AI 模型和平台
LongCat-2.5 带1.6T的调试机参数和原生视觉托肯
在 Google 上的首选来源中添加 Unite.AI
LongCat 推出 LongCat-2.5于2026年11月1日正式启用，是一种本土多式专家混合型模式，用于长距代理任务，总参数为1.6万亿，每令牌激活约480亿。
LongCat 称发行基于LongCat-2.0，具有更强的本土视觉理解和代理编码。 其培训内容包括更多长视轨道和大规模长视强化学习，用于复杂的密码基开发和全项目建设。 发布链接到LongCat的聊天界面和API平台，而它的GitHub和Hugging Face按钮则很快贴上标签。
视盘和Agent培训
LongCat-2.5代表视觉信号作为多级离散符号，使其主干能够以统一的符号格式处理视觉和文字输入。 设计结合了本土分辨率的视觉符号化，离线视觉预处理和与骨干共同学习的视觉嵌入。 它将残留的矢量量化应用到一个语义式和相通编码器的原生分辨率特征上，图像编码为离散符号序列，由视觉的去触控器重建。
固定的代号器允许视觉代号ID被预先计算和缓存离线，因此主干处理预tokenized序列。 由于在数据打包和打乱过程中可以知道图像计数，所以模式载荷是可以预测的，其比例在数据平行排位上可以保持大致一致。 LongCat 称在平均约有30亿个激活参数的较小的MOE上进行初步验证，显示出t-SNE可视化中相互交织的视觉和文字嵌入，建议在共享语义空间内进行整合。
对于代理编码任务，合成管道会产生培训任务，交互环境和可核查的测试。 LongCat过滤GitHub牵引请求和链接问题，使用agents对任务进行注释和合成环境，并通过故障通过和通过测试验证。 直播推出通过率指导重新贴标签和过滤，同时对假阳性和假阴性轨迹进行离线分析纠正并延长测试。 真实世界的agent故障轨迹也转化为可复制，可核查的训练任务。
在收集了整整一批之后，同步部分推出中断并节省飞行轨道，然后在下一个取样阶段恢复。 为了限制奖励黑客，LongCat在任务环境中禁用网络访问，删除Git历史和缓存文件，并使用LLM判断器来审核开发的轨迹。 附加处罚处理多回合互动中重复推理和重复的工具呼叫。
加速器培训和W4A4推论
长序训练既发生在中训期间，也发生在每台设备内存低于80GB的家用AI加速器上监督微调。 平行组跟随超节点地形学，将参数全加泰尔，专家符号全加泰尔和KV全加泰尔操作保留在其高带宽互联内。
双硬FSDP在每个超级节点内保持模型参数的硬化，同时进一步使FP32主重和优化状态跨越FSDP域。 LongCat报告在长序监督的微调任务中，每台设备的吞吐量比其DDP基线高86%.
LongCat 称的训练和推论堆栈保留了比特-等同的每托肯日志概率，其性能上下接近零，同时解开它们的平行配置。 两种引擎都使用批量-内核和对齐框架逻辑，对训练有落后的支持。
W4A4推论将专家的权重和激活量量化为4位，并在原生INT4单元上执行相应的矩阵乘法。 在专家之间进行共享输入转换后，可以在象征性复制和发送之前进行量化，在专家交流和计算过程中可以重新使用相同的INT4表示。 LongCat报告的准确性与所有评估的下游任务的未量化模型相当。
在针对W8A8 INT8基线的在线压力测试中，LongCat报告预填吞吐量增加43.3%，解码吞吐量增加42.77%，同时TTFT减少15.91%,TPOT减少19.72%。 GMM内核在W8A8上平均实现1.73×加速。
报告的评价结果
LongCat报告了长卡-2.5及其前身的基准测试结果如下：
对于视觉评价，LongCat报告了3DCode Bench Text-to-3D的55.4和Vision2Web的78.6。
除非另有说明，LongCat-2.5评价采用的是思维功能，温度为1.0，最高为0.95。 Terminal Beach v2.1使用Claude Code牵引，最大序列长度为512K，平均运行于三个独立运行。 DeepSWE v1.1使用了最大序列长度为1M的迷你-swe-agent，并且也平均在3次运行中。
使用星号标注的分数来自公共技术报告、博客文章或官方基准测试领导板。 未记分的分数是自负盈亏的，只被描述为指示性的。
API 访问和定价
API快速启动指南列出LongCat-2.5两种兼容OpenAI和Anthropic格式。 它们各自的基点分别是https://api.longcat.chat/openai和https://api.longcat.chat/anthropic，支持/v1/chat/完成和/v1/messages. 单项请求有一个1M-token上下文窗口，最大输出长度为128K令牌。
LongCat的产品页面列出了与Claude Code,Codex,Hermes和其他agent的牵引装置的兼容性。 它还描述了对视觉编码，创意设计和3D任务的支持，与复杂的代码库和全项目建设一起，涉及多步骤推理和工具使用。
现收现付定价列出的限定时间贴现率，每百万令令牌中，未预定投入为0.30美元，缓存投入为0.006美元，产出为1.20美元。 相应的人民币汇率为2元，0.04元和8元。 价格可能会发生变化，在API平台上显示的价格和计费记录都被视为权威。
由于GitHub和Hugging Face仍然在即将到来时被标记，发行时将其聊天界面和API作为可用的访问路线呈现。
本文由 AI图鉴自动抓取并翻译，版权归原作者所有；如需查看原文请点下方链接。
AI Models & Platforms
LongCat-2.5 Debuts With 1.6T Parameters and Native Visual Tokens
Add Unite.AI to your preferred sources on Google
LongCat introduced LongCat-2.5 on November 1, 2026, a natively multimodal mixture-of-experts model for long-horizon agentic tasks with 1.6 trillion total parameters and approximately 48 billion activated per token.
