deepseek-v4.1POST
OpenRouter 列出 V4.1-Flash 规格：552B 总参数，读 8B、写 16B 激活
据 OpenRouter 页面，模型为 552B 骨干，读取时激活 8B、写入时激活 16B，输入价 $0.0284/百万 token；作者追问 1M 上下文是否真有实际工作负载用得上。
perper
@perperp_er10 天前收录原推发布于 2026.10.17
perper @perperp_er原推发布于 2026.10.17
552b backbone, 8b active when reading, 16b active when writing. that's deepseek v4.1 flash per openrouter's listing, with input priced at $0.0284 per million tokens. reading a long prompt and writing the answer now cost different amounts of compute inside the same model. does anyone's real workload actually live in the 1m context window?
x.com/perperp_er/status/2111386131862606091采集于 2026.10.18 16:44