by Baidu
Qianfan-OCR-Fast is a multimodal large model specialized for OCR, trained primarily on OCR-domain data while retaining appropriate general multimodal capabilities, and it outperforms Qianfan-OCR.
| Input | $0.06 / 1M tokens |
| Output | $0.25 / 1M tokens |
| Context window | 32,000 tokens |
| Modalities | text, image |
Use qianfan-ocr via the AIHubMix unified API — one interface for every major LLM.