Qianfan OCR Fast
DeprecatesQianfan OCR Fast is Baidu's image to text model with a 66K context window and up to 29K output tokens, starting at $0.680 / 1M input and $2.81 / 1M output. A domain-specific multimodal OCR model on Baidu's Qianfan platform, purpose-built for fast and accurate text recognition from images.
baidu-ocr-fast |
| Image to Text |
| Deprecating |
| Baidu |
| 66K tokens |
| 29K tokens |
| ImageText |
| Text |
| default |
| · 1 month ago |
Capabilities
Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities1/13
Reasoning✓
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·
Pricing by Provider
| Provider | Standard | |
|---|---|---|
| Input $ / 1M | Output $ / 1M | |
 OpenRouter | $0.680 | $2.81 |
Cost Calculator
Preset:
Other models
| Model | Tier | Released | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|---|
| DeepSeek-OCR 2 | — | — | — | — | — |
| DeepSeek-OCR | — | — | 8K | $0.030 | $0.030 |
| DeepSeek-OCR | — | — | — | — | — |
| Document OCR | — | — | — | — | — |
| Mistral OCR | — | — | — | $2.00 | $3.00 |
| OCR | — | — | — | — | — |
| Prebuilt Document | — | — | — | — | — |
| Prebuilt Layout | — | — | — | — | — |
| Prebuilt Read | — | — | — | — | — |