm device.
Diagram of the Meta Muse lineup: Muse Wonder, Muse Spark 1.3 and Muse Ember on the Meta Model API with their per-token prices, Muse Wonder Full only in Muse Code subscriptions, Muse Spark Open and Muse Glimmer 30B as open weights, and Muse Charm marked as a device rather than a model
The Meta Muse lineup as of 12 November 2026, grouped by how you get access

The Meta Muse models at a glance

NameWhat it isHow you get itPrice (per 1M tokens, in / out)Released
Muse WonderFrontier reasoning model for hard coding and long agent runsModel API (muse-wonder-1.0), Muse Code$4.00 / $20.0012 Oct 2026
Muse Wonder FullHigher-capability Wonder variantMuse Code Power ($50/month) and Maximum ($200/month) plans onlySubscription12 Oct 2026
Muse Spark 1.3Mid-tier model for the main agent loopModel API (muse-spark-1.3), Muse Code$1.25 / $4.252 Sep 2026
Muse EmberSmallest hosted model for high-volume stepsModel API (muse-ember-1.0), Muse Code$0.10 / $0.509 Nov 2026
Muse Spark OpenOpen-weight Muse Spark, 816B total / 42B activeHugging Face, Muse Model LicenseYour hardware15 Oct 2026
Muse Glimmer 30BSmall open model for local agentsHugging Face, Ollama, Apache 2.0Your hardwareModel card dated Aug 2026
Muse CharmPocket device for talking to the Muse agentNot on sale yetNo price announcedAnnounced 23 Sep 2026

Prices are Standard mode list prices from Meta's pricing page. Muse Ember charges more for prompts over 200K input tokens ($0.30 in, $0.012 cached, $1.50 out), while Wonder and Spark charge the same rate at any context length.

Muse Wonder and Muse Wonder Full

Muse Wonder launched on 12 October 2026 as Meta's top model on the API. Meta positions it for multi-file changes in real repositories, multi-hour agent runs, sub-agent orchestration and computer use. It costs $4 per million input tokens, $0.20 cached and $20 output.

Muse Wonder Full is the confusing one. According to Meta's launch post, it is available only inside Muse Code on the Power Usage ($50 a month) and Maximum Usage ($200 a month) plans. The Choose a model guide is explicit that no model ID on the Model API selects it. So if a tutorial tells you to set model="muse-wonder-full" in your API code, it is wrong.

Muse Spark 1.3 (and 1.2, 1.1)

Muse Spark 1.3 came out on 2 September 2026 and is the model Meta recommends for most work. Meta says it uses about 20% fewer tool calls and 25% fewer tokens than 1.2 in its internal comparisons. The older muse-spark-1.2 and muse-spark-1.1 IDs are still listed at the same price, which is why you still see searches like "meta muse spark 1.1". Unless you have a pinned evaluation on 1.1, there is no price reason to stay on it.

Spark is also the only hosted model with Contributor mode: muse-spark-1.3-contributor and muse-spark-1.2-contributor cost $0.10 in and $0.20 out, but Meta may use your prompts, files and outputs to train future models, and the rate limit drops from 3,000 to 150 requests per minute.

Two smaller details from the docs: the "max" reasoning effort works on muse-spark-1.3 but not on 1.2, 1.1 or the Contributor variant, and Meta notes that audio understanding may be degraded on 1.3, so it points audio work to 1.2 or Muse Voice Transcribe.

If you want the open-weight Spark rather than the API, my Muse Spark Open developer guide covers the model card, hardware and license in detail.

Muse Ember: the cheap workhorse

Muse Ember, released on 9 November 2026, is Meta's smallest hosted model. Meta describes it as built for "the work agents repeat all day": tool calls, coding subtasks, routing, extraction and long-document parsing. It has a 1M-token context window, up to 512K output tokens, and supports the Responses API.

The headline claim is cost. On Artificial Analysis Intelligence Index v5, Meta reports Ember at about $0.14 per task with a score of 36, against $2.39 per task for Muse Spark 1.3 at 37. Meta also says Ember matches Claude Haiku 5.5's best score at about a third of the cost and beats every GPT-6 Luna setting. Some partner numbers are striking too, for example Cloudflare reported up to 30% faster tail latency than the comparable model it tested.

