DeepSeek OCR · deepinfra

DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. Specifically, DeepEncoder serves as the core engine, designed to maintain low activations under high-resolution input while achieving high compression ratios to ensure an optimal and manageable number of vision tokens. Experiments show that when the number of text tokens is within 10 times that of vision tokens (i.e., a compression ratio < 10x), the model can achieve decoding (OCR) precision of 97%. Even at a compression ratio of 20x, the OCR accuracy still remains at about 60%. This shows considerable promise for research areas such as historical long-context compression and memory forgetting mechanisms in LLMs.

Base modelAll models on this baseAll models of the providerto the provider

Read also: DeepSeek API pricing: V4 Pro and V4 Flash at every provider

All DeepSeek models at every provider

Input, $/1M $0.03

Output, $/1M $0.10

Context 8 192

Accepts —

Last checked 04.11.2026 12:00:14 UTC

Source —