Qwen: Qwen3 VL 30B A3B Instruct

qwen/qwen3-vl-30b-a3b-instruct

Qwen3 VL 30B A3B Instruct is a 30B open-weight model (3B active per token), ranking #161 of 235 on the TryAii Score. It's served by 7 independent hosts from $0.15/$0.6 per million input/output tokens — a little under the going rate for its score class. It's on the slow side at roughly 10-22 tokens/sec.

Prompt $/1M

$0.150

Completion $/1M

$0.600

Context

262,144 tok

Best provider

51 tok/s · AtlasCloud

Specs

Model id: qwen/qwen3-vl-30b-a3b-instruct
Display name: Qwen: Qwen3 VL 30B A3B Instruct
Modality: text+image->text
Tokenizer: Qwen3
Instruct type: —
Context length: 262,144
Max completion: 16,384
Prompt $/1M: $0.150
Completion $/1M: $0.600
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
AtlasCloudfastest	51	617 ms	730 ms
Phala	27	1,312 ms	1,472 ms
Venice	21	1,758 ms	2,229 ms
DeepInfrafastest	18	347 ms	449 ms
SiliconFlow	11	2,302 ms	2,492 ms
Alibaba	10	420 ms	474 ms
Novita	8	821 ms	1,142 ms
Darkbloom	6	1,785 ms	2,511 ms
qwenfastest	—	—	—
Artificial Analysis	0	0 ms	—