Get started

Qwen3.6 35B A3B

Sold by 10 sellers, timed at 50.9 tok/s, scored 41.9 on the Coding Index, and with results on 1 openly licensed board.

retrieved sha256 · 0bb53a77713f

Models/Qwen/Qwen3.6 35B A3BUSD per 1M tokens · as OpenRouter routes it
qwen/qwen3.6-35b-a3bQwen · base listing · Qwen tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.10per 1M tokens
Output$0.90per 1M tokens
Cached input$0.025per 1M tokens
Context262k262,144 tokens
What Vitna read · 3 providers, each from its own pricing page, kept as dated recordsin / out per 1M tokens
DeepInfraopen weights$0.10 / $0.10confirmed 22 Nov 2026
Parasailopen weights$0.15 / $1.00confirmed 22 Nov 2026
Novita AIopen weights$0.248 / $1.485confirmed 22 Nov 2026

The same weights served by 3 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 the list says · the fields OpenRouter publishes for this id10 fields
AuthorQwen
Listed
Canonical idqwen/qwen3.6-35b-a3b-20260415
Context262,144 tokens
Max output235,929 tokens
Modalitiestext, image, video → text
TokenizerQwen
Reasoningoptional, on by default
Moderationnot moderated by OpenRouter
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Parameters36B · 35,951,822,704 declared
Model classQwen3_5MoeForConditionalGeneration
Downloadnot gated
Published

What sellers charge

10 sellers · 4.8x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.05 at Darkbloom to $0.24 at SiliconFlow. 2 sellers undercut the $0.10 listed; 3 are dearer. A faint tick declares no number format. Every seller is named on the endpoint ledger below.

Measured speed

1,012,687 requests · 10 endpoints · 30-minute window
Throughput50.9 tok/sMedian output rate, weighted across the 10 endpoints serving it by the requests each answered.the speed board
First token771msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread20 to 68The slowest and the fastest route serving this model, in tokens per second. Speed is a property of the route, not of the weights.the board, fastest first

OpenRouter'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

10 priced · 10 timed · cheapest first
  1. Darkbloomdarkbloom/fp4$0.05$0.70$0.025fp4236k68 tok/s36906ms10,777 req99.86%
  2. DeepInfradeepinfra/fp8/flex$0.08$0.76$0.08fp866knot matchednonenonenot matched100%
  3. AkashMLakashml/fp8 · listed$0.10$0.90$0.05fp8236k23 tok/s191.4s53,305 req100%
  4. CoreWeavecoreweave/fp8 · listed$0.10$0.89$0.035fp8236k62 tok/s50499ms524,093 req99.93%
  5. DeepInfradeepinfra/fp8 · listed$0.10$0.95$0.10fp866knot matchednonenonenot matched99.71%
  6. Parasailparasail/fp8 · listed$0.10$0.90$0.025fp8236k54 tok/s37.1752ms232,176 req100%
  7. Venicevenice/fp8 · listed$0.10$1.00not listedfp866k22 tok/s18784ms129 req100%
  8. PrimeIntellectprimeintellect/fp8$0.11$1.01$0.099fp866k38 tok/s292.03s25,926 req100%
  9. DeepInfradeepinfra/fp8/priority$0.15$1.425$0.15fp866knot matchednonenonenot matched99.82%
  10. SiliconFlowsiliconflow/fp8$0.24$1.80$0.15fp8236k34 tok/s19978ms177 req94.09%
  11. DeepInfranot matchednot matchednot matchednot matchedno offer21 tok/s171.73s83,158 reqno offer
  12. DeepInfranot matchednot matchednot matchednot matchedno offer22 tok/s18774ms82,236 reqno offer
  13. DeepInfranot matchednot matchednot matchednot matchedno offer20 tok/s18573ms710 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: 7 of the 10 timed routes are slower than it, and the middle route runs at 28.5 tok/s. The widest median-to-p90 gap is Darkbloom's, 1.89x.

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 . 10 of the 13 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: AtlasCloud at 12.46% on 9 Nov 2026, SiliconFlow at 69.73% on 15 Nov 2026, DekaLLM at 78.66% on 11 Nov 2026, DeepInfra (deepinfra/fp8/flex) at 85.71% on 15 Nov 2026, and 6 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

19 parameters · 10 sellers
  1. frequency_penaltyevery seller
  2. include_reasoningevery seller
  3. max_tokensevery seller
  4. presence_penaltyevery seller
  5. reasoningevery seller
  6. temperatureevery seller
  7. top_kevery seller
  8. top_pevery seller
  9. repetition_penalty9 of 10not Venice
  10. response_format9 of 10not Venice
  11. stop9 of 10not SiliconFlow
  12. structured_outputs9 of 10not Venice
  13. seed8 of 10not SiliconFlow and Venice
  14. tool_choice8 of 10not CoreWeave and SiliconFlow
  15. tools8 of 10not CoreWeave and SiliconFlow
  16. logit_bias5 of 10
  17. logprobs4 of 10
  18. min_p4 of 10
  19. top_logprobs4 of 10

8 of these 19 are accepted by every one of the 10 sellers that publish a list; the other 11 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 models

Blended $0.30 per million tokens, 3 in to 1 out: cheaper than 246 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 board

Each 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.

Intelligence Indexnot scoredArtificial Analysis has not scored this model on its Intelligence Index.the intelligence leaderboard
Coding Index41.9Position 73 of 118, above 38% of the models scored.the coding leaderboard
Agentic Index13.1Position 56 of 94, above 40% of the models scored.the agentic leaderboard

Not ranked in any Design Arena category.

Epoch Capabilities Index · a fit by a third party over every benchmark this model has results onthe whole index, with intervals
Index144.1142.2 to 145.9
Position103 of 258above 60% of the models placed
Results behind it9benchmark results
As Epoch names itQwen 3.6 35B-A3Breleased 14 Apr 2026

Position 103 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 · 7 results
Epoch AI Benchmarking Hub · publisher-run, CC-BY-4.04 of 22 tasks

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 qwen3.6-35b-a3b_none and qwen3.6-35b-a3b, and the effort beside each score says which run it is, unstated where the publisher wrote none. A run missing from a task's rows has no published result there, which is not a score of zero. 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 Qwen3.6 35B A3B, 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; an effort that is a link opens its run's row there, where the run is ranked on Vitna's scale. Every board, with its licence and what its publisher measures, is on /benchmarks.

Sources

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.