Qwen3 Omni 30B A3b Thinking

Qwen3 Omni 30B A3b Thinking is a text model from Novita AI with a context window of 66K tokens and max output of 16K tokens. Pricing starts at 0.25 per million input tokens and 0.97 per million output tokens (cheapest at DeepInfra).

Price Comparison by Provider

Compare prices for Qwen3 Omni 30B A3b Thinking across different providers. The same model may be available through multiple providers at different price points.

• Chart
• Table

Provider	Model Key	Input Price, $	Output Price, $
Vercel AI Gateway	vercel_ai_gateway/alibaba/qwen-3-30b	0.100	0.300
Novita AI	novita/qwen/qwen3-30b-a3b-fp8	0.090	0.450
NNebius	nebius/Qwen/Qwen3-30B-A3B	0.100	0.300
Fireworks AI	fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b	0.150	0.600
DeepInfra	deepinfra/Qwen/Qwen3-30B-A3B	0.080	0.290
DashScope (Alibaba)	dashscope/qwen3-30b-a3b	N/A	N/A

All Variants

All available versions, regions, and API endpoints for Qwen3 Omni 30B A3b Thinking.

Model Key	Provider	Mode	Input Price, $	Output Price, $	Context	Max Output	Vision	Functions
dashscope/qwen3-30b-a3b	DashScope (Alibaba)	Text	N/A	N/A	129K	16K	no	yes
deepinfra/Qwen/Qwen3-30B-A3B	DeepInfra	Text	0.080	0.290	41K	41K	no	yes
fireworks_ai/accounts/fireworks/models/qwen3-30b-a3b	Fireworks AI	Text	0.150	0.600	131K	131K	no	no
nebius/Qwen/Qwen3-30B-A3B	NNebius	Text	0.100	0.300	33K	33K	no	yes
novita/qwen/qwen3-30b-a3b-fp8	Novita AI	Text	0.090	0.450	41K	20K	no	no
novita/qwen/qwen3-omni-30b-a3b-instruct	Novita AI	Text	0.250	0.970	66K	16K	yes	yes
novita/qwen/qwen3-omni-30b-a3b-thinking	Novita AI	Text	0.250	0.970	66K	16K	yes	yes
vercel_ai_gateway/alibaba/qwen-3-30b	Vercel AI Gateway	Text	0.100	0.300	41K	16K	no	no