Models

Faster, lower-cost variant of DeepSeek V4, optimized for coding assistants, high-throughput chat, and latency-sensitive Agent workflows.

Context

1M

Input / 1M tokens

¥1.008

Output / 1M tokens

¥2.016

Cache read / 1M

¥0.02016

Cache write / 1M

-

DeepSeek V4 flagship with adjustable reasoning depth, built for full-codebase analysis, multi-step automation, and complex reasoning tasks.

Context

1M

Input / 1M tokens

¥3.132

Output / 1M tokens

¥6.264

Cache read / 1M

¥0.0261

Cache write / 1M

-