---
title: "Muse Ember 1.0"
canonical: "https://openvibe.exchange/m/meta/muse-ember-1.0"
updated: null
---

# Muse Ember 1.0

HTML: [Muse Ember 1.0](https://openvibe.exchange/m/meta/muse-ember-1.0)

[](/models)

# Muse Ember 1.0

muse-ember · 1 offer

- cheapest in, per M: $0.10
- cheapest out, per M: $0.50
- context, tokens: 1,048,576
- typical first answer: –
- uptime, 7 days: –

## Measured

From OpenVibe.Report: real calls in the last 30 days, with no prompt and no person in them.

Not measured yet: a model is measured after 20 calls in 30 days.

## Every offer that serves it

Price in, out and cached per million tokens; speed and uptime from the last seven days of real requests; the privacy label and the provider’s own data policy.

| Offer | Status | In / out per M | Speed | First token | Uptime | Errors | Privacy | Data policy | Try |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| [Meta Model API](#try) | Down<br>off until the owner turns it on | **$0.10** / $0.50 | – p50 · – p95 | – | – | – | Anonymized<br>interactive/background/batch only | training not stated · no retention | [Try it](https://openvibe.chat/vibe?models=meta%2Fmuse-ember-1.0) |

[Compare Muse Ember 1.0 with another model →](https://openvibe.compare/things/meta%2Fmuse-ember-1.0)

## Measured performance

Measured performance is unavailable.

## Presets

A preset fixes the router’s floor, ceiling and policy, and you name it as the model.

 **Cheapest** `model: "openvibe/economy"` 

The lowest cost per successful answer.

 **Fastest** `model: "openvibe/fast"` 

The quickest measured offer.

 **Private** `model: "openvibe/private"` 

Only capacity OpenVibe runs or that sits on a local machine.

 **Balanced** `model: "openvibe/auto"` 

Cost, health and latency weighed together. The default.

These four aliases work today. A saved preset (`model: "@preset/private"`) is the router’s floor, ceiling, quantization, region and data policy written down once. The private preset is the strict one: only offers that keep nothing and train on nothing, or OpenVibe’s own deployments, may answer, and the router refuses rather than fall back.

## Try it

[Chat with Muse Ember 1.0](https://openvibe.chat/vibe?models=meta%2Fmuse-ember-1.0) [How it ranks](https://openvibe.report/ai/models/meta%2Fmuse-ember-1.0)

## Use it from code

~~~~
curl https://api.openvibe.exchange/v1/chat/completions \
  -H "Authorization: Bearer $OPENVIBE_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"meta/muse-ember-1.0","messages":[{"role":"user","content":"Hello"}]}'
~~~~

~~~~
import OpenAI from 'openai';
const ai = new OpenAI({ baseURL: 'https://api.openvibe.exchange/v1', apiKey: process.env.OPENVIBE_KEY });
const r = await ai.chat.completions.create({ model: 'meta/muse-ember-1.0', messages: [{ role: 'user', content: 'Hello' }] });
~~~~

The endpoint, keys and usage: [the API](/api).