DeepSeek-V4-Flash is a highly efficient Mixture-of-Experts (MoE) language model featuring 158B total parameters with only 13B activated during inference. It utilizes a Hybrid Attention Architecture (combining Compressed Sparse Attention and Heavily Compressed Attention) to natively and efficiently support a 1-million-token context window. The model offers switchable reasoning modes (Non-think, Think High, and Think Max) and excels at high-speed generation for reasoning, coding, tool-calling, and agentic tasks.

DeepSeek-V4-Pro is a flagship Mixture-of-Experts (MoE) language model with 862B total parameters (49B activated) and a 1-million-token context window. It features a Hybrid Attention Architecture combining Compressed Sparse Attention and Heavily Compressed Attention for efficient long-context processing. With multiple distinct reasoning modes (such as Think Max for maximum reasoning effort), it is built for advanced mathematical reasoning, software engineering, tool use scenarios, and complex long-horizon agentic workflows.

Model	Category	Input	Output	Context	Pricing
DeepSeek: DeepSeek V4 Flash 0fa38dcc8d014138b2f7049951532a9e	text	text	text	1M	$0.300 in / $1.200 out
DeepSeek: DeepSeek V4 Pro b348948916bf49c58cb451cec8f119f4	text	text	text	1M	$1.320 in / $3.960 out

DeepSeek models on OneInfer

Categories

Modalities

API access

DeepSeek model catalog