Get started

Muse Glimmer 30B

Sold by 3 sellers, timed at 102 tok/s, scored 6.3 on the Intelligence Index, and on 6 Design Arena boards.

retrieved sha256 · 0bb53a77713f

Models/Meta/Muse Glimmer 30BUSD per 1M tokens · as OpenRouter routes it
meta/muse-glimmer-30bMeta · base listing · Other tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.35per 1M tokens
Output$1.50per 1M tokens
Cached input$0.04per 1M tokens
Context131k131,072 tokens
What Vitna read · the provider's own pricing page, kept as a dated recordin / out per 1M tokens
Together AIopen weights$0.35 / $1.50confirmed 22 Nov 2026

The same weights, served by one provider at its own list price, read from www.together.ai. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.

What the list says · the fields OpenRouter publishes for this id11 fields
AuthorMeta
Listed
Canonical idmeta/muse-glimmer-30b-20260810
Context131,072 tokens
Max output117,964 tokens
Modalitiestext, image → text
TokenizerOther
Reasoningalways on · effort xhigh, high, medium, low, medium by default
Moderationnot moderated by OpenRouter
Other listingbatch variant
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Licenceapache-2.0
Parameters29.8B · 29,776,626,688 declared
Model classMuseGlimmerForConditionalGeneration
Downloadnot gated
Published

What sellers charge

3 sellers · 1.17x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.30 at DeepInfra to $0.35 at Together. 2 sellers undercut the $0.35 listed; 0 are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

1,607 requests · 3 endpoints · 30-minute window
Throughput102 tok/sMedian output rate, weighted across the 3 endpoints serving it by the requests each answered.the speed board
First token387msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread90 to 121The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter's own timing of its routed traffic, weighted by requests, over one 30-minute window read . Every route is on the endpoint ledger below.

Every endpoint

3 priced · 3 timed · cheapest first
  1. DeepInfradeepinfra/bf16$0.30$1.20$0.04bf1616k121 tok/s43356ms491 req99.77%
  2. ModelRunmodelrun/bf16$0.30$1.20$0.04bf16118k90 tok/s74512ms442 req100%
  3. Togethertogether · listed$0.35$1.50$0.04not declared118k95 tok/s74327ms674 req100%

Each track runs from a route's p90, the rate nine in ten of its requests met or beat, up to its median. Weighted by requests, the figure above reports where the traffic went rather than what one route does: 2 of the 3 timed routes are slower than it, and the middle route runs at 95 tok/s. The widest median-to-p90 gap is DeepInfra's, 2.81x.

Uptime is OpenRouter's own figure for each seller over the trailing day, read once a day, and the column prints the latest reading, taken . 1 of the 3 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Together at 56.05% on 26 Oct 2026. Source: OpenRouter's public endpoints API, one reading a day for each seller: 1,211 sellers carried one on the latest of the 23 days held.

Source: OpenRouter's public endpoints API. 1257 sellers across 359 models when the mirror ran, 186 of them served by more than one. List prices, not what anybody paid; a discount is the seller's own. Read . Speed is OpenRouter's own timing over one 30-minute window, read .

What each seller accepts

20 parameters · 3 sellers
  1. frequency_penaltyevery seller
  2. include_reasoningevery seller
  3. max_tokensevery seller
  4. presence_penaltyevery seller
  5. reasoningevery seller
  6. reasoning_effortevery seller
  7. repetition_penaltyevery seller
  8. stopevery seller
  9. structured_outputsevery seller
  10. temperatureevery seller
  11. tool_choiceevery seller
  12. toolsevery seller
  13. top_pevery seller
  14. logit_bias2 of 3not ModelRun
  15. min_p2 of 3not ModelRun
  16. response_format2 of 3not ModelRun
  17. top_k2 of 3not ModelRun
  18. logprobs1 of 3not DeepInfra and ModelRun
  19. seed1 of 3not ModelRun and Together
  20. top_logprobs1 of 3not DeepInfra and ModelRun

13 of these 20 are accepted by every one of the 3 sellers that publish a list; the other 7 are declared by some sellers and not others, so what a request sending one of them gets depends on which seller serves it. Each list is the seller's own declaration in OpenRouter's endpoints API, read , and nothing here tested one.

Price position

342 priced models

Blended $0.638 per million tokens, 3 in to 1 out: cheaper than 190 of the 342 priced models in the catalog. Each bar is one stretch of the catalog on a logarithmic price scale; the mark is this listing.

Measured quality

145 models with an index · 132 on a design arena board

Each mark is one board this model stands on, placed at the share of that board it scores above, and led to its number in the list under the rule. The columns and the ledger below carry the figures.

Intelligence Index6.3Position 49 of 58, above 16% of the models scored.the intelligence leaderboard
Coding Index49.0Position 60 of 118, above 49% of the models scored.the coding leaderboard
Agentic Index8.5Position 57 of 94, above 39% of the models scored.the agentic leaderboard
  1. pdf · Agents1107 Elowin rate 39.1% · source rank 33the board, 36 ranked
  2. 3D scenes · Models1073 Elowin rate 25.8% · source rank 102the board, 113 ranked
  3. Code · Models1159 Elowin rate 35.5% · source rank 81the board, 120 ranked
  4. Game development · Models1109 Elowin rate 29.8% · source rank 96the board, 120 ranked
  5. UI components · Models1199 Elowin rate 40.6% · source rank 63the board, 116 ranked
  6. Websites · Models1185 Elowin rate 39.2% · source rank 74the board, 126 ranked
Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals

Epoch AI has not placed Muse Glimmer 30B on its Capabilities Index, or places it under a name the pairing does not reach. Epoch places a model once four of its benchmarks carry a result.

Benchmark results

none of 6 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Muse Glimmer 30B under a name that matches its listing, and names are matched to the catalog exactly and never guessed. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

Source: OpenRouter (openrouter.ai/models), as of 17 Nov 16:29 UTC. sha256 0bb53a77713f over 853,270 bytes.
Catalog: OpenRouter's public model list.
Intelligence, coding and agentic indexes: Artificial Analysis, as published by OpenRouter.
Elo, win rate and rank: Design Arena, as published by OpenRouter.
Source: each model's own Hugging Face repository (huggingface.co), as of 20 Nov 2026. 162 repositories read, 4 did not answer.
Licence, parameter count, model class and gating: each model's own Hugging Face repository, the one OpenRouter names for the listing.
A licence is the tag the uploader put on the repository, read from nothing else and verified by nobody.
A parameter count is the total the repository's safetensors files declare; for a mixture of experts that is every expert, not the share one token runs through.
Vitna ran none of these evaluations and adjusted none of these figures.