Does Muse Glimmer 30B support zero data retention?

Yes. Muse Glimmer 30B is available with zero data retention by default on EmpirioLabs, Fireworks through the qynio gateway.

Where is Muse Glimmer 30B hosted?

Muse Glimmer 30B is available on multi-region hosting through the qynio gateway. See the per-route table for details.

Is Muse Glimmer 30B trained on prompts and outputs?

No. Every hosting route for Muse Glimmer 30B is configured so customer prompts and outputs are not used to train models by default.

Is a no-KYC deposit available for Muse Glimmer 30B?

Yes. A no-KYC Data Processing Agreement is available on at least one route serving Muse Glimmer 30B. Contact hello@qyn.io to receive it.

Muse Glimmer 30B

by Meta

Muse Glimmer 30B is Meta Superintelligence Labs' August 2026 open-weight release, a 30 billion parameter model published under Apache 2.0 and aimed at agents that run continuously rather than at conversation. The permissive license is the notable part, marking a move away from the community terms the Llama family shipped under. The model is sized for local GPU inference, so an agent loop can run on a workstation or a single accelerator with no hosted frontier model in the path. It takes image input alongside text and supports tool calling and structured output, which fits always-on automation, on-device assistants, and any workflow where the round trip to a remote API is the thing slowing it down.

Open in playground Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

33K

Input price

$0.20 /1M

Output price

$0.80 /1M

Zero data retention on pay-as-you-go
No training by default
no-KYC deposit available

Available routes

Muse Glimmer 30B runs on 2 different routes through the qynio gateway. Compare residency, zero retention, and training posture at a glance — full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output
EmpirioLabs	Multi	Zero data retention	No	$0.20	$0.80
Fireworks	Multi	Zero data retention	No	$0.35	$1.50

Uptime and availability

One of Muse Glimmer 30B's 2 routes is on the monitoring board, so the figure below is that provider's availability rather than the model's.

100%route uptime, last 30 days

Its other routes aren't measured here yet.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. .

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 1 further route is not on the board yet. See uptime for every provider qynio monitors.

Data handling per route

Each route hosting Muse Glimmer 30B has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.

EmpirioLabs — Multi-region

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. GLOBAL; wallets; deposit available.

Zero data retention: On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: None
Moderation: Not established
Caching: Not established
Subprocessor access: No subprocessor reads content
no-KYC deposit: deposit available
Transfer mechanism: wallets

Fireworks — Multi-region

Zero data retention is on by default on Pay-as-you-go — no action required. No training on customer data. GLOBAL; wallets; deposit available.

Zero data retention: On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training: No training on customer data.
Logging: None
Moderation: Not established
Caching: Not established
Subprocessor access: Subprocessors may read content
no-KYC deposit: deposit available
Transfer mechanism: wallets

Get started

Call Muse Glimmer 30B through the qynio gateway with one API key. Let your coding agent set it up, or call it directly — qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.QYN_API_KEY,
5  baseURL: "https://api.qyn.io/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "empiriolabs/muse-glimmer-30b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);