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.

Modèle de baseTous les modèles de cette baseTous les modèles du fournisseurvers le fournisseur

À lire aussi : Prix de l'API DeepSeek : V4 Pro et V4 Flash chez chaque fournisseur

Tous les modèles DeepSeek chez tous les fournisseurs

Entrée, $/1M $0.03

Sortie, $/1M $0.10

Contexte 8 192

Accepte —

Dernière vérification 04.11.2026 12:00:14 UTC

Source —