Get started

Qwen3.5-122B-A10B

Sold by 3 sellers, timed at 106 tok/s, scored 45.7 on the Coding Index, and with results on 1 openly licensed board.

retrieved sha256 · 0bb53a77713f

Models/Qwen/Qwen3.5-122B-A10BUSD per 1M tokens · as OpenRouter routes it
qwen/qwen3.5-122b-a10bQwen · base listing · Qwen3 tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.26per 1M tokens
Output$2.08per 1M tokens
Cached inputnot listedper 1M tokens
Context262k262,144 tokens
What Vitna read · the provider's own pricing page, kept as a dated recordin / out per 1M tokens
Novita AIopen weights$0.40 / $3.20confirmed 22 Nov 2026

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 the list says · the fields OpenRouter publishes for this id10 fields
AuthorQwen
Listed
Canonical idqwen/qwen3.5-122b-a10b-20260224
Context262,144 tokens
Max output65,536 tokens
Modalitiestext, image, video → text
TokenizerQwen3
Reasoningoptional
Moderationnot moderated by OpenRouter
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Parameters125B · 125,086,497,008 declared
Model classQwen3_5MoeForConditionalGeneration
Downloadnot gated
Published

What sellers charge

3 sellers · 1.54x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.26 at Alibaba to $0.40 at Novita. The $0.26 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

2,086 requests · 3 endpoints · 30-minute window
Throughput106 tok/sMedian output rate, weighted across the 3 endpoints serving it by the requests each answered.the speed board
First token763msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread46 to 110The 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

3 priced · 3 timed · cheapest first
  1. Alibabaalibaba · listed$0.26$2.08not listednot declared66k110 tok/s24594ms1,419 req100%
  2. SiliconFlowsiliconflow/fp8 · listed$0.26$2.08not listedfp8236k46 tok/s30891ms91 req96.09%
  3. Novitanovita/bf16$0.40$3.20not listedbf1666k106 tok/s681.16s576 req98.76%

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: 2 of the 3 timed routes are slower than it, and the middle route runs at 106 tok/s. The widest median-to-p90 gap is Alibaba's, 4.58x.

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 4 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 56.74% on 25 Oct 2026, SiliconFlow at 79.78% on 25 Oct 2026, Alibaba at 95.09% on 6 Nov 2026, and Novita at 98.60% on 14 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 · 3 sellers
  1. frequency_penaltyevery seller
  2. include_reasoningevery seller
  3. max_tokensevery seller
  4. presence_penaltyevery seller
  5. reasoningevery seller
  6. response_formatevery seller
  7. temperatureevery seller
  8. top_kevery seller
  9. top_pevery seller
  10. logprobs2 of 3not SiliconFlow
  11. repetition_penalty2 of 3not Alibaba
  12. seed2 of 3not SiliconFlow
  13. stop2 of 3not SiliconFlow
  14. structured_outputs2 of 3not Novita
  15. tool_choice2 of 3not SiliconFlow
  16. tools2 of 3not SiliconFlow
  17. top_logprobs2 of 3not SiliconFlow

9 of these 17 are accepted by every one of the 3 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 models

Blended $0.715 per million tokens, 3 in to 1 out: cheaper than 181 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 Index45.7Position 65 of 118, above 45% of the models scored.the coding leaderboard
Agentic Index7.6Position 61 of 94, above 35% 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

Epoch AI has not placed Qwen3.5-122B-A10B 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

1 of 6 boards · 1 result
Epoch AI Benchmarking Hub · publisher-run, CC-BY-4.01 of 22 tasks · 149 runs scored on the task · at none effort

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 this run qwen3.5-122b-a10b_none. 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 Qwen3.5-122B-A10B, 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.

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.
Vitna ran none of these evaluations and adjusted none of these figures.