LongCat said the release builds on LongCat-2.0 with stronger native visual understanding and agentic coding. Its training incorporates more long-horizon trajectories and large-scale long-horizon reinforcement learning for complex codebase development and full-project builds. The release links to LongCat’s chat interface and API platform, while its GitHub and Hugging Face buttons are labelled as coming soon.
Discrete Visual Tokens and Agent Training
LongCat-2.5 represents visual signals as multi-level discrete tokens, allowing its backbone to process visual and textual inputs in a unified token-based format. The design combines native-resolution visual tokenization, offline visual preprocessing and visual embeddings learned jointly with the backbone. It applies Residual Vector Quantization to native-resolution features from a Semantic-and-Aligned Encoder, with images encoded as discrete token sequences and reconstructed by a visual de-tokenizer.
A fixed tokenizer allows visual token IDs to be precomputed and cached offline, so the backbone processes pre-tokenized sequences. Because image-token counts are known during data packing and shuffling, modality loads are predictable and their proportions can be kept approximately uniform across data-parallel ranks. LongCat said preliminary validation on a smaller MoE with approximately 3 billion activated parameters on average showed interwoven visual and textual embeddings in t-SNE visualizations, suggesting integration within a shared semantic space.
For agentic coding tasks, a synthesis pipeline generates training tasks, interactive environments and verifiable tests. LongCat filters GitHub pull requests and linked issues, uses agents to annotate tasks and synthesize environments, and validates them with fail-to-pass and pass-to-pass tests. Live rollout pass rates guide relabeling and filtering, while offline analysis of false-positive and false-negative trajectories corrects and extends the tests. Real-world agent failure trajectories are also converted into reproducible, verifiable training tasks.
Asynchronous partial rollouts interrupt and save in-flight trajectories after a full batch is collected, then resume them during the next sampling phase. To limit reward hacking, LongCat disables network access in task environments, removes Git history and cached files, and uses an LLM judge to audit trajectories for exploits. Additional penalties address repetitive reasoning and repeated tool calls during multi-turn interactions.
Accelerator Training and W4A4 Inference
Long-sequence training occurs during both mid-training and supervised fine-tuning on domestic AI accelerators with less than 80 GB of memory per device. Parallel groups follow the supernode topology, keeping parameter all-gather, expert token all-to-all and KV all-gather operations within its high-bandwidth interconnect.
Dual-shard FSDP keeps model-parameter sharding within each supernode while further sharding FP32 master weights and optimizer states across FSDP domains. LongCat reported 86% higher per-device throughput than its DDP baseline in long-sequence supervised fine-tuning tasks.
LongCat said its training and inference stack preserves bitwise-identical per-token log probabilities with near-zero performance overhead while decoupling their parallelism configurations. Both engines use batch-invariant kernels and aligned framework logic, with backward support for training.
W4A4 inference quantizes expert weights and activations to 4 bits and executes the corresponding matrix multiplications on native INT4 units. A shared input transformation across experts enables quantization before token replication and dispatch, allowing the same INT4 representation to be reused during expert communication and computation. LongCat reported accuracy comparable to the unquantized model on all evaluated downstream tasks.
In online stress tests against a W8A8 INT8 baseline, LongCat reported 43.3% higher prefill throughput and 42.77% higher decode throughput, alongside reductions of 15.91% in TTFT and 19.72% in TPOT. The GMM kernel achieved an average 1.73× speedup over W8A8.
Reported Evaluation Results
LongCat reported the following benchmark results for LongCat-2.5 and its predecessor:
For visual evaluations, LongCat reported 55.4 on 3DCodeBench Text-to-3D and 78.6 on Vision2Web.
Unless otherwise specified, the LongCat-2.5 evaluations used thinking enabled, a temperature of 1.0 and top_p of 0.95. Terminal Bench v2.1 used the Claude Code harness with a 512K maximum sequence length and was averaged over three independent runs. DeepSWE v1.1 used mini-swe-agent with a 1M maximum sequence length and was also averaged over three runs.
For other models included in LongCat’s full evaluation table, scores marked with an asterisk came from public technical reports, blog posts or official benchmark leaderboards. Unmarked scores were self-run and described as indicative only.
API Access and Pricing
The API quick-start guide lists LongCat-2.5 for both OpenAI- and Anthropic-compatible formats. Their respective base endpoints are https://api.longcat.chat/openai and https://api.longcat.chat/anthropic, supporting /v1/chat/completions and /v1/messages. A single request has a 1M-token context window and a maximum output length of 128K tokens.
The LongCat product page lists compatibility with Claude Code, Codex, Hermes and other agent harnesses. It also describes support for visual coding, creative design and 3D tasks, alongside complex codebases and full-project builds involving multi-step reasoning and tool use.
Pay-as-you-go pricing lists limited-time discounted rates per million tokens of $0.30 for uncached input, $0.006 for cached input and $1.20 for output. The corresponding yuan rates are ¥2, ¥0.04 and ¥8. Prices may change, with the prices displayed on the API platform and billing records treated as authoritative.
With GitHub and Hugging Face still marked as coming soon, the release presents its chat interface and API as the available access routes.
Auto-fetched and translated by AI Atlas. All rights belong to the original author.