Pass IndexThe State of AISign in

Qwen3.5-27B

Qwen3.5-27B is Alibaba's largest dense Qwen3.5 model, delivering near-frontier quality across reasoning, coding, and instruction following.

text + image + video → text · made by Alibaba

$0.2$1.56per Mtok in / out
Nous Research · 8 sellers

Sold by 16 ways

SellerLaneRate
Requesty aggregatornot on the seller's list todaydeepinfra flex$0.19per Mtok in$1.87per Mtok outrouter.requesty.ai · read 2026-08-25
Requesty aggregatordeepinfra$0.21per Mtok in$2.08per Mtok outrouter.requesty.ai · read 2026-09-16
Nous Research aggregatorstandard$0.2per Mtok in$1.56per Mtok outinference-api.nousresearch.com · read 2026-09-12
OpenRouter 6 ways$0.2per Mtok in$1.56per Mtok out
OpenRouter aggregatorstandard$0.2per Mtok in$1.56per Mtok outopenrouter.ai · read 2026-08-24
OpenRouter aggregatorsiliconflow/fp8$0.25per Mtok in$2per Mtok outopenrouter.ai · read 2026-08-25
OpenRouter aggregatordeepinfra/fp8$0.26per Mtok in$2.6per Mtok outopenrouter.ai · read 2026-08-25
OpenRouter aggregatoratlas-cloud/fp8$0.27per Mtok in$2.16per Mtok out$0.27per Mtok cachedopenrouter.ai · read 2026-08-25
OpenRouter aggregatornovita/bf16$0.3per Mtok in$2.4per Mtok outopenrouter.ai · read 2026-08-25
OpenRouter aggregatorphala$0.3per Mtok in$2.4per Mtok out$0.15per Mtok cachedopenrouter.ai · read 2026-08-25
SiliconFlow aggregatorstandard$0.25per Mtok in$2per Mtok outmodels.dev · read 2026-09-16
DeepInfra aggregatorstandard$0.26per Mtok in$2.6per Mtok outapi.deepinfra.com · read 2026-08-25
Hugging Face Inference Providers 3 ways$0.3per Mtok in$2.4per Mtok out
Hugging Face Inference Providers aggregatordeepinfra$0.26per Mtok in$2.6per Mtok outrouter.huggingface.co · read 2026-08-25
Hugging Face Inference Providers aggregatorstandard$0.3per Mtok in$2.4per Mtok outmodels.dev · read 2026-09-16
Hugging Face Inference Providers aggregatornovita$0.3per Mtok in$2.4per Mtok outrouter.huggingface.co · read 2026-08-25
Novita AI aggregatorstandard$0.3per Mtok in$2.4per Mtok outapi.novita.ai · read 2026-08-25
PPIO aggregatorstandard$1.8per Mtok in$14.4per Mtok outapi.ppinfra.com · read 2026-09-16

Measured 7 standings

PlaceBoardMetricScore
52ndof 60Vending bench 2 — Epoch AIScore201.976
57thof 161Dtbench — Epoch AIAccuracy82.4
57thof 123Lmca — Epoch AIScore33.98
79thof 105Vectara Hallucination LeaderboardHallucination Rate12.1
92ndof 121Webdev arena — Epoch AIArena Score1357.46
98thof 112Ale bench — Epoch AIPerformance349.45
112thof 170Weirdml — Epoch AIAccuracy39.53

About

Qwen3.5-27B — a text model from Alibaba, sold by 8 companies from $0.2 in and $1.56 out per million tokens, placed 57th of 161 on Dtbench — Epoch AI.

It takes text, images and video and returns text, with a context window of 262,144 tokens. It was published in February 2026, trained on material up to April 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under agents. Eight companies sell it. The cheapest is $0.2 in and $1.56 out per million tokens at Nous Research. Beside the standard rate there are separately routed and regional lanes. It has been measured on 7 boards, and stands best at 57th of 161 on Dtbench — Epoch AI.

Every current figure

Maker
Alibaba
Register
model
Takes
text + image + video
Returns
text
Context
262,144 tokens
Published
February 2026
Knowledge to
April 2025
Parameters
28 billion
Licence
not read
Sellers
8
Maker's own price
not read
Price
$0.2 in and $1.56 out per million tokens — Nous Research
Boards
7
Best place
57th of 161 — Dtbench — Epoch AI

Known as 3 names

Qwen/Qwen3.5-27Bdeepinfra/Qwen/Qwen3.5-27Bdeepinfra/Qwen/Qwen3.5-27B:flex