Inkling 2 Small
Sold by 6 sellers, timed at 192 tok/s, and scored 30.6 on the Intelligence Index.
retrieved sha256 · 0bb53a77713f
What sellers charge
6 sellers · 2x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.15 at PrimeIntellect to $0.30 at Together. 2 sellers undercut the $0.30 listed; 0 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
14,293 requests · 6 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
6 priced · 6 timed · cheapest first- PrimeIntellectprimeintellect/fp4$0.15$0.50$0.03fp4944k157 tok/s74945ms736 req99.85%
- DeepInfradeepinfra/fp4 · 5% off$0.285$0.95$0.0285fp4944k149 tok/s98374ms8,098 req100%
- Cloudflarecloudflare · listed$0.30$1.00$0.03not declared944k262 tok/s94696ms1,527 req100%
- Modalmodal/nvfp4 · listed$0.30$1.00$0.03nvfp4131k205 tok/s67368ms430 req99.54%
- Nebiusnebius/fp4 · listed$0.30$1.00$0.06fp4944k36 tok/s21.96.68s134 req99.10%
- Togethertogether · listed$0.30$1.00$0.03not declared944k277 tok/s144296ms3,368 req99.91%
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: 3 of the 6 timed routes are slower than it, and the middle route runs at 181 tok/s. The widest median-to-p90 gap is Modal's, 3.06x.
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 . 4 of the 6 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Nebius at 92.99% on 17 Nov 2026, Together at 93.95% on 18 Nov 2026, DeepInfra at 97.79% on 13 Nov 2026, and PrimeIntellect at 97.81% on 17 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 · 6 sellers- include_reasoningevery seller
- max_tokensevery seller
- reasoningevery seller
- reasoning_effortevery seller
- response_formatevery seller
- stopevery seller
- structured_outputsevery seller
- temperatureevery seller
- toolsevery seller
- top_pevery seller
- frequency_penalty5 of 6not Modal
- logit_bias5 of 6not Modal
- logprobs5 of 6not DeepInfra
- presence_penalty5 of 6not Modal
- tool_choice5 of 6not Nebius
- top_k5 of 6not Modal
- top_logprobs5 of 6not DeepInfra
- min_p4 of 6not Modal and Nebius
- repetition_penalty4 of 6not Modal and Nebius
- seed4 of 6not Modal and Together
10 of these 20 are accepted by every one of the 6 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 $0.475 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 boardNot ranked in any Design Arena category.
Epoch AI has not placed Inkling 2 Small 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 Inkling 2 Small 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.
