AI Observatory / Model Radar
Baidu / baidu/qianfan-ocr-fast:free
Baidu: Qianfan-OCR-Fast (free)
Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR.
65,536
Context
28,672
Max output
<$0.01 / 1M
Prompt price
2026-04-20
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Baidu | Input modalities | image, text |
|---|---|---|---|
| Output modalities | text | Prompt price | <$0.01 / 1M |
| Completion price | <$0.01 / 1M | Request price | N/A |
| Context length | 65,536 | Max completion tokens | 28,672 |
| Supported parameters | frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, seed, stop, temperature, top_p | ||
Best for
baidu/qianfan-ocr-fast:free
Baidu: Qianfan-OCR-Fast (free)
Qianfan-OCR-Fast is a domain-specific multimodal large model purpose-built for OCR. By leveraging specialized OCR training data while preserving versatile multimodal intelligence, it provides a powerful performance upgrade over Qianfan-OCR.
Cross-modal work
High-volume usage
new
vision
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.