Qwen: Qwen3.5-35B-A3B

qwen/qwen3.5-35b-a3b

Qwen3.5-35B-A3B is a 35B open-weight model (3B active per token), ranking #115 of 235 on the TryAii Score. Its best showing is #32 on IFBench. It's served by 12 independent hosts from $0.25/$1.25 per million input/output tokens — about the going rate for its score class.

Prompt $/1M

$0.250

Completion $/1M

$1.250

Context

262,144 tok

Best provider

204 tok/s · CoreWeave

Specs

Model id: qwen/qwen3.5-35b-a3b
Display name: Qwen: Qwen3.5-35B-A3B
Modality: text+image+video->text
Tokenizer: Qwen3
Instruct type: —
Context length: 262,144
Max completion: 235,929
Prompt $/1M: $0.250
Completion $/1M: $1.250
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptno
Visionyes
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
CoreWeavefastest	204	275 ms	290 ms
WandBfastest	183	339 ms	353 ms
Artificial Analysis	157	1,190 ms	—
Venice	146	880 ms	991 ms
NextBit	113	705 ms	984 ms
Ambient	93	448 ms	625 ms
Alibaba	90	543 ms	602 ms
DekaLLM	79	1,165 ms	1,487 ms
SiliconFlow	78	1,364 ms	1,583 ms
DeepInfra	59	330 ms	381 ms
AkashML	55	515 ms	612 ms
AtlasCloud	43	1,090 ms	1,250 ms
Parasail	39	575 ms	659 ms
Darkbloom	13	3,689 ms	4,637 ms
qwenfastest	—	—	—