Qwen: Qwen3 VL 235B A22B Instruct

qwen/qwen3-vl-235b-a22b-instruct

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets general vision-language use (VQA, document parsing, chart/table...

Prompt $/1M

$0.210

Completion $/1M

$1.900

Context

131,072 tok

Best provider

60 tok/s · Artificial Analysis

Specs

Model id: qwen/qwen3-vl-235b-a22b-instruct
Display name: Qwen: Qwen3 VL 235B A22B Instruct
Modality: text+image->text
Tokenizer: Qwen3
Instruct type: —
Context length: 131,072
Max completion: 32,768
Prompt $/1M: $0.210
Completion $/1M: $1.900
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
Artificial Analysis	60	1,076 ms	—
Alibabafastest	25	587 ms	735 ms
AtlasCloud	20	2,576 ms	3,330 ms
DeepInfra	16	1,442 ms	2,505 ms
Venice	13	1,714 ms	2,792 ms
Novita	13	606 ms	973 ms
SiliconFlow	12	3,068 ms	3,967 ms
Parasail	8	1,395 ms	2,064 ms