Muse Spark Open
Timed at 224 tok/s, scored 24.9 on the Intelligence Index, and on 6 Design Arena boards.
retrieved sha256 · 0bb53a77713f
The same weights served by 2 providers, each at its own list price. OpenRouter's rate is its routed rate across whichever of them it uses, and it need not match any one of them.
Measured speed
1,551 requests · 5 endpoints · 30-minute windowOpenRouter'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
5 priced · 5 timed · cheapest first- BaseTenbaseten/fp4 · listed$1.25$4.25$0.15fp4944k310 tok/s200269ms440 req100%
- Fireworksfireworks · listed$1.25$4.25$0.15not declared944k238 tok/s161290ms203 req100%
- Modalmodal · listed$1.25$4.25$0.15not declared262k279 tok/s173225ms298 req100%
- Nebiusnebius/fp4 · listed$1.25$4.25$0.15fp4944k181 tok/s133414ms113 req100%
- Togethertogether · listed$1.25$4.25$0.15not declared944k118 tok/s55465ms497 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 5 timed routes are slower than it, and the middle route runs at 238 tok/s. The widest median-to-p90 gap is Together's, 2.15x.
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 . 7 of the 7 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Fireworks (fireworks) at 5.16% on 8 Nov 2026, Fireworks (fireworks/us) at 6.01% on 8 Nov 2026, Nebius at 82.91% on 25 Oct 2026, Makora at 87.76% on 3 Nov 2026, and 3 more. 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 · 5 sellers- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- reasoning_effortevery seller
- stopevery seller
- temperatureevery seller
- tool_choiceevery seller
- toolsevery seller
- top_pevery seller
- frequency_penalty4 of 5not Modal
- logprobs4 of 5not BaseTen
- presence_penalty4 of 5not Modal
- response_format4 of 5not BaseTen
- structured_outputs4 of 5not BaseTen
- top_k4 of 5not Modal
- top_logprobs4 of 5not BaseTen
- logit_bias3 of 5not BaseTen and Modal
- repetition_penalty2 of 5not BaseTen, Modal, and Nebius
- min_p1 of 5only Together
- seed1 of 5only Nebius
9 of these 20 are accepted by every one of the 5 sellers that publish a list; the other 11 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 modelsBlended $2.00 per million tokens, 3 in to 1 out: cheaper than 99 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 boardEach 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.
- pdf · Agents1039 Elowin rate 30.4% · source rank 35the board, 36 ranked
- 3D scenes · Models1232 Elowin rate 43.0% · source rank 39the board, 113 ranked
- Code · Models1297 Elowin rate 51.0% · source rank 18the board, 120 ranked
- Game development · Models1260 Elowin rate 47.4% · source rank 30the board, 120 ranked
- UI components · Models1300 Elowin rate 49.0% · source rank 18the board, 116 ranked
- Websites · Models1305 Elowin rate 51.7% · source rank 14the board, 126 ranked
Position 44 of the 258 models Epoch has placed, which is not the population of either board above, on a scale anchored at Claude 3.5 Sonnet 130 and GPT-5 150. Epoch states that absolute values are meaningless by themselves and that comparisons between models are what the index is for, that values are not linearly related to benchmark accuracy, and that a highly specialised model may score low while being capable in its own domain.
Benchmark results
none of 6 boardsNone of the 6 openly licensed boards Vitna mirrors has published a result for Muse Spark Open 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.
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.
Source: the Epoch AI Capabilities Index (epoch.ai/eci), as of 20 Nov 2026. 258 models placed over 2917 benchmark results.
Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
Vitna ran none of these evaluations and adjusted none of these figures.
