Pass IndexThe State of AISign in

Qwen3.5 9B

Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture.

text + image + video → text · made by Alibaba

$0.08$0.13per Mtok in / out
Nous Research · 8 sellers

Sold by 16 ways

SellerLaneRate
Thinking Machines Lab apitraining$0.66per Mtok in$2per Mtok out$0.13per Mtok cachedtinker-docs.thinkingmachines.ai · read 2026-08-25
Nous Research 2 ways$0.08per Mtok in$0.13per Mtok out
Nous Research aggregatorstandard$0.08per Mtok in$0.13per Mtok outinference-api.nousresearch.com · read 2026-09-11
Nous Research aggregatorbatch$0.17per Mtok in$0.25per Mtok outinference-api.nousresearch.com · read 2026-09-12
OpenRouter 5 ways$0.1per Mtok in$0.15per Mtok out
OpenRouter aggregatordarkbloom/fp4$0.08per Mtok in$0.13per Mtok outopenrouter.ai · read 2026-09-08
OpenRouter aggregatorstandard$0.1per Mtok in$0.15per Mtok outopenrouter.ai · read 2026-08-24
OpenRouter aggregatorparasail/bf16$0.1per Mtok in$0.25per Mtok outopenrouter.ai · read 2026-08-25
OpenRouter aggregatorbatch$0.17per Mtok in$0.25per Mtok outopenrouter.ai · read 2026-08-29
OpenRouter aggregatortogether$0.17per Mtok in$0.25per Mtok outopenrouter.ai · read 2026-08-25
DeepInfra aggregatorstandard$0.1per Mtok in$0.15per Mtok outapi.deepinfra.com · read 2026-08-25
Hugging Face Inference Providers 4 ways$0.17per Mtok in$0.25per Mtok out
Hugging Face Inference Providers aggregatordeepinfra$0.1per Mtok in$0.15per Mtok outrouter.huggingface.co · read 2026-08-25
Hugging Face Inference Providers aggregatorovhcloud$0.12per Mtok in$0.18per Mtok outrouter.huggingface.co · read 2026-08-25
Hugging Face Inference Providers aggregatorstandard$0.17per Mtok in$0.25per Mtok outmodels.dev · read 2026-09-16
Hugging Face Inference Providers aggregatortogether$0.17per Mtok in$0.25per Mtok outrouter.huggingface.co · read 2026-08-25
SiliconFlow aggregatorstandard$0.1per Mtok in$0.15per Mtok outmodels.dev · read 2026-09-16
Venice AI aggregatorstandard$0.1per Mtok in$0.15per Mtok outmodels.dev · read 2026-09-16
Together AI aggregatorstandard$0.17per Mtok in$0.25per Mtok outdocs.together.ai · read 2026-08-24

Measured 12 standings

PlaceBoardMetricScore
24thof 32AIME 2026Accuracy (± 95% CI)92.5
79thof 123Lmca — Epoch AIScore24.47
85thof 161Dtbench — Epoch AIAccuracy71.2
122ndof 222Chess puzzles — Epoch AImean_score (none)12
124thof 177Critpt — Epoch AIAccuracy0.286
125thof 313GPQA Diamondmean_score78.977
132ndof 184Artificial Analysis · Coding IndexIndex28.7
152ndof 302Artificial Analysis · Intelligence IndexArtificial Analysis Intelligence Index14
153rdof 168Scicode — Epoch AIScore27.546
157thof 290OTIS Mock AIME 2024-2025mean_score (none)61.667
194thof 202Terminalbench — Epoch AIAccuracy mean0.092
451stof 656Epoch capabilities index — Epoch AIECI Score (none)139.46

About

Qwen3.5 9B — a text model from Alibaba, sold by 8 companies from $0.08 in and $0.13 out per million tokens, placed 125th of 313 on GPQA Diamond.

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 extract and reasoning. Eight companies sell it. The cheapest is $0.08 in and $0.13 out per million tokens at Nous Research. Beside the standard rate there are separately routed, batch and regional lanes. It has been measured on 12 boards, and stands best at 125th of 313 on GPQA Diamond.

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
9.7 billion
Licence
not read
Sellers
8
Maker's own price
not read
Price
$0.08 in and $0.13 out per million tokens — Nous Research
Boards
12
Best place
125th of 313 — GPQA Diamond

Known as 2 names

Qwen3.5-9BQwen/Qwen3.5-9B