Qwen3-VL 30B-A3B Instruct
by NEAR AI Cloud · family qwen · listed Sep 2025TVW
Qwen vision-language model for visual reasoning, documents, and agent tasks
Current rates USD per 1M tokens
Input$0.15
Output$0.55
Cache read—
Cache write—
Against the market
On the record
- Model id
Qwen/Qwen3-VL-30B-A3B-Instruct- Context window
- 256K tokens
- Max output
- 33K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2025-09-23
- Last updated
- 2025-09-23
- Provider docs
- docs.near.ai/
Back of the envelope
≈
Also listed at
- Kilo Gateway$0.13 in · $0.52 out
- OpenRouter$0.13 in · $0.52 out
- NovitaAI$0.20 in · $0.70 out
- LLM Gateway$0.20 in · $0.70 out
- evroc$0.23 in · $0.92 out
- SiliconFlow (China)$0.29 in · $1.00 out
- SiliconFlow$0.29 in · $1.00 out