google/gemma-4-E4B-it vs PaddleOCR VL
They cost about the same for input tokens: google/gemma-4-E4B-it $0.02 per M, PaddleOCR VL $0.02 per M. PaddleOCR VL is 5× cheaper for output tokens: google/gemma-4-E4B-it costs $0.10 per M and PaddleOCR VL costs $0.02 per M. google/gemma-4-E4B-it reads more: google/gemma-4-E4B-it takes up to 131,072 tokens of context and PaddleOCR VL up to 16,384. google/gemma-4-E4B-it accepts text; PaddleOCR VL accepts image, text.
| google/gemma-4-E4B-it | PaddleOCR VL | |
|---|---|---|
| Model id | google/gemma-4-E4B-it | paddlepaddle/paddleocr-vl |
| Input | $0.02 per M | $0.02 per M |
| Output | $0.10 per M | $0.02 per M |
| Context length | 131,072 tokens | 16,384 tokens |
| Accepts | text | image, text |
| Produces | text | text |
| Served by | deepinfra | novita |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.