Hy3
Sold by 2 sellers, timed at 50.5 tok/s, on 6 Design Arena boards, and not scored by Artificial Analysis.
retrieved sha256 · 0bb53a77713f
The same weights, served by one provider at its own list price, read from novita.ai. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.
What sellers charge
2 sellers · 1.06x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.132 at Tencent to $0.14 at Novita. The $0.0825 listed is the cheapest on offer; 2 sellers are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
3,607 requests · 2 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
2 priced · 2 timed · cheapest first- Tencenttencent/fp8$0.132$0.528$0.033fp8128k51 tok/s271.78s2,657 req100%
- Novitanovita$0.14$0.58$0.035not declared236k49 tok/s203.49s950 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: 1 of the 2 timed routes are slower than it, and the middle route runs at 50 tok/s. The widest median-to-p90 gap is Novita's, 2.45x.
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 . 2 of the 5 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Phala at 98.75% on 4 Nov 2026 and AtlasCloud at 98.80% on 4 Nov 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
17 parameters · 2 sellers- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- reasoning_effortevery seller
- stopevery seller
- structured_outputsevery seller
- temperatureevery seller
- tool_choiceevery seller
- toolsevery seller
- frequency_penalty1 of 2not Tencent
- max_completion_tokens1 of 2not Novita
- presence_penalty1 of 2not Tencent
- repetition_penalty1 of 2not Tencent
- response_format1 of 2not Novita
- seed1 of 2not Tencent
- top_k1 of 2not Tencent
- top_p1 of 2not Tencent
9 of these 17 are accepted by every one of the 2 sellers that publish a list; the other 8 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 $0.144 per million tokens, 3 in to 1 out: cheaper than 292 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 · Models1154 Elowin rate 43.8% · source rank 68the board, 113 ranked
- Code · Models1164 Elowin rate 41.1% · source rank 77the board, 120 ranked
- Data visualisation · Models1121 Elowin rate 36.1% · source rank 97the board, 110 ranked
- Game development · Models1125 Elowin rate 38.6% · source rank 90the board, 120 ranked
- UI components · Models1152 Elowin rate 40.2% · source rank 83the board, 116 ranked
- Websites · Models1172 Elowin rate 41.3% · source rank 82the board, 126 ranked
Epoch AI has not placed Hy3 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 Hy3 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.
