Qwen3-VL 30B A3B Instruct
Text generationQwen3-VL-30B-A3B-Instruct
Qwen3-VL 30B A3B Instruct on FlexAI: Alibaba LLM, Apache 2.0 license, deployable as a dedicated FlexAI or self-hosted endpoint.
Pricing and availability
| Rate | Price |
|---|---|
| Configuration | 2× H100 |
| Endpoint rate | $8.66 / hour(for 2 GPUs at $4.33 per hour) |
| Availability | Dedicated endpoint, provisioned per customer |
Deployment requirements
- Capabilities
- Accepts image input (vendor-declared)
- API endpoint
- /v1/chat/completions
- Compatibility
- OpenAI
- Parameters
- 31.1B total / 3B active
- License
- Apache 2.0
- Hardware
- 2× H100
- GPUs to self-host
- 2× H100
- Native precision
- BF16, from torch_dtype
- Weights
- Qwen/Qwen3-VL-30B-A3B-Instruct
- Published by
- Alibaba
- Origin
- China
- Knowledge cutoff
- 2025-03-31
Qwen3-VL 30B A3B Instruct runs as a dedicated endpoint, provisioned per customer on FlexAI's infrastructure or your own, not served through the shared Token Factory API.