Meta's own docs also say where not to use it: for hard single-shot coding problems, knowledge-heavy questions or visual coding, use Spark or Wonder instead. That matches what I would expect from a small model, and it is the right way to think about Ember: as the model for sub-agents and bulk jobs, not the brain of the agent.

Muse Glimmer: the local model

Muse Glimmer 30B is a different kind of release. It is an open model under Apache 2.0, distilled from Muse Spark and designed to run agents locally without a network connection. From the model card:

  • About 29.6B parameters, dense transformer, plus a roughly 1.8B-parameter vision encoder. It takes text and images in and returns text. Audio is not supported.
  • Context of 131,072 tokens or more, and a knowledge cutoff of 4 January 2026.
  • Quantized builds target 24 GB or 32 GB of GPU memory. The Ollama build is an 18 GB Q4_K_M download.
  • A speculative decoding drafter (DFlash) that Meta measured at 233 tokens per second on an RTX 5090, and about 50 on an M5 Max.
  • Reasoning strength is set in the system prompt (Reasoning strength: high), with low, medium, high and xhigh levels.

Meta's research paper was published on 19 October 2026, while the Hugging Face card lists an August 2026 release date, which explains why you see both dates online. Running it is one command:

ollama run muse-glimmer:30b
# Apple Silicon build with the MLX engine
ollama run muse-glimmer:30b-mlx

Glimmer is the option to look at when data must not leave a machine, for example a support assistant that reads internal documents on an office workstation. Meta's card recommends adding human confirmation for irreversible actions when the model can act in the real world, which is good advice for any local agent.

Muse Charm is a device, not a model

Muse Charm shows up in the same searches, but it is hardware. Meta revealed it at Connect 2026 on 23 September as a small pocket device for talking to the Muse agent. Meta's 5 November post says voice conversations are "coming soon" to Muse Charm. There is no Muse Charm model ID, no API and, as of 12 November, no published price or ship date. You do not need to plan any integration work for it.

Which Muse model should you use?

Meta's Choose a model guide gives a clear workload table. Here is my condensed version for typical client projects:

WorkloadModelWhy
Coding agent main loop, multi-file refactorsMuse WonderCapability matters more than token price
Chatbot or assistant main loop on a budgetMuse Spark 1.3Strong reasoning at about a third of Wonder's input price
Tool calls, routing, classification, extractionMuse EmberCheapest hosted option, built for many short steps
Same task over thousands of files or recordsMuse EmberWatch the 200K-token long-context price step
Data must stay on your own machineMuse Glimmer 30BApache 2.0, runs on one 24 GB GPU
Self-hosting a frontier-size modelMuse Spark OpenOpen weights, but server-class hardware
Audio understandingMuse Spark 1.2 or Muse Voice TranscribeMeta flags degraded audio on Spark 1.3

The pattern Meta recommends is to combine them in one agent: a bigger model plans on the main loop and Ember handles the volume. I use the same split for AI chatbots that need to look things up, where most turns are simple tool calls and only a few need deep reasoning. If you are weighing Muse against other providers, my LLM API pricing comparison shows how to compare cost per task instead of cost per token.

Calling the Muse models from code

The Model API is drop-in compatible with the OpenAI SDK at https://api.meta.ai/v1, per Meta's SDK docs. Keys start with LLM_, and the SDK does not read MODEL_API_KEY on its own, so pass it explicitly. Because Wonder, Spark and Ember accept the same request body, routing is just a different model value per call:

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.meta.ai/v1",
    api_key=os.environ["MODEL_API_KEY"],  # keys start with LLM_
)

# One place to decide which Muse model handles which kind of step.
MODEL_FOR = {
    "plan": "muse-spark-1.3",      # main loop; use muse-wonder-1.0 for hard repo work
    "tool_step": "muse-ember-1.0",  # short, bounded sub-tasks
    "extract": "muse-ember-1.0",
}

def run(step: str, prompt: str) -> str:
    response = client.responses.create(model=MODEL_FOR[step], input=prompt)
    return response.output_text

plan = run("plan", "Break this support ticket into lookup steps: order #1234 never arrived.")
print(plan)
print(run("extract", "Return only the order number from: 'order #1234 never arrived'"))

Keep the mapping in config, not scattered through the code, so you can move a step to a bigger model when your evaluations say it needs one.

