中文X多名作者传播DeepSeek应用能力通过API向开发者开放的消息,新增讨论集中于搜索、文件处理、语音交互及OCR等接口。Max For AI称,DeepSeek发布应用API,涵盖联网搜索、深度思考搜索、文件解析、链接阅读,以及ASR、TTS和OCR等底层能力,并提到应用开源。歸藏与向阳乔木分别强调应用能力可单独调用、接口种类丰富及申请配置后台易用。这些帖子延续DeepSeek生态的API开放脉络,但接口开放与整个App源代码开源是不同事项。本批材料未附官方接口文档、开源仓库、定价或额度说明,不能确认全部开放范围、功能等价性及实际调用效果,也不能据此认定DeepSeek Harness同步新增相同功能。
DeepSeek开源推理框架DeepInfer后,中文X新增对集群吞吐、单卡收入及跨数据中心部署风险的讨论。Max For AI转述部署文档称,V4.1 Flash因KV缓存大幅压缩,可以将输入处理Prefill与输出生成Decode部署在不同数据中心,并特别提醒施工挖断光纤的风险。周先知称,相关披露包含单集群日吞吐155万亿Token、每卡每小时收入38美元;Passluo也围绕单卡收入及部分代码未开放发表评论。讨论从开源价值延伸至推理商业化与技术开放边界,但材料未附完整文档、测试条件、收入计算口径或成本数据,不能将收入等同于利润,也不能据此确认此前服务中断的原因。
Participated post:DeepSeek just open sourced its high-performance, large-scale inference framework DeepInfer in Apache-2.0 license.
https://t.co/W2cfi6O9LO
Supported features:
- Optimized kernels, model and sampler runtime
- Parallelism: Attention DP / balanced CP, MoE EP + EPLB
- DSpark and confidence-scheduled verification
- SWA bounded replay
- Asynchronous scheduling (zero-overhead batch scheduler)
- Batch-invariant inference
- Deterministic sampling
- Structured output
Participated post:Congrats to the Claude Code team on shipping Mods! A cute way to make your agent harness extensible and customizable.
It's a nice convergence of ideas: in Claude Code, mods are just plugins; and @DeepSeekHarness has been built around rethinking the concept of plugins from the very beginning.
While a subset of Claude Code features are made available as mods, in @DeepSeekHarness everything is a plugin: models, tools, skills, sessions, sandboxes, filesystems, loops, orchestration, and UI are ALL implemented as plugins, and can be mixed, matched, replaced, and extended.
In @DeepSeekHarness's Creator Mode, you can prompt the agent to inspect the live runtime, write plugins, and persist them, in order to change the UI, modify agent-loop behavior and mechanisms, and add tools or new ways of orchestration — simply everything about the agent harness can be modified on the fly and persisted.
So we've been thinking about the term https://t.co/iZMrTtTvrM for a while… Or should it be https://t.co/uK0yod3rht now? 😂