Qwen: Qwen3.6 35B A3B

qwen/qwen3.6-35b-a3b

Qwen3.6 35B A3B is a 35B open-weight model (3B active per token), ranking #126 of 260 on the TryAii Score. Its best showing is #17 on Tau2-bench. It's served by 10 independent hosts from $0.15/$1 per million input/output tokens — a little under the going rate for its score class.

Prompt $/1M

$0.150

Completion $/1M

$1.000

Context

262,144 tok

Best provider

153 tok/s · Venice

Specs

Model id: qwen/qwen3.6-35b-a3b
Display name: Qwen: Qwen3.6 35B A3B
Modality: text+image+video->text
Tokenizer: Qwen
Instruct type: —
Context length: 262,144
Max completion: 235,929
Prompt $/1M: $0.150
Completion $/1M: $1.000
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
Venicefastest	153	677 ms	720 ms
DeepInfra	142	527 ms	691 ms
Artificial Analysis	141	1,060 ms	—
DekaLLM	121	1,246 ms	1,505 ms
AtlasCloud	115	950 ms	1,248 ms
CoreWeave	110	354 ms	403 ms
SiliconFlow	91	800 ms	1,382 ms
Parasail	80	482 ms	562 ms
AkashML	58	549 ms	641 ms
Darkbloom	38	3,444 ms	3,908 ms
Phala	35	1,076 ms	1,253 ms