What a task costs on each model

A quick worked example with list prices, for a step with 20,000 input tokens and 2,000 output tokens:

ModelCost per stepCost per 1,000 steps
Muse Wonder$0.120$120.00
Muse Spark 1.3$0.034$33.50
Muse Ember$0.003$3.00

Two things change this in practice. Reasoning tokens bill as output, as LiteLLM's Spark 1.3 notes point out, and Wonder and Ember default to "max" effort when a request sets none, so real output counts can be much higher than the visible answer. Cached input is far cheaper ($0.004 per million on Ember), so a stable system prompt and tool list at the start of each request pays off. Web search grounding adds $2.50 per 1,000 queries on all three.

Rate limits and data use

Rate limits are per team, not per key: 3,000 requests and 4 million tokens per minute for each Standard model, with each model counted separately. In Standard mode Meta states your content is not used for training. In Muse Code, subscriptions default to Contributor mode, so check that setting before you point Muse Code at a client repository.

Bottom line

For most apps the Meta Muse lineup comes down to three API model IDs: Wonder for the hardest work, Spark 1.3 for a cheaper main loop, and Ember for everything repetitive. Glimmer is the one to try when the model has to run on your own hardware, Wonder Full lives only in Muse Code, and Charm is a gadget. Test Ember on your real tool-calling steps first, because that is where the savings are largest.

Frequently asked questions

What is Meta Muse?

Meta Muse is Meta's brand for its current AI assistant, agent and models. For developers it covers three hosted models on the Meta Model API (Muse Wonder, Muse Spark and Muse Ember), two open-weight models (Muse Spark Open and Muse Glimmer), and products such as the Muse app, Muse Code and the Muse Charm device.

How do I use the Muse Spark API?

Create a key in the Meta Model API dashboard, then point the OpenAI SDK at https://api.meta.ai/v1 with that key and the model ID muse-spark-1.3. The same request works for muse-wonder-1.0 and muse-ember-1.0, so switching models is a model ID change.

What is the difference between Muse Ember and Muse Spark?

Muse Spark 1.3 is the mid-tier model for an agent's main loop at $1.25 input and $4.25 output per million tokens. Muse Ember is the smallest hosted model at $0.10 and $0.50, built for tool calls, routing, extraction and sub-agent tasks. Meta recommends Spark or Wonder for hard single-shot coding and knowledge-heavy questions.

Is Muse Glimmer open source and can I run it locally?

Yes. Muse Glimmer 30B is released under Apache 2.0 on Hugging Face. Its 4-bit builds target 24 GB or 32 GB of GPU memory, and Ollama offers an 18 GB build you can run with ollama run muse-glimmer:30b. It takes text and images in and does not support audio.

Can I call Muse Wonder Full through the API?

No. Meta says Muse Wonder Full is available only in Muse Code on the Power Usage and Maximum Usage plans, and no Model API model ID selects it. On the API, use muse-wonder-1.0.

Is Muse Charm a model?

No. Muse Charm is a small pocket device for talking to the Muse agent, announced at Connect 2026. It has no API or model ID, and Meta had not published a price or ship date as of 12 November 2026.

Is Meta Muse Spark 1.1 still available?

Yes. muse-spark-1.1 is still listed on the Model API at the same price as 1.3, but Meta recommends muse-spark-1.3, and the max reasoning effort only works on 1.3.

Sources

  1. Introducing Our Smallest, Most Efficient Model: Muse Ember (Meta AI Research, 2026-11-09)
  2. Pricing and rate limits (Meta Model API docs)
  3. Choose a model (Meta Model API docs)
  4. Put your ideas to work with Muse Wonder and Muse Wonder Full (Meta for Developers, 2026-10-12)
  5. Muse Wonder model page (Meta)
  6. Introducing Muse Spark 1.3 (Meta AI Research, 2026-09-02)
  7. SDKs and libraries (Meta Model API docs)
  8. Authentication (Meta Model API docs)
  9. Muse Glimmer 30B model card (Hugging Face)
  10. Muse Glimmer 30B: An On-Device Agentic Model (AI at Meta, 2026-10-19)
  11. muse-glimmer:30b (Ollama)
  12. The Biggest News From Connect 2026 (Meta Newsroom)
  13. Give Your Muse a Voice (Meta Newsroom, 2026-11-05)
  14. Day 0 support: Meta Muse Spark 1.3 (LiteLLM, 2026-09-02)
SharePost on XLinkedIn

Comments

Share a question or note about this article.

Loading comments…

Meta Muse Models Explained: Which One to Use (2026) | Nadeera Silva