Last refreshed 2026-06-29. Next refresh: weekly.
Why use Qwen3 Omni 30B A3B on Novita AI?
Novita AI offers Qwen3 Omni 30B A3B with pay-as-you-go pricing at $0.25/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.
Input / 1M
$0.25
Output / 1M
$0.97
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: qwen3-omni-30b-a3b-instructModel ID
qwen3-omni-30b-a3b-instructRequest example
Curated snippets for this provider have not been sourced yet.
Gotchas
- Use provider model ID "qwen3-omni-30b-a3b-instruct", not the LLMReference slug "qwen3-omni-30b-a3b".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.25 |
| Output tokens | $0.97 |
Capabilities
VisionMultimodalReasoningJSON / Tool useStructured OutputsAudio
About Qwen3 Omni 30B A3B
Qwen3 Omni 30B A3B is Alibaba's natively end-to-end omnimodal MoE model from the Qwen3 generation, capable of processing text, audio, images, and video while generating real-time streaming text and speech responses. Achieves SOTA on 22 of 36 audio/video benchmarks and open-source SOTA on 32 of 36. Available in Instruct and Thinking (reasoning) variants. Released September 22, 2025.
Get Started
Model Specs
Released2025-09-22
Parameters30B total / 3B active
Context66k
ArchitectureMixture of Experts