HackerNews中文版HackerNews CN
GitHubTwitter

DeepSeek v4.1 Flash 现已可供内部测试使用。

9 分•作者: dares2573•13 天前•原帖
DeepSeek V4.1 Flash 现已可供内部测试使用。它采用了新的模型架构，具备原生多模态支持、更强的能力、更快的速度和更低的成本。<p>请保持 `base_url` 不变，并将模型名称设置为 `deepseek-v4.1-flash-expires-on-0910` 以进行使用。目前定价与 `deepseek-v4-flash` 相同，账户级别的请求限制为 20 个并发请求。
查看原文
DeepSeek V4.1 Flash is now available for internal beta testing. It uses a new model architecture, with native multimodal support, stronger capabilities, faster speed, and lower cost.<p>Keep the `base_url` unchanged and set the model name to `deepseek-v4.1-flash-expires-on-0910` to use it. Pricing is currently the same as `deepseek-v4-flash`, with an account-level rate limit of 20 concurrent requests.