Last refreshed 2026-06-29. Next refresh: weekly.
Why use Qwen3-30B-A3B on Novita AI?
Novita AI offers Qwen3-30B-A3B with pay-as-you-go pricing at $0.09/1M 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.
Compare Qwen3-30B-A3B across 7 providers to find the best fit for your use caseInput / 1M
$0.090
Output / 1M
$0.45
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: qwen3-30b-a3b-fp8Model ID
qwen3-30b-a3b-fp8Request example
Curated snippets for this provider have not been sourced yet.
Gotchas
- Use provider model ID "qwen3-30b-a3b-fp8", not the LLMReference slug "qwen3-30b-a3b".
Compare Qwen3-30B-A3B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | $0.05 | $0.34 |
| OpenRouter | $0.08 | $0.28 |
| Fireworks AI | $0.50 | $0.50 |
| AWS Bedrock | $0.10 | $0.30 |
| Vercel AI Gateway | $0.08 | $0.29 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.09 |
| Output tokens | $0.45 |
Capabilities
Structured Outputs
About Qwen3-30B-A3B
Alibaba's Qwen3-30B with 3B active parameters via mixture-of-experts architecture. Delivers strong performance with efficient inference on Cloudflare Workers AI platform.
Get Started
Model Specs
Released2025-04-28
Parameters30B
Context128k
ArchitectureMixture of Experts