Qwen3 VL 30B A3B Instruct is
Alibaba's language model with a 262K context window and up to 33K output tokens, available from 4 providers, starting at $0.130 / 1M input and $0.520 / 1M output. An instruction-tuned MoE vision-language model with 30B total and 3B active parameters, optimized for general multimodal instruction following across images and video.
alibaba-qwen3-vl-30b-a3b-instruct |
| Language |
| Active |
| 262K tokens |
| 33K tokens |
| ImageText |
| Text |
| 30B |
| · 6 months ago |
16.1#166 |
14.3#142 |
72.3#47 |
0.8#96 |
0.7#106 |
0.1#117 |
0.5#94 |
0.3#185 |
1.17s#252 |
0.3#127 |
0.7#47 |
0.2#135 |
0.1#140 |
0.2#197 |
126.1#65 |
Capabilities
Input2/5
✓
✓
·
·
·
Output1/5
✓
·
·
·
·
Capabilities3/13
·
·
✓
✓
✓
·
·
·
·
·
·
·
·
Pricing by Provider
| Provider | Standard | Batch | ||
|---|---|---|---|---|
| Input $ / 1M | Output $ / 1M | Input $ / 1M | Output $ / 1M | |
OpenRouter | $0.130 | $0.520 | — | — |
Fireworks AI | $0.150 | $0.600 | — | — |
Alibaba Qwen | $0.200 | $0.800 | $0.100 | $0.400 |
Novita | $0.200 | $0.700 | — | — |
Cost Calculator
Preset:
Compares every provider & tier in USD
Versions
| Version | Released | Context | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|---|
| Qwen3 VL 30B A3B Instruct | 262K | $0.130 | $0.520 | Current | |
| Qwen3 VL 30B A3B Thinking | 262K | $0.130 | $0.600 | Available | |
| Qwen3 VL 235B A22B Instruct | 262K | $0.200 | $0.880 | Available | |
| Qwen3 VL 235B A22B Thinking | 262K | $0.220 | $0.880 | Available |
HuggingFace
562 likes3,045,246 downloads/month14,017,745 total downloads