Beam 1.0 501B A23B
Sold by 5 sellers, timed at 417 tok/s, scored 17.7 on the Intelligence Index, and on 5 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.
What sellers charge
5 sellers · 1.6x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.25 at Nebius to $0.40 at Together. 1 seller undercuts the $0.30 listed; 3 are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
The same sellers grouped by the number format each declares, on the same scale. The fp4 group alone spans 100% of the range, so the cheap end is not cheap for its number format. A declaration is checked by nobody: this groups the rows and certifies none.
Measured speed
845 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- Nebiusnebius/fp4$0.25$1.00$0.05fp4131k193 tok/s111738ms61 req100%
- CoreWeavecoreweave/nvfp4 · listed$0.30$1.00$0.04nvfp4944k478 tok/s196266ms577 req98.75%
- BaseTenbaseten/fp4$0.40$1.20$0.04fp4131k401 tok/s170131ms8 req100%
- DigitalOceandigitalocean$0.40$1.20$0.04not declared944k138 tok/s67336ms48 req100%
- Togethertogether$0.40$1.20$0.04not declared131k365 tok/s154171ms151 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: 4 of the 5 timed routes are slower than it, and the middle route runs at 365 tok/s. The widest median-to-p90 gap is CoreWeave's, 2.44x.
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 . 6 of the 8 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: CoreWeave (coreweave/nvfp4) at 95.34% on 19 Nov 2026, DigitalOcean at 96.52% on 14 Nov 2026, Nebius (nebius/fp4) at 96.72% on 8 Nov 2026, Together at 96.94% on 19 Nov 2026, and 2 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
- response_formatevery seller
- structured_outputsevery seller
- temperatureevery seller
- top_pevery seller
- frequency_penalty4 of 5not DigitalOcean
- logprobs4 of 5not CoreWeave
- presence_penalty4 of 5not DigitalOcean
- stop4 of 5not DigitalOcean
- tool_choice4 of 5not BaseTen
- tools4 of 5not BaseTen
- top_logprobs4 of 5not CoreWeave
- repetition_penalty3 of 5not BaseTen and DigitalOcean
- top_k3 of 5not BaseTen and DigitalOcean
- logit_bias2 of 5not BaseTen, CoreWeave, and DigitalOcean
- seed2 of 5not BaseTen, DigitalOcean, and Together
- min_p1 of 5only Together
8 of these 20 are accepted by every one of the 5 sellers that publish a list; the other 12 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 $0.475 per million tokens, 3 in to 1 out: cheaper than 215 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.
- 3D scenes · Models1122 Elowin rate 33.0% · source rank 82the board, 113 ranked
- Code · Models1223 Elowin rate 43.7% · source rank 55the board, 120 ranked
- Game development · Models1187 Elowin rate 40.0% · source rank 63the board, 120 ranked
- UI components · Models1258 Elowin rate 49.0% · source rank 39the board, 116 ranked
- Websites · Models1238 Elowin rate 45.9% · source rank 50the board, 126 ranked
Epoch AI has not placed Beam 1.0 501B A23B 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 boardsNone of the 6 openly licensed boards Vitna mirrors has published a result for Beam 1.0 501B A23B 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.
Vitna ran none of these evaluations and adjusted none of these figures.
