Qwen3 Omni 30B A3B Instruct
Qwen3 Omni 30B A3B Instruct is Alibaba's language model with a 66K context window and up to 16K output tokens, starting at $0.25 / 1M input and $0.97 / 1M output. An end-to-end multilingual omni-modal LLM with 30B total and 3B activated parameters, natively processing text, images, audio, and video inputs.
| Benchmarks | |
|---|---|
| Intelligence Index | #475 |
| Math Index | #163 |
| MMLU-Pro | #207 |
| GPQA | #331 |
| HLE | #427 |
| LiveCodeBench | #182 |
| IFBench | #359 |
| Time to First Token | #491 |
| SciCode | #449 |
| AIME 2025 | #163 |
| LCR | #449 |
| TerminalBench Hard | #339 |
| TAU2 | #355 |
| Output TPS | #131 |
Capabilities
Input2/5
Text·
Image✓
Audio✓
Video·
PDF·
Output1/5
Text·
Image·
Audio✓
Video·
Embedding·
Capabilities3/13
Reasoning·
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling✓
Structured Outputs✓
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
US Dollar ($)
Per 1M tokens
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
| $0.25 | $0.97 | |
Cost Calculator
US Dollar ($)
Preset:
Cheapest Instances to Run It
Cloud GPU instances that can host Qwen3 Omni 30B A3B Instruct, ranked by cheapest on-demand price. The model needs about 72 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.
All clouds
FP16 (full precision)
US Dollar ($)
Instance | Cloud | GPU | VRAM | Price | Cheapest region | |
|---|---|---|---|---|---|---|
| Standard_NP20s |  Azure | 2× AMD Alveo U250 FPGA (64GB) | 128 GB | $3.30/hr | ||
| g7e.2xlarge |  AWS | RTX PRO Server 6000 | 96 GB | $3.36/hr | ||
| Standard_NC24ads_A100_v4 | Azure | NVIDIA A100 | 80 GB | $3.67/hr | ||