Return to model library
Alibaba 2024-Q3
qwen-vl-max
Qwen 视觉旗舰 · OCR/图文理解 SOTA
UniversaltextVisionThought chain reasoningVisual multimodalityTool callChinese first
Data Policy: 未知 / Unknown
未经法务确认上游 ToS,不做承诺
View Alibaba terms of serviceNote: This provider's data policy is pending legal review; medical/legal customers please contact sales to confirm DPA.
context window
32K
tokens
maximum output
2K
tokens
knowledge cutoff
2024-06
Overall rating
7.86
/ 10
capability radar
code7.0
Mathematics7.5
reasoning8.5
creativity7.5
multilingual9.0
long context8.0
speed7.5
Pricing
input price$2.8/ 1M tokens
output price$2.8/ 1M tokens
* This model adopts mixed pricing (input and output have the same price)
Support features
Tool callStreaming output
Recommended scenarios
Qwen 视觉旗舰
OCR/图文理解 SOTA
Call example
Called via Nexevo.ai gateway — fully compatible with OpenAI SDK, just replace base URL
curl https://api.nexevo.ai/v1/chat/completions \
-H "Authorization: Bearer $NEXEVO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen-vl-max",
"messages": [
{ "role": "user", "content": "Hello!" }
]
}'