All AI models · LLM benchmarks · Methodology

PaddleOCR-VL

Multimodal model for analyzing text, images, documents, and rich media

Model facts

Context window
16K tokens
Maximum output
16K tokens
Cheapest paid input
$0.02 per 1M tokens
Cheapest paid output
$0.02 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

attachments, temperature control, open weights, text, image.

Observed price history

  • 2026-08-24: $0.02 input / $0.02 output per 1M tokens

API providers

  • NovitaAI — model id paddlepaddle/paddleocr-vl; $0.02 input / $0.02 output per 1M tokens; provider documentation