DeepSeek-V3.2 · deepinfra

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training framework further improves reasoning, with reported performance in the GPT-5 class, and the model has demonstrated gold-medal results on the 2025 IMO and IOI. V3.2 also uses a large-scale agentic task synthesis pipeline to better integrate reasoning into tool-use settings, boosting compliance and generalization in interactive environments.

BasismodellAlle Modelle dieser BasisAlle Modelle des Anbieterszum Anbieter

Lesen Sie auch: DeepSeek-API-Preise: V4 Pro und V4 Flash bei jedem Anbieter

Alle DeepSeek-Modelle bei allen Anbietern

Eingabe, $/1M $0.26

Ausgabe, $/1M $0.38

Kontext 163 840

Max. Ausgabe 64 000

Akzeptiert Text

Zuletzt geprüft 04.11.2026 12:00:14 UTC

Quelle —