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

-

Flash tier of GLM-5.3: native multimodal inputs, suited for efficient coding and long-horizon agents with stable long-context behavior in production.

Context

1M

Input / 1M tokens

¥0.792

Output / 1M tokens

¥2.808

Cache read / 1M

¥0.2304

Cache write / 1M

-

Flash tier of GLM-5.3: native multimodal inputs, suited for efficient coding and long-horizon agents with stable long-context behavior in production.

Context

1M

Input / 1M tokens

¥0.792

Output / 1M tokens

¥2.808

Cache read / 1M

¥0.2304

Cache write / 1M

-