PaddleOCR-VL
Multimodal model for analyzing text, images, documents, and rich media
Cheapest input
$0.02
$/MTok · models.dev
Cheapest output
$0.02
$/MTok
Context
16K
tokens
Offers
4
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestpaddlepaddle/paddleocr-vl | Novita AI | $0.02 | $0.02 | $0 | 16K |
| LiteLLMnovita/paddlepaddle/paddleocr-vl | — | $0.02 | $0.02 | $0.002 | — |
| LiteLLMpaddlepaddle/paddleocr-vl | — | $0.02 | $0.02 | $0.002 | — |
| LiteLLMpaddleocr-vl | — | $0.02 | $0.02 | $0.002 | — |
Capabilities
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Released: 2025-10-22