智能体
www.aibase.com ·
DeepSeek-V4.1-Flash 上线千问 AI 平台，API 与 Token Plan 同步开放
据 AIbase 报道，DeepSeek-V4.1-Flash 已在千问 AI 平台上线，开放 API 与 Token Plan，可在 Qoder、Qwen APP、Codex 等工具中用于代码、文档、视觉理解和 Agent 任务。该模型采用 MoE 架构，总参数 552B，Causal-Encoder-Decoder 非对称结构，输入激活约 8B、输出激活约 16B，原生支持文本与图像理解，最大上下文 100 万 token，最大输出约 393K。官方称其在多项 Agent 与代码基准上较前代明显提升。成本方面，新一代缓存压缩将 KV Cache 的 HBM 需求降至前代四分之一、SSD 存储降至八分之一；千问页面按时段定价：闲时输入 1 元/百万 token、输出 4 元，忙时分别为 2 元和 8 元，限流 15K RPM、1M TPM，支持前缀补全、函数调用、缓存、结构化输出、批量任务和联网搜索。阿里云百炼与 vLLM 社区完成适配，覆盖北京、新加坡及美国、德国、日本、香港等区域。
AI推荐理由 内容给出 DeepSeek-V4.1-Flash 在千问 AI 平台上线、API 与 Token Plan 开放的具体信息，包括 552B 总参数 MoE、约 8B 输入激活/16B 输出激活、100 万 token 上下文、约 393K 最大输出、KV Cache 压缩至前代 HBM 四分之一与 SSD 八分之一，以及分时定价（闲时输入 1 元/百万 token、输出 4 元；忙时 2 元/8 元）和 15K RPM、1M TPM 限流。这些参数与价格对开发者和 Agent 长上下文落地有参考价值。但来源为 AIbase 转述平台公告，未提供官方链接或可验证基准数据，'显著提升'等表述缺乏具体数字，且发布时间为 2026 年，需以官方发布为准。
72
正文
DeepSeek-V4.1-Flash Launches on Qwen AI Platform, API and Token Plan Opened Simultaneously
AIbase基地
Published inAI News · 4 min read · Sep 14, 2026
5
DeepSeek-V4.1-Flash has recently been launched on the Qwen AI platform, with API services and Token Plan now available. Developers can integrate the model into their systems via standard APIs, or directly use the Token Plan in tools such as Qoder, Qwen APP, and Codex for code, documentation, visual understanding, and agent tasks.
According to the platform announcement, this model is DeepSeek's new lightweight flagship, featuring a MoE architecture with 552B total parameters, using a Causal-Encoder-Decoder asymmetric structure, with input activation of about 8B and output activation of about 16B; it natively supports text and image understanding, with a maximum context length of 1 million tokens, and a maximum output of approximately 393K. The official stated that it has improved significantly over its predecessor in several Agent and code benchmarks, achieving high throughput and low latency with lower activation parameters.
The cost side is a major focus of this release. The new generation of cache compression reduces the KV Cache demand for HBM to one-quarter of the previous generation and for SSD storage to one-eighth, saving more resources for long contexts and multi-turn tool calls. The Qwen page provides time-based pricing: 1 yuan per million tokens during off-peak hours for input and 4 yuan per million tokens for output; 2 yuan and 8 yuan respectively during peak hours. The rate limits are 15K RPM and 1M TPM, covering features such as prefix completion, function calls, caching, structured output, batch tasks, and online search.
In terms of deployment, Alibaba Cloud BaiLian has collaborated with the vLLM open-source community to complete the adaptation, making it accessible on both the China site and international site, covering regions including Beijing, Singapore, and Global locations such as the United States, Germany, Japan, and Hong Kong. According to BaiLian documentation, the model supports multi-turn conversations, function calls, online search, context caching, and structured output, with a max_tokens limit of approximately 393,216, making it suitable for enterprises to migrate tasks such as long document parsing, customer service knowledge base, code repository Q&A, and multimodal order review to a single interface.
Industry experts believe that by incorporating the combination of "large parameters, small activation, strong caching" into the Qwen ecosystem, V4.1-Flash will reduce the trial and error costs of long-context agents; for small teams, the low off-peak price combined with the Token Plan subscription allows for more flexible batch inference and prototype validation.
DeepSeek-V4.1-FlashQwen AI PlatformTokenPlanCodeBaseline
This article is from AIbase Daily
Scan to view
Welcome to the [AI Daily] column! This is your daily guide to exploring the world of artificial intelligence. Every day, we present you with hot topics in the AI field, focusing on developers, helping you understand technical trends, and learning about innovative AI product applications.
—— Created by the AIbase Daily Team
© Copyright AIbase Base 2024, Click to View Source -