Context
262K
Input
$0.15/M
Output
$0.60/M
Aliases:qwen3-vl-30b
Alibaba's Qwen3 vision-language model with 30B total / 3B active parameters. Supports text and image inputs.
deepinfra/qwen3-vl-30b-a3bQuantfp8
- Input
- $0.15/M
- Output
- $0.60/M
- Context
- 262K
- Max out
- 33K
- Caching
- Not offered
- Thinking out
- $0.60/M