LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Muse Glimmer 30B

meta·meta/muse-glimmer-30b·GA·Open weights·muse series
Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·DoublewordGateway
$0.11 / $0.32
Blended $0.16 · 18.2× spread
3 more $0 channels
Context
131,072
Output limit
131,072
Knowledge cutoff
2026-01-04
Released / updated
2026-08-10 / 2026-08-10
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDFVideo
License
Apache-2.0
Weights
Hugging Face
References
AnnouncementModel cardDeveloper docs

Muse Glimmer 30B by meta is offered by 18 providers on this page. Public prices are shown for 15 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is Doubleword at $0.11 / $0.32 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 18× across the providers that host it. It also has 3 free ($0) channels; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

The context window is 131,072 tokens, with an output limit of 131,072 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, PDF, and Video. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2026-01-04.

Available at 18 providers15 with public prices · 3 free

  • ProviderInput / Output
  • RequestyGateway
    Free
    Context 131,072Output limit 20,480
  • NvidiaCloud
    Free
    Context 131,072Output limit 131,072
  • KenariGateway
    muse-glimmer-30b:free
    Free
    Context 131,072Output limit 131,072
  • DoublewordGateway
    meta-models/Muse-Glimmer-30B
    $0.11 / $0.32
    Cache read $0.013Context 131,072Output limit 131,072
  • EmpirioLabs AIGateway
    $0.20 / $0.80
    Cache read $0.05Context 131,072Output limit 32,768
  • VultrCloud
    $0.25 / $1.00
    Context 131,072Output limit 131,072
  • LLM GatewayGateway
    $0.30 / $1.20
    Cache read $0.04Context 131,072Output limit 16,384
  • DevPass (LLM Gateway)Gateway
    $0.30 / $1.20
    Cache read $0.04Context 131,072Output limit 131,072
  • Eden AIGateway
    deepinfra/meta-models/Muse-Glimmer-30B
    $0.30 / $1.20
    Cache read $0.04Context 131,072Output limit 131,072
  • Kilo GatewayGateway
    $0.30 / $1.20
    Cache read $0.04Context 131,072Output limit 117,964
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
RequestyGatewayFree——131,07220,480
NvidiaCloudFree——131,072131,072
Kenari
muse-glimmer-30b:free
GatewayFree——131,072131,072
Doubleword
meta-models/Muse-Glimmer-30B
Gateway$0.11$0.32$0.013$0.14131,072131,072
EmpirioLabs AIGateway$0.20$0.80$0.05—131,07232,768
VultrCloud$0.25$1.00——131,072131,072
LLM GatewayGateway$0.30$1.20$0.04—131,07216,384
DevPass (LLM Gateway)Gateway$0.30$1.20$0.04—131,072131,072
Eden AI
deepinfra/meta-models/Muse-Glimmer-30B
Gateway$0.30$1.20$0.04—131,072131,072
Kilo GatewayGateway$0.30$1.20$0.04—131,072117,964

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = noneeffort = loweffort = mediumeffort = higheffort = maxeffort = minimaleffort = xhigh

Interleaved thinking (reasoning between tool calls) is declared by 2 of 18 providers.

1 / 18 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Doubleword$26.38
2EmpirioLabs AI$62.00
3LLM Gateway$88.80
4DevPass (LLM Gateway)$88.80
5Eden AI$88.80
6Kilo Gateway$88.80

3 more channels offer $0 (Requesty, Nvidia, Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.64$02026-08-112026-11-15
2026-11-15Input list —Output list —Min blended $0.16

Benchmark9 items

NameConditionsScoreMetricSource
MCP Atlasvariant: public75.5success rateSource ↗
DeepSearch QA—74.6—Source ↗
SWE-Bench Pro—51.2resolve rateSource ↗
SWE-Bench Verified—76resolve rateSource ↗
Terminal-Benchvariant: with terminus2 · v2.151.7success rateSource ↗
OSWorld-Verified—65.9success rateSource ↗
AIME 2026—94.7accuracySource ↗
GPQA Diamondvariant: AA83.5accuracySource ↗
CharXiv Reasoning—78.8accuracySource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

Muse Embersame series$0.10 / $0.50Muse Spark Opensame series—Muse Wondersame series$4.00 / $20.00Muse Spark 1.1same lab$1.25 / $4.25
Data partly from models.dev (MIT)