Get started

Qwen3 Coder 480B A35B

Sold by 2 sellers, timed at 73.4 tok/s, on 5 Design Arena boards, and not scored by Artificial Analysis.

retrieved sha256 · 0bb53a77713f

Models/Qwen/Qwen3 Coder 480B A35BUSD per 1M tokens · as OpenRouter routes it
qwen/qwen3-coderQwen · base listing · Qwen3 tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$0.30per 1M tokens
Output$1.00per 1M tokens
Cached input$0.10per 1M tokens
Context262k262,144 tokens
What Vitna read · 3 providers, each from its own pricing page, kept as dated recordsin / out per 1M tokens
Googleopen weights$0.22 / $1.80confirmed 22 Nov 2026
AWSopen weights$0.45 / $1.80confirmed 22 Nov 2026
DeepInfraopen weights$0.30 / $1.00confirmed 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-coder-480b-a35b-07-25
Context262,144 tokens
Max output65,536 tokens
Modalitiestext → text
TokenizerQwen3
Moderationnot moderated by OpenRouter
Knowledge cutoff2025-06-30
What the weights say · read from the model's own repository on Hugging Faceretrieved from huggingface.co ↗
Parameters480B · 480,154,875,392 declared
Model classQwen3MoeForCausalLM
Downloadnot gated
Published

What sellers charge

2 sellers · 1.17x from cheapest to dearest

One tick per seller, on a log scale of input price per million from $0.30 at DeepInfra to $0.35 at Venice. The $0.30 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

986 requests · 2 endpoints · 30-minute window
Throughput73.4 tok/sMedian output rate, weighted across the 2 endpoints serving it by the requests each answered.the speed board
First token774msMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread73 to 74The 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

2 priced · 2 timed · cheapest first
  1. DeepInfradeepinfra/turbo · listed$0.30$1.00$0.10fp466k73 tok/s42.2574ms558 req96.50%
  2. Venicevenice/fp8$0.35$1.50$0.04fp866k74 tok/s381.04s428 req92.08%

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 73.5 tok/s. The widest median-to-p90 gap is Venice's, 1.95x.

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 3 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Google at 0.00% on 23 Oct 2026, Venice at 71.99% on 26 Oct 2026, and DeepInfra at 80.76% on 26 Oct 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

15 parameters · 2 sellers
  1. frequency_penaltyevery seller
  2. max_tokensevery seller
  3. presence_penaltyevery seller
  4. response_formatevery seller
  5. stopevery seller
  6. structured_outputsevery seller
  7. temperatureevery seller
  8. tool_choiceevery seller
  9. toolsevery seller
  10. top_kevery seller
  11. top_pevery seller
  12. logit_bias1 of 2not Venice
  13. min_p1 of 2not Venice
  14. repetition_penalty1 of 2not Venice
  15. seed1 of 2not Venice

11 of these 15 are accepted by every one of the 2 sellers that publish a list; the other 4 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 $0.475 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 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 Indexnot scoredArtificial Analysis has not scored this model on its Coding Index.the coding leaderboard
Agentic Indexnot scoredArtificial Analysis has not scored this model on its Agentic Index.the agentic leaderboard
  1. Code · Models1131 Elowin rate 61.2% · source rank 96the board, 120 ranked
  2. Data visualisation · Models1084 Elowin rate 54.9% · source rank 108the board, 110 ranked
  3. Game development · Models1088 Elowin rate 58.7% · source rank 102the board, 120 ranked
  4. UI components · Models1101 Elowin rate 61.4% · source rank 99the board, 116 ranked
  5. Websites · Models1149 Elowin rate 61.7% · source rank 97the board, 126 ranked
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 Coder 480B A35B 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 boards

None of the 6 openly licensed boards Vitna mirrors has published a result for Qwen3 Coder 480B A35B 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.

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.