Qwen: Qwen3 VL 235B A22B Instruct

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

Qwen3 VL 235B A22B Instruct is an open-weight heavyweight from Qwen — 235B parameters with 22B active per token, ranking #156 of 260 on the TryAii Score. Its best showing is #30 on AIME-2025. API pricing starts at $0.21/$1.9 per million input/output tokens, though similar scores now sell for about $1.2 per million output tokens, with 3 independent hosts serving it. It's on the slow side at roughly 16-26 tokens/sec.

Prompt $/1M

$0.210

Completion $/1M

$1.900

Context

262,144 tok

Best provider

32 tok/s · Parasail

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: 262,144
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
Parasailfastest	32	1,157 ms	1,450 ms
Venice	20	1,797 ms	2,171 ms
DeepInfra	12	3,374 ms	6,961 ms