Which has the larger context window, PaddlePaddle/PaddleOCR-VL-1.5 or Qwen/Qwen3.5-122B-A10B?

Qwen/Qwen3.5-122B-A10B has the larger context window (262K tokens).

PaddlePaddle/PaddleOCR-VL-1.5 vs Qwen/Qwen3.5-122B-A10B

Q: Is PaddlePaddle/PaddleOCR-VL-1.5 or Qwen/Qwen3.5-122B-A10B cheaper?

PaddlePaddle/PaddleOCR-VL-1.5 is cheaper on output tokens ($0.00 vs $2.32 per 1M).

PaddlePaddle/PaddleOCR-VL-1.5 is cheaper on output tokens, while Qwen/Qwen3.5-122B-A10B offers a larger context window. Choose PaddlePaddle/PaddleOCR-VL-1.5 or Qwen/Qwen3.5-122B-A10B based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	PaddlePaddle/PaddleOCR-VL-1.5	Qwen/Qwen3.5-122B-A10B
Provider	SiliconFlow (China)	SiliconFlow (China)
Input / 1M tokens	$0.00	$0.29
Output / 1M tokens	$0.00	$2.32
Context window	16K	262K
Parameters	—	122B
Open weights	Yes	Yes
Released	Jan 2026	Feb 2026

PaddlePaddle/PaddleOCR-VL-1.5 details →Qwen/Qwen3.5-122B-A10B details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.