Models

Meta ships seven model lines. Muse Wonder, Muse Spark, Muse Ember, Muse Image, Muse Voice Transcribe, and Segment Anything Model (SAM) are hosted on Meta Model API; Muse Glimmer is open-weight and runs on your own hardware. Muse Spark also has an open-weight release, Muse Spark Open. Pick one by what you're building, then read its section to learn more. To decide between Muse Wonder, Muse Spark, and Muse Ember, see Choose a model.

Models at a glance

Use case	Model	Input	Output	API endpoints
Agentic work, coding, and reasoning	Muse Wonder, Muse Spark, Muse Ember	Text, image, video, audio, and PDF	Text	Responses, Chat Completions, Messages
Image generation and editing	Muse Image	Text and image	Image	Responses, Image generation
Speech to text	Muse Voice Transcribe	Audio	Text (transcription)	Transcribe
Image and video segmentation	Segment Anything Model	Text prompt, image, and video	Text (geometry)	Responses, Segmentation
Self-hosted or provider-hosted agentic and coding work; post-training	Muse Spark Open	Text, image, video, and audio	Text	None (self-host or a hosted provider)
Self-hosted inference; supervised fine-tuning	Muse Glimmer	Text and image	Text	None (self-host)

Muse Wonder

Muse Wonder is Meta's most capable model, built for complex software engineering and long-horizon agentic work. It makes and verifies changes across many files in real repositories, and it plans, delegates to sub-agents, calls tools in parallel, and recovers from errors across many steps. Muse Wonder is in preview.

Model ID	Input	Output	Context window
`muse-wonder-1.0`	Text, image, video, audio, PDF	Text	1,048,576 tokens

Muse Wonder comes in two variants: Muse Wonder on Model API and in Muse Code, and the higher-capability Muse Wonder Full in Muse Code only. See the Muse Wonder page for specs, recommended settings, and availability.

Muse Spark

Muse Spark is Meta's model for agentic and coding work at scale, such as multi-step tool loops, software engineering assistants, and long-context reasoning. It comes in three versions, and Muse Spark 1.3 is recommended for new work.

Model ID	Input	Output	Context window
`muse-spark-1.3`, `muse-spark-1.2`, `muse-spark-1.1`	Text, image, video, audio, PDF	Text	1,048,576 tokens

On Model API, Muse Spark also offers discounted Contributor-mode variants. See the Muse Spark page for every version, recommended settings, and availability.

Muse Ember

Muse Ember is the efficient execution model in the Muse family, built for high-volume, repeated work: sub-agent tasks, tool calls, routing, and processing large collections of images, files, and records. It takes the same requests as Muse Spark at a lower price per token. Pair it with Muse Spark or Muse Wonder: the larger model plans, and Muse Ember handles the volume.

Model ID	Input	Output
`muse-ember-1.0`	Text, image, video, audio, PDF	Text

On Model API, Muse Ember runs in Standard mode only. See the Muse Ember page for specs, recommended uses, and availability.

Muse Image

Muse Image is Meta's image generation model line. Send a text prompt (and optional reference images) and get an image back, or send an image with an instruction to edit it. One model handles both generation and editing. It's agentic, so it can search the web for visual references and current facts and run code to build layouts before it renders.

Model ID	Input	Output
`muse-image-1.0`	Text, image	Image

Reach Muse Image two ways: the Responses API for conversational, multi-turn editing, or the single-shot /v1/images/generations and /v1/images/edits endpoints for one-off calls. See the Image generation guide to get started.

Muse Voice Transcribe

Muse Voice Transcribe is Meta's speech-to-text model on Meta Model API. Use it to transcribe live audio streams or supported audio files.

Model ID	Input	Output
`muse-voice-transcribe-1.0`	Audio	Text transcript

Muse Voice Transcribe is built for real-time speech products: voice agents, meeting and call intelligence, live transcription, dictation, captioning, and high-volume transcription. It supports streaming speaker diarization, native endpointing and voice activity detection, contextual and keyword biasing, 25 evaluated languages with code-switching, and turn-level timestamps.

