Qwen3 14B
Sold by 4 sellers, timed at 61.4 tok/s, scored 13.8 on the Coding Index, and with results on 1 openly licensed board.
retrieved sha256 · 0bb53a77713f
The same weights, served by one provider at its own list price, read from deepinfra.com. OpenRouter's rate is its routed rate across whichever sellers it uses, and the two need not agree.
What sellers charge
4 sellers · 1.88x from cheapest to dearestOne tick per seller, on a log scale of input price per million from $0.096 at DeepInfra to $0.18 at DeepInfra. 2 sellers undercut the $0.12 listed; 1 is dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.
Measured speed
1,837 requests · 4 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
4 priced · 4 timed · cheapest first- DeepInfradeepinfra/fp8/flex$0.096$0.192not listedfp837knot matchednonenonenot matched100%
- NextBitnextbit/int4$0.10$0.22not listedint437k72 tok/s56274ms478 req100%
- DeepInfradeepinfra/fp8 · listed$0.12$0.24not listedfp816knot matchednonenonenot matched98.88%
- DeepInfradeepinfra/fp8/priority$0.18$0.36not listedfp837knot matchednonenonenot matched96.41%
- DeepInfranot matchednot matchednot matchednot matchedno offer59 tok/s33461ms1,257 reqno offer
- DeepInfranot matchednot matchednot matchednot matchedno offer40 tok/s2618.2s1 reqno offer
- DeepInfranot matchednot matchednot matchednot matchedno offer41 tok/s24326ms101 reqno offer
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 4 timed routes are slower than it, and the middle route runs at 50 tok/s. The widest median-to-p90 gap is DeepInfra's, 1.79x.
DeepInfra publishes 3 offers and had 3 routes timed. The two documents share no route id, so those offers and routes are printed apart rather than paired.
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 . 3 of the 4 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: DeepInfra (deepinfra/fp8) at 94.86% on 18 Nov 2026, DeepInfra (deepinfra/fp8/flex) at 96.29% on 16 Nov 2026, and DeepInfra (deepinfra/fp8/priority) at 96.41% on 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
19 parameters · 4 sellers- frequency_penaltyevery seller
- include_reasoningevery seller
- max_tokensevery seller
- presence_penaltyevery seller
- reasoningevery seller
- repetition_penaltyevery seller
- response_formatevery seller
- seedevery seller
- stopevery seller
- structured_outputsevery seller
- temperatureevery seller
- top_pevery seller
- logit_bias3 of 4not NextBit
- min_p3 of 4not NextBit
- top_k3 of 4not NextBit
- logprobs1 of 4not DeepInfra (deepinfra/fp8), DeepInfra (deepinfra/fp8/flex), and DeepInfra (deepinfra/fp8/priority)
- tool_choice1 of 4not DeepInfra (deepinfra/fp8/flex), DeepInfra (deepinfra/fp8/priority), and NextBit
- tools1 of 4not DeepInfra (deepinfra/fp8/flex), DeepInfra (deepinfra/fp8/priority), and NextBit
- top_logprobs1 of 4not DeepInfra (deepinfra/fp8), DeepInfra (deepinfra/fp8/flex), and DeepInfra (deepinfra/fp8/priority)
12 of these 19 are accepted by every one of the 4 sellers that publish a list; the other 7 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 $0.15 per million tokens, 3 in to 1 out: cheaper than 288 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.
Not ranked in any Design Arena category.
Position 140 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
1 of 6 boards · 4 results| Task | All runs | Effort | Score |
|---|---|---|---|
| GPQA diamond | 342 | none | 0.53 |
| unstated | 0.64 | ||
| OTIS Mock AIME 2024-2025 | 319 | none | 0.26 |
| unstated | 0.66 |
Mean accuracy, 0 to 1, on the task the row names, as Epoch AI runs it and averaged over repeated runs. All eighteen of their tasks, including the held-out FrontierMath tiers, named as they name them. The model id carries the effort setting the run used. Epoch AI Benchmarking Hub names these runs qwen3-14b_none and qwen3-14b, and the effort beside each score says which run it is, unstated where the publisher wrote none. All runs is how many runs the publisher scored on the task, every model's. Read from epoch.ai ↗, which dates its own data . Epoch AI Benchmarking Hub data, by Epoch AI, under CC BY 4.0.
1 of the 6 openly licensed boards Vitna mirrors carries a result for Qwen3 14B, each printed as its publisher published it and none added to another. MTEB, LiveBench, HELM, Vectara hallucination leaderboard and Aider polyglot have not published one under a name that matches its listing, and names are matched to the catalog exactly and never guessed. A task that is a link opens its column on /capability, with every run scored on it. 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.
