Qwen: Qwen3 VL 30B A3B Instruct

GoodOpen Weight

Compare pricing across 4 providers. Cheapest: Fireworks AI at $0.263/1M tokens.

Family

qwen

Parameters

30B

Context Window

131K

Max Output

33K

Arena ELO

1140

Type

image

Provider Pricing(4 providers)

Provider	Input/1M↑	Output/1M	Cached In	Speed	TTFT	Link
Fireworks AICheapest	$0.150	$0.600	—	—	—	Use model
DeepinfraCheapest	$0.150	$0.600	—	—	—	Use model
OpenRouter	$0.156	$0.624	—	—	—	Use model
Novita AI	$0.200	$0.700	—	—	—	Use model

Model Aliases

qwen/qwen3-vl-30b-a3b-instructaccounts-fireworks-models-qwen3-vl-30b-a3b-instructaccounts/fireworks/models/qwen3-vl-30b-a3b-instruct

Try on Fireworks AI Compare with other models Estimate monthly cost

Frequently Asked Questions

The cheapest provider for Qwen: Qwen3 VL 30B A3B Instruct is currently Fireworks AI at $0.2625 per million tokens (blended rate). Prices are verified every 6 hours. Check the provider comparison table below for all available options.

Prices in USD per 1M tokens. Updated every 6 hours.