Get started

Qwen3.8 Max (0902) (batch)

Timed at 37.6 tok/s, scored 33.7 on the Intelligence Index, and with results on 1 openly licensed board.

retrieved sha256 · 0bb53a77713f

Models/Qwen/Qwen3.8 Max (0902) (batch)USD per 1M tokens · as OpenRouter routes it
qwen/qwen3.8-max-0902:batchQwen · batch variant · Qwen tokenizer
OpenRouter list price · the routed rate, as the catalog carried itretrieved 17 Nov 16:29 UTC from openrouter.ai ↗
Input$1.15per 1M tokens
Output$3.45per 1M tokens
Cached inputnot listedper 1M tokens
Context262k262,144 tokens
What the list says · the fields OpenRouter publishes for this id11 fields
AuthorQwen
Listed
Canonical idqwen/qwen3.8-max-20260902
Context262,144 tokens
Max output131,072 tokens
Modalitiestext, image, video → text
TokenizerQwen
Reasoningalways on · effort xhigh, high, medium, low, minimal, xhigh by default
Moderationnot moderated by OpenRouter
Variantbatch
Other listingbase listing

Measured speed

3,678 requests · 2 endpoints · 30-minute window
Throughput37.6 tok/sMedian output rate, weighted across the 2 endpoints serving it by the requests each answered.the speed board
First token2.75sMedian wait before the first token, over the same window and weighted the same way.how Vitna reads a figure
Endpoint spread37 to 39The 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. Alibabaalibaba/us-east-1$2.00$6.00$0.25not declared131k39 tok/s321.8s1,192 req100%
  2. Alibabaalibaba$2.00$6.00$0.25not declared131k37 tok/s223.21s2,486 req100%

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 38 tok/s. The widest median-to-p90 gap is Alibaba's, 1.68x.

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 . 2 of the 2 sellers with a reading fell under 99% on at least one of the 23 days held, 23 Oct 2026 to 21 Nov 2026: Alibaba (alibaba/us-east-1) at 97.84% on 16 Nov 2026 and Alibaba (alibaba) at 97.97% on 15 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 · 2 sellers
  1. frequency_penaltyevery seller
  2. include_reasoningevery seller
  3. logprobsevery seller
  4. max_tokensevery seller
  5. presence_penaltyevery seller
  6. reasoningevery seller
  7. reasoning_effortevery seller
  8. response_formatevery seller
  9. seedevery seller
  10. stopevery seller
  11. structured_outputsevery seller
  12. temperatureevery seller
  13. tool_choiceevery seller
  14. toolsevery seller
  15. top_kevery seller
  16. top_logprobsevery seller
  17. top_pevery seller

All 17 are accepted by every one of the 2 sellers that publish a list. 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 $1.725 per million tokens, 3 in to 1 out: cheaper than 111 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 Index33.7Position 19 of 58, above 67% of the models scored.the intelligence leaderboard
Coding Index76.2Position 8 of 118, above 93% of the models scored.the coding leaderboard
Agentic Index56.0Position 3 of 94, above 97% 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
Index156.0153.9 to 158.3
Position42 of 258above 84% of the models placed
Results behind it9benchmark results
As Epoch names itQwen3.8 Max (0902)released 1 Sep 2026

Position 42 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 · 8 results
Epoch AI Benchmarking Hub · publisher-run, CC-BY-4.08 of 22 tasks · at xhigh 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 qwen3.8-max-0902_xhigh. 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 Qwen3.8 Max (0902) (batch), 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: 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.