Inception Labs 更新 Mercury 系列扩散 LLM 产品线
Product – Blog Inception
Inception Labs 在其产品博客集中列出 Mercury 系列扩散 LLM 的进展：Mercury 2 面向搜索场景，可在既有延迟预算内为每次查询执行五十到一百次 LLM 调用；Mercury 2 用于语音智能体时 TTFT 低于 300 ms，并已上线 Azure AI Foundry。Mercury 2.5 被称为市面上能力最强的扩散 LLM，运行速度 1,107 tokens/sec，智能水平较 Mercury 2 提升 40%。此外，Mercury 2 新 API key 可获 100M 免费 tokens，速率限制提升 10 倍。
推荐理由
AI 评分 67
Inception Labs 公布 Mercury 系列扩散 LLM 的产品线，读者可了解其在搜索、语音与推理场景的速度定位。
主题
正文
当前显示原文，中文全文译文尚未就绪。
Mercury 2 for Search: Fast enough to run a hundred times per query
Mercury Voice is a diffusion LLM (dLLM) tuned to power voice agents. It reasons, calls tools, and follows long system prompts while keeping latency low enough for natural conversation.
Mercury 2.5 is the most capable diffusion LLM on the market. It runs at 1,107 tokens/sec and offers a 40% increase in intelligence over Mercury 2, comparable to cost-optimized frontier models.
Sep 8, 2026
Product
Mercury 2 for Search: Fast enough to run a hundred times per query
Mercury 2 is the fastest speed-optimized LLM in every step of the search pipeline. Fifty to a hundred LLM calls per query, inside the latency budget you already have.
Aug 11, 2026
Product
Mercury 2 for Search: Fast enough to run a hundred times per query
Mercury 2 is the fastest speed-optimized LLM in every step of the search pipeline. Fifty to a hundred LLM calls per query, inside the latency budget you already have.
Aug 11, 2026
Product
More builders. More throughput. Better Mercury 2.
The response to Mercury 2 has been bigger than we expected. Today, alongside our partners at Baseten, we're making Mercury even easier to build with: 100M free tokens for every new API key, 10x higher rate limits, and a faster, more capable model.
Jul 29, 2026
Product
More builders. More throughput. Better Mercury 2.
The response to Mercury 2 has been bigger than we expected. Today, alongside our partners at Baseten, we're making Mercury even easier to build with: 100M free tokens for every new API key, 10x higher rate limits, and a faster, more capable model.
Jul 29, 2026
Product
Mercury 2: the first reasoning model fast enough to pick up the phone
Mercury 2 brings real-time reasoning to voice agents. TTFT <300 ms on standard NVIDIA GPUs, so your agents can actually hold a conversation.
Jul 14, 2026
Product
Mercury 2: the first reasoning model fast enough to pick up the phone
Mercury 2 brings real-time reasoning to voice agents. TTFT <300 ms on standard NVIDIA GPUs, so your agents can actually hold a conversation.
Mercury 2 is now available on Azure AI Foundry, combining Inception’s diffusion architecture with Azure’s enterprise-ready infrastructure for fast, production-grade AI.
Jun 24, 2026
Product
Mercury 2 and the Rise of Real-time Subagents
Inception's diffusion LLMs power fast, parallel agent workflows in production at Augment Code
May 12, 2026
Product
Mercury 2 and the Rise of Real-time Subagents
Inception's diffusion LLMs power fast, parallel agent workflows in production at Augment Code
A next-edit diffusion LLM built for the fastest parts of your coding workflow
Mar 30, 2026
Product
We evaluated Mercury 2 on PinchBench, the open-source benchmark built on top of OpenClaw — the fastest-growing open-source project in GitHub history, with 250K+ stars in under 60 days.
Mar 24, 2026
Product
We evaluated Mercury 2 on PinchBench, the open-source benchmark built on top of OpenClaw — the fastest-growing open-source project in GitHub history, with 250K+ stars in under 60 days.
Today, we're introducing Mercury 2 — the world's fastest reasoning language model, built to make production AI feel instant.