Models / Alibaba / Qwen3 VL 30B A3B Instruct
Alibaba · qwen
Qwen3 VL 30B A3B Instruct
Open vision-language MoE model for image and video understanding, documents, and visual agents
$0.15 in · $0.60 out
per 1M tokens · provider rate closest to the median. No first-party Alibaba price was listed. The reference price is Deep Infra's rate, the provider closest to the median.
Provider input prices run from $0.11 to $0.20 per 1M tokens. Output prices run from $0.43 to $0.70.
- Context
- 262,144
- Max output
- 32,768
- Cache read
- —
- Cache write
- —
- Reasoning
- No
- Tool calls
- Yes
- Structured output
- Unknown
- Vision
- Yes
- Open weights
- Yes
- License
- Apache-2.0
- Released
- Oct 4, 2025
- Updated in source
- Oct 4, 2025
- Knowledge
- —
- Providers
- 8
Providers
| Provider | Input | Output | Cache read | Cache write | Status |
|---|---|---|---|---|---|
| Merge Gateway | $0.11 | $0.43 | $0.022 | — | — |
| Deep Infrareference | $0.15 | $0.60 | — | — | — |
| Eden AI | $0.15 | $0.60 | — | — | — |
| Kilo Gateway | $0.15 | $0.60 | — | — | — |
| OpenRouter | $0.15 | $0.60 | — | — | — |
| Hugging Face | $0.20 | $0.70 | — | — | — |
| Novita AI | $0.20 | $0.70 | — | — | — |
| Prime Inference | $0.20 | $0.70 | — | — | — |
Jobs this model qualifies for
- Long-document Q&A — clears the bar
- Cheapest summarization — clears the bar