It returns transcript text. It does not synthesize speech or provide a speech-to-speech conversation API. It does not provide word-level timestamps, sound event detection, or emotion detection.

Reach Muse Voice Transcribe two ways: the realtime WebSocket endpoint (wss://api.meta.ai/v1/asr/realtime) for live audio, or the file endpoint (POST /v1/asr/transcribe) for a recording you already have.

Start with the Muse Voice Transcribe guide. See Pricing and rate limits for audio pricing.

Segment Anything Model

SAM 3.1 is Meta's segmentation model on Meta Model API. Give it a short noun phrase such as "yellow school bus" with an image or video, and it returns every match as a box and a pixel-accurate mask. Or mark specific objects with boxes, points, or masks to segment only those objects. One model handles both stills and clips, and in video it follows each object across frames.

Model ID	Input	Output
`sam-3.1`	Text prompt, image, video	Boxes and masks

Reach SAM 3.1 over the Responses API (POST /v1/responses), and upload clips through the Files API when you segment them more than once. See the SAM overview to get started.

Muse Spark Open

Muse Spark Open is the open-weight release of Muse Spark: an 816B-parameter mixture-of-experts model with 42B active parameters. You don't call it over Model API. Download the weights and serve them through a runtime such as SGLang, vLLM, TensorRT-LLM, or llama.cpp, or call it through a hosted inference provider.

Muse Spark Open lives in the Open-weight models section:

Muse Spark Open overview: checkpoints, hardware, license, and launch partners.
Get the model: download the BF16 or NVFP4 weights.
Run inference: serve it on your own GPUs or call a hosted provider.
Post-training: adapt it with supervised fine-tuning (SFT) or reinforcement learning (RL).

Muse Glimmer

Muse Glimmer is Meta's open-weight multimodal model, distilled from Muse Spark and built to run on your own hardware. You run it yourself instead of calling it over Model API: download the weights and serve them through a runtime such as vLLM, SGLang, llama.cpp, or ExecuTorch.

Muse Glimmer lives in the Open-weight models section, covering how to get, prompt, deploy, and customize the model:

Muse Glimmer overview: variants, architecture, license, and launch partners.
Get the model: download the weights and verify your setup.
Run inference: pick a runtime and serve it locally.
Post-training: adapt it to your domain with supervised fine-tuning (SFT) or reinforcement learning (RL).

List models via the API

Query the catalog programmatically when you need to check what's enabled for your team. This returns the API-hosted models; self-hosted Muse Glimmer isn't included.

python
import os
from openai import OpenAI
client = OpenAI(
    base_url="https://api.meta.ai/v1",
    api_key=os.environ["MODEL_API_KEY"],
)
response = client.models.list()
print(response.model_dump_json(indent=2))

typescript
import OpenAI from 'openai';
const apiKey = process.env.MODEL_API_KEY;
if (!apiKey) {
  throw new Error('MODEL_API_KEY is not set');
}
const client = new OpenAI({
  baseURL: 'https://api.meta.ai/v1',
  apiKey,
});
const models = await client.models.list();
console.log(JSON.stringify({ object: models.object, data: models.data }, null, 2));

python
import json
import os
import requests
response = requests.get(
    "https://api.meta.ai/v1/models",
    headers={"Authorization": f"Bearer {os.environ['MODEL_API_KEY']}"},
)
response.raise_for_status()
print(json.dumps(response.json(), indent=2))

shell
curl -X GET "https://api.meta.ai/v1/models" \
  -H "Authorization: Bearer $MODEL_API_KEY"

The response returns models sorted newest-first by creation time, with the model ID as a stable tiebreaker. Each object includes a created field — the Unix timestamp in seconds for when the model was added to the registry. GET /v1/models/{model} returns the same created value for a single model.