opendunes

Muse Ember

New

by MetaReleased 9 November 2026

This model reads text, pictures, video, audio and files, taking in about 1,000 pages at once and writing up to 940 pages back. It thinks before answering, so it suits work you sit down to repeat all day: coding subtasks, routing requests, and running the small tool-driven steps behind an assistant. It can search the web, use your tools and fill answers into a fixed format, and it costs less when the same text is sent again. Its size makes it best for short, repeated reasoning jobs rather than long, heavy drafting, which calls for a larger model.

TakesTextImagesVideoAudioFiles
GivesText

Where your request runs

Two companies run this model. OpenDunes sends each request to one of them. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Google…
↑ Sent, per 1M
33,28 DA
↓ Back, per 1M
166,42 DA
Cache read
1,33 DA
Latency
…
Throughput
…
Meta…
↑ Sent, per 1M
33,28 DA
↓ Back, per 1M
166,42 DA
Cache read
1,33 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Google33,28 DA166,42 DA1,33 DA………
Meta33,28 DA166,42 DA1,33 DA………

Also charged: writing to the cache, at Meta ↑ 41,60 · a web search, at Google 3,33 DA each, at Meta 0,83 DA each.

You pay the price of the provider that served your request. Prices read 02:47 · speed over the last 30 minutes · uptime over 3 days.

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,12 DA per message3 000 DA buys about 25 000 messages

One message, the ordinary use

1 000 sent1 000 tokens sent× 33,28 per 1M× 33,28 DA per 1M0,033 DA
500 back500 tokens back× 166,42 per 1M× 166,42 DA per 1M0,083 DA
Total≈ 0,12 DA

Every rate

Meter↑ you send↓ comes back
Text tokens33,28 DA166,42 DA
Cached tokens read1,33 DA
Cache-write tokens41,60 DA

per 1M tokens

Web search · 3,33 DA per call

Everyday jobs, priced

Answer a question with two web searches about a 5-page article≈ 0,47 DA
Draft a 1-page answer reusing a 60-page reference already sent≈ 0,83 DA
Summarise a 40-page scanned report and draft a 2-page brief≈ 1,00 DA
Transcribe a 10-minute audio clip and write 3 pages of meeting notes≈ 1,30 DA
Sort 500 customer messages into fixed reply categories≈ 2,91 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
Add creditDeposits from 100 DA, withEdahabiaCIB

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Understands images
You send

What's the total on this invoice, and when is it due?

invoice-scan.jpg · photoTry in Chat Lab
Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txtTry in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
meta/muse-ember
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="meta/muse-ember",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kseedrepetition_penalty

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Limits

The hard numbers — what it can take in, what it can give back, and where it stops.

Context window
1 048 576 tokens
Max output
943 718 tokens
Reads at once
≈ 1 000 pages
Longest reply
≈ 708 000 words
Tokenizer
Other
Released
9 Nov 2026
Full API reference

Questions about Muse Ember

How much does Muse Ember cost in dinars?

About 0,12 DA per message. ↑ 33,28 DA · ↓ 166,42 DA per 1M tokens.

Is Muse Ember free? Can I try it?

No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.

What is Muse Ember best for?

This model reads text, pictures, video, audio and files, taking in about 1,000 pages at once and writing up to 940 pages back. It thinks before answering, so it suits work you sit down to repeat all day: coding subtasks, routing requests, and running the small tool-driven steps behind an assistant. It can search the web, use your tools and fill answers into a fixed format, and it costs less when the same text is sent again. Its size makes it best for short, repeated reasoning jobs rather than long, heavy drafting, which calls for a larger model.

How do I pay for Muse Ember without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Muse Ember included, is paid from that balance. No foreign card, no conversion.

Does Muse Ember work in Arabic, French or Darja?

Meta names no languages for Muse Ember. Arabic, French and Darja: not stated.

Can it read PDFs, images or a whole book?

It reads text, images, video, audio and PDFs. Up to 1M tokens in one request, about 1 000 pages. It writes up to 708 000 words at once.

Is Muse Ember open source?

No. Meta has not published its weights.

Who makes Muse Ember, and when was it released?

Meta. Released 9 November 2026.

Other Meta models, priced in dinars

See all Meta models
Muse ImageMeta · Aug 26, 2026

Muse Image makes and edits pictures from a written description, with optional reference pictures. It thinks before it draws, breaks multi-part requests into steps, and can search the web for factual requests. It writes readable text inside the picture, keeps a style or subject steady across a series, and edits by taking the previous result back with a fresh instruction.

3,33 DAper image
View model
Muse Voice Transcribe 1.0Meta · Sep 11, 2026

Muse Voice Transcribe 1.0 turns speech into text in a single step. Send a single-channel WAV recording of up to 10 minutes and get the transcript back. It handles push-to-talk, finding where a speaker stops, and separate speakers, and you can steer it toward specialist terms or a language with a hint. It gives no word-by-word timing or confidence scores, so convert recordings in other formats to WAV first.

1,00 DAper minute of audio
View model
Muse Spark 1.3 ContributorMeta · Sep 2, 2026

Muse Spark 1.3 Contributor is the lower-cost tier of Muse Spark 1.3, with the same text, picture, video and PDF input and thousand-page memory, for experiments, learning and early automated and coding projects. It keeps track of information across long tasks and works through conflicting information. For the previous release at this tier, use 1.2 Contributor.

Searches the webThinks firstUses your tools
≈0,067 DAper message
View model
Muse WonderMeta · Oct 12, 2026

#1 for code · Muse Wonder is Meta's model for long, complex automated work, and it thinks before it answers. It takes PDFs, audio, video, pictures and text, answers in text, and keeps about a thousand pages in mind. It plans, hands tasks to helper agents, uses several tools at once, recovers from errors, operates browsers and desktop or mobile apps, and edits across many files in a code project.

Searches the webThinks firstUses your tools
≈4,66 DAper message
View model