DeepSeek-V3 · deepinfra

DeepSeek-V3, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token. To achieve efficient inference and cost-effective training, DeepSeek-V3 adopts Multi-head Latent Attention (MLA) and DeepSeekMoE architectures, which were thoroughly validated in DeepSeek-V2.

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 $0.32

Output, $/1M $0.89

Context 163 840

Accepts text

Last checked 04.11.2026 12:00:14 UTC

Source —