Muse Glimmer 30B

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It is suited for long-horizon agentic and coding workflows, with multi-step reasoning, reliable tool use, failure recovery, image understanding, and multilingual support across more than 100 languages.

meta/muse-glimmer-30b

Organization: Meta
Family: muse
Providers: 12
Context: 131,072
Output limit: 131,072
Knowledge: 2026-01-04
Release: 2026-08-10
Updated: 2026-08-10
Weights: Open
Input: text, image
Output: text
Capabilities: Tools, Reasoning, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

17 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
DevPass (LLM Gateway)	muse-glimmer-30b	131,072	131,072	$0.30 / $1.20	Yes	Yes	Yes	View
Eden AI	together_ai/meta-models/Muse-Glimmer-30B	131,072	131,072	$0.35 / $1.50	Yes	Yes	Yes	View
Eden AI	deepinfra/meta-models/Muse-Glimmer-30B	131,072	131,072	$0.30 / $1.20	Yes	Yes	Yes	View
EmpirioLabs AI	muse-glimmer-30b	131,072	32,768	$0.20 / $0.80	Yes	Yes	Yes	View
Kilo Gateway	meta/muse-glimmer-30b	131,072	117,964	$0.30 / $1.10	Yes	Yes	Yes	View
LLM Gateway	together-ai/muse-glimmer-30b	131,072	117,964	$0.35 / $1.50	Yes	Yes	Yes	View
LLM Gateway	deepinfra/muse-glimmer-30b	131,072	16,384	$0.30 / $1.20	Yes	Yes	Yes	View
LLMTR	muse-glimmer-30b-tr	131,072	131,072	$2.00 / $5.00	Yes	Yes	Yes	View
NanoGPT	meta/muse-glimmer-30b	131,072	117,964	$0.35 / $1.50	Yes	Yes	Yes	View
NanoGPT	TEE/muse-glimmer-30b	131,072	131,072	$0.35 / $1.50	Yes	Yes	Yes	View
Nvidia	meta/muse-glimmer-30b	131,072	131,072	$0.00 / $0.00	Yes	Yes	Yes	View
DeepInfravia OpenRouter	meta/muse-glimmer-30b bf16	131,072	16,384	$0.30 / $1.20	Yes	Yes	Yes	View
Phalavia OpenRouter	meta/muse-glimmer-30b unknown	131,072	117,964	$0.30 / $1.10	Yes	Yes	Yes	View
Togethervia OpenRouter	meta/muse-glimmer-30b unknown	131,072	117,964	$0.35 / $1.50	Yes	Yes	Yes	View
Requesty	muse-glimmer-30b	131,072	20,480	$0.00 / $0.00	Yes	Yes	No	View
Vercel AI Gateway	meta/muse-glimmer-30b	131,072	131,072	$0.35 / $1.50	Yes	Yes	Yes	View
Vultr	muse-glimmer-30b	131,072	131,072	$0.25 / $1.00	Yes	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.00Per 1M input tokens

Output from$0.00Per 1M output tokens

Available offers17Across 12 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 3 lowest-priced configurations

InputOutput

DeepInfradeepinfra/bf16

$0.30$1.20

Phalaphala

$0.30$1.10

Togethertogether

$0.35$1.50

meta/muse-glimmer-30bObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.35
Output: $1.50
Cache read: $0.04

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
DeepInfradeepinfra/bf16	$0.30	$1.20	$0.04	—
Phalaphala	$0.30	$1.10	$0.04	—
Togethertogether	$0.35	$1.50	$0.04	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 3 endpoints

P50P75P90P99

DeepInfradeepinfra/bf16

1,124–3,672 ms

Phalaphala

510–38,845.94 ms

Togethertogether

206–29,853 ms

All latency percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
DeepInfradeepinfra/bf16	1,124 ms	1,980 ms	2,583 ms	3,672 ms
Phalaphala	510 ms	856 ms	1,145 ms	38,845.94 ms
Togethertogether	206 ms	662 ms	988 ms	29,853 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 3 endpoints

P50P75P90P99

DeepInfradeepinfra/bf16

89–186 t/s

Phalaphala

63–68 t/s

Togethertogether

98–107.19 t/s

All throughput percentiles 3 endpoints

Endpoint	P50	P75	P90	P99
DeepInfradeepinfra/bf16	89 t/s	100 t/s	128 t/s	186 t/s
Phalaphala	63 t/s	66 t/s	67 t/s	68 t/s
Togethertogether	98 t/s	103 t/s	105 t/s	107.19 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 3 endpoints

Endpoint5 minutes30 minutes24 hours

DeepInfradeepinfra/bf16Observed Oct 4, 2026, 11:31 AM UTC

100%

PhalaphalaObserved Oct 4, 2026, 11:31 AM UTC

100%

99.95%

TogethertogetherObserved Oct 4, 2026, 11:31 AM UTC

100%

98.97%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

tau bench verified airlineMeta: Muse Glimmer 30B

74.667%

gpqa diamondMeta: Muse Glimmer 30B

80.598%

Evaluation	Configuration	Source	Results	Details
tau bench verified airline	Meta: Muse Glimmer 30Bmeta/muse-glimmer-30b-20260810	OpenRouter	74.667%	Details
gpqa diamond	Meta: Muse Glimmer 30Bmeta/muse-glimmer-30b-20260810	OpenRouter	80.598%	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

meta/muse-glimmer-30bObserved Oct 4, 2026, 11:31 AM UTC

Context: 131,072
Maximum output: 117,964
Tokenizer: Other
Input: text, image
Output: text
Moderation: No
Added to OpenRouter: 2026-08-09

Base URLhttps://openrouter.ai/api/v1

Model IDmeta/muse-glimmer-30b

Version IDmeta/muse-glimmer-30b-20260810

Weights IDmeta-models/Muse-Glimmer-30B

Reasoning

Required: Yes
Enabled by default: Not reported
Default effort: medium
Supported efforts: xhigh, high, medium, low

Supported parameters

frequency_penalty
include_reasoning
logit_bias
max_tokens
min_p
presence_penalty
reasoning
reasoning_effort
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_p

Default parameters

top k: 64
top p: 0.95
temperature: 1

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Muse Glimmer 30B cost?

Listed rates start at $0.00 per million input tokens and $0.00 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Muse Glimmer 30B?

There are 17 cataloged offers across 12 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 131,072 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Resources

Apache 2.0

Announcement ↗Model card ↗Developer docs ↗Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 8c80bd7d45c8
Sep 12, 2026 · c0d22be6fddc