Hy4
Sold by 2 sellers, timed at 84.2 tok/s, scored 34.6 on the Intelligence Index, and on 5 Design Arena boards.
retrieved sha256 · 0bb53a77713f
What sellers charge
2 sellers · 2x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.417 at Tencent to $0.834 at Together. The $0.417 listed is the cheapest on offer; 1 seller is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
3,573 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/fp4 · listed · 50% off$0.417$1.2505$0.021fp466k75 tok/s262.92s2,143 req100%
- Togethertogether$0.834$2.501$0.042not declared944k98 tok/s60.8841ms1,430 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 86.5 tok/s. The widest median-to-p90 gap is Tencent's, 2.88x.
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 . Every one of the 2 sellers with a reading was at 99% or better on each of the 23 days held, 23 Oct 2026 to 21 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
20 parameters · 2 sellers- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- reasoning_effortevery seller
- response_formatevery seller
- stopevery seller
- structured_outputsevery seller
- temperatureevery seller
- tool_choiceevery seller
- toolsevery seller
- frequency_penalty1 of 2not Tencent
- logit_bias1 of 2not Tencent
- logprobs1 of 2not Tencent
- max_completion_tokens1 of 2not Together
- min_p1 of 2not Tencent
- presence_penalty1 of 2not Tencent
- repetition_penalty1 of 2not Tencent
- top_k1 of 2not Tencent
- top_logprobs1 of 2not Tencent
- top_p1 of 2not Tencent
10 of these 20 are accepted by every one of the 2 sellers that publish a list; the other 10 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 $0.625 per million tokens, 3 in to 1 out: cheaper than 193 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 · Models1251 Elowin rate 47.1% · source rank 29the board, 113 ranked
- Code · Models1254 Elowin rate 47.5% · source rank 41the board, 120 ranked
- Game development · Models1278 Elowin rate 50.4% · source rank 25the board, 120 ranked
- UI components · Models1197 Elowin rate 39.4% · source rank 64the board, 116 ranked
- Websites · Models1250 Elowin rate 47.4% · source rank 43the board, 126 ranked
Epoch AI has not placed Hy4 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 Hy4 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.
