Muse Ember API

Q: What is the Muse Ember model ID?

Use meta/muse-ember as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

Try this model

Run tool calls, coding-agent subtasks and routing in repeated agent loops on Meta's smallest reasoning model

Modalities: Image, Text, VideoText
In / Out price: $0.1058/$0.529per 1M
Context window: 1.05M tokens
Released: Nov 9, 2026

Muse Ember overview

Muse Ember by Meta

Muse Ember is Meta's reasoning model for repeated coding subtasks, tool calls, routing and extraction.

Muse Ember specs

Model ID: meta/muse-ember
Developer: Meta
Context window: 1,048,576 tokens
Max output: 524,288 tokens
Input: Image, Text, Video
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Delegate the steps your agents repeat

Muse Ember is Meta's smallest reasoning model. It is built for coding subtasks, tool calls, routing, extraction and long-document processing. Meta recommends pairing it with Muse Wonder or Muse Spark: use Muse Wonder or Muse Spark for planning and Muse Ember for repeated execution.

Work within the model's context and output limits

The context window holds 1,048,576 tokens. Meta documents a maximum response of 524,288 output tokens. Set max_tokens to the size your task needs: extracting a few fields does not need the same output budget as producing a long document.

Connect tools and control the response format

The AI/ML API endpoint lists text, image and video inputs, plus file input, tools, structured output, streaming and reasoning. Use structured output when another step needs to read the answer as data. Set reasoning_effort per request and test the smallest effort that completes your task reliably.

Use cases

Run focused coding subtasks inside a larger agent workflow.

Extract fields from long documents into structured output.

Route requests and make repeated tool calls.

Process images, video frames and files alongside text instructions.

Capabilities

File input
Reasoning
Streaming
Structured outputs
Function calling
Vision

Muse Ember benchmarks by Artificial Analysis

See how Muse Ember compares in intelligence and cost per task. Data retrieved Nov 9, 2026.

Intelligence#17 / 6336Index v5.0 Cost per task#7 / 54$0.14USD / benchmark task

Intelligence

Index v5.0

Cost per task

USD / benchmark task

Muse Ember API pricing

Muse Ember pricing in US dollars
Usage	Price	Unit
Input	$0.1058	1M tokens
Output	$0.529	1M tokens
Cached input	$0.0042	1M tokens

Prices from the AI/ML API price list, checked on Nov 10, 2026.

Muse Ember vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Muse Ember	$0.1058	$0.529
Muse Glimmer 30B	$0.3703	$1.59
Muse Spark Open	$1.32	$4.5
Muse Spark 1.3	$1.32	$4.5
Muse Wonder	$4.23	$21.16

How to use the Muse Ember API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "meta/muse-ember",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "meta/muse-ember",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "meta/muse-ember",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Muse Ember FAQ

How much does Muse Ember cost?

Muse Ember costs $0.1058 / 1M tokens for input and $0.529 / 1M tokens for output on AI/ML API. Cached input is billed at $0.004232 / 1M tokens.

What inputs does Muse Ember accept?

The AI/ML API endpoint lists text, image and video inputs and supports file input. Meta documents PDF support for Muse Ember. The model returns text.

How can I control reasoning?

Set reasoning_effort in the request to control how much reasoning the model uses. Test the setting on your own coding, routing or extraction tasks before using it across an agent workflow.

Does it support tools and structured output?

Yes. The capabilities listed for this endpoint are file input, reasoning, streaming, structured output, tools and vision.

Which agent tasks is Muse Ember designed for?

Meta designed Muse Ember for repeated tool calls, coding subtasks, routing, extraction and long-document processing.

What is the Muse Ember model ID?

Use meta/muse-ember as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

What is the context window of Muse Ember?

Muse Ember accepts up to 1,048,576 tokens of context and returns up to 524,288 output tokens.

Start building with Muse Ember

Get API key

Muse Ember API

meta/muse-ember

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "meta/muse-ember",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "meta/muse-ember",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "meta/muse-ember",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Muse Ember API

Muse Ember overview

Muse Ember by Meta

Muse Ember specs

Delegate the steps your agents repeat

Work within the model's context and output limits

Connect tools and control the response format

Use cases

Capabilities

Muse Ember benchmarks by Artificial Analysis

Intelligence

Cost per task

Muse Ember API pricing

Muse Ember vs other models: token prices

How to use the Muse Ember API

Build with your agent

1Get your API key

2Make your first request

Muse Ember FAQ

Start building with Muse Ember

Muse Ember API

Build with your agent

1Get your API key

2Make your first request

Muse Ember API

Muse Ember overview

Muse Ember by Meta

Muse Ember specs

Delegate the steps your agents repeat

Work within the model's context and output limits

Connect tools and control the response format

Use cases

Capabilities

Intelligence

Cost per task

Muse Ember API pricing

Muse Ember vs other models: token prices

How to use the Muse Ember API

Build with your agent

1Get your API key

2Make your first request

Models similar to Muse Ember

Muse Spark Open

Muse Wonder

Muse Spark 1.3

Reka Edge

Seed-2.0-Mini

LFM2.5-24B-A2B

Muse Ember FAQ

Start building with Muse Ember