LLM ReferenceLLM Reference

Qwen3-VL-30B-A3B

qwen3-vl-30b-a3b

Researched 29d ago

Last refreshed 2026-05-11. Next refresh: weekly.

MultimodalVisionJSON / Tool use

Qwen3-VL-30B-A3B is worth evaluating for vision and json / tool use when its provider route and context window match the workload.

Decision context: Vision task fit, 2 tracked provider routes, and research from 2026-04-19.

Use it for

  • Teams evaluating vision and json / tool use
  • Buyers comparing 2 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence

Cheapest output

$0.600

Fireworks AI per 1M tokens

Provider routes

2

Tracked API hosts

Quality / dollar

Unknown

No task benchmark coverage yet

Freshness

2026-04-19

Researched 29d ago

fresh

Top use-case fit

Vision

Included by capability and metadata signals in the decision map.

JSON / Tool use

Included by capability and metadata signals in the decision map.

Provider price ladder

ProviderInput / 1MOutput / 1MRoute
Fireworks AI$0.150$0.600
Serverless
OpenRouter$0.130$1.56
Serverless

Benchmark peer barsfor Vision

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

About

Qwen3-VL-30B-A3B input tokens at $0.13/1M, output at $1.56/1M.

Capabilities

VisionMultimodalStructured Outputs

Rankings

Specifications

FamilyQwen3-VL
Released2025-01-01
Parameters30B
ArchitectureDecoder Only
Specializationmultimodal
Trainingpretrained

Created by

AI research institute of Alibaba Group.

Hangzhou, Zhejiang, China
Founded 2017
Website