Published 2026-08-16 · 赵予安
Direct answer
DeepSeek V3.2 CN is listed at 0.042 / 0.064 per million tokens. Context window and CacheSafety for this exact id stay unpublished. This guide is written for Canada-based product and platform teams comparing model quality, spend, routing policy, and production rollout risk.
What shipped
Deepseek V3.2 CN is listed in the NextModel gateway catalog. The public slug is deepseek--deepseek-v3.2-cn, and the catalog model id is deepseek/deepseek-v3.2-cn. The provider is DeepSeek. The display name is Deepseek V3.2 CN. The model has streaming capability. The catalog lists Chinese as its use case.
Pricing and context
Input price is $0.042 per 1M tokens. Output price is $0.064 per 1M tokens. The latency band is 1000 to 3000 ms. Context window is unpublished in this catalog snapshot. The catalog value for context window is 0, so it should be treated as unpublished.
Related catalog entries
Deepseek V4 Flash CN is listed at $0.020 per 1M input tokens and $0.041 per 1M output tokens. Deepseek V4 PRO CN is listed at $0.239 per 1M input tokens and $0.479 per 1M output tokens.
Who this launch is for
This model is for developers who need Chinese-language output through a streaming API. It is one of the DeepSeek entries in the NextModel catalog. Teams comparing DeepSeek options can use the listed prices and latency band to narrow choices.
What is still unverified
Release date is unpublished in this catalog snapshot. Context window is unpublished. The provided notes do not include independent third-party quality scores. No first-party CacheSafety row exists for this exact model. Safe Hit, Bad Hit, and trap rates are unpublished.