Model Positioning
Qianfan-EngCard-VL is Baidu's domain-specialized image understanding model for educational scenarios. Baidu Qianfan lists it as an image understanding model in the Inference Service API V2. (cloud.baidu.com)
Capabilities and Uses
For the fill-in-the-blank sections of English answer sheets that have already been segmented into regions, the model can automatically recognize answers in the original question order, making it suitable for assisting with teaching assessment. (qianfan.cloud.baidu.com)
Limitations
The officially described applicable input is the fill-in-the-blank section of English answer sheets that has already been segmented into regions; this does not establish that the model supports automatic question segmentation of entire answer sheets or other question types. Parameter count, context length, accuracy, and output format have not been verified.
Release Date
On August 28, 2025, the Baidu Qianfan model update record listed the model as newly added. (cloud.baidu.com)
Pricing
As of November 18, 2026, Baidu AI Cloud's domestic pricing documentation and international pricing page were checked, but no official pricing for this model was verified in either source; the amounts and units charged for input and output have not been verified. Prices for other models cannot be applied to this model. (cloud.baidu.com)
Official Sources
- Baidu Qianfan model update record
- Baidu Qianfan community product update announcement
- Original Baidu model update record link provided in the input: direct retrieval timed out on this occasion; the Baidu AI Cloud update record above contains the corresponding entry for this model.
- Pricing checks: Baidu AI Cloud domestic pricing documentation; Baidu AI Cloud international pricing page.