Pi 编码智能体记录了 1,929,244 月访问量，月度环比增长为 +4%，定价为免费。Relace 记录了 8,865 月访问量，增长率为 -48.5%，定价为免费增值，付费。
Relace is an inference provider serving open-weight frontier models through a per-token API, known for aggressive pricing and top-tier throughput on OpenRouter.
可在终端自由重塑的极简编程智能体
用 TypeScript 扩展构建命令、工具、快捷键、浮层、子智能体或权限拦截，也可从 npm 与 git 以包形式安装。
AGENTS.md 指令、项目级 SYSTEM.md、按需技能、提示模板与可自定义压缩，让上下文窗口完全可控。
支持从 Anthropic、OpenAI 到 Bedrock、Groq、OpenRouter 与本地 Ollama 的 15+ 供应商，并可在会话中切换模型。
交互式 TUI、用于脚本的 print/JSON、面向非 Node 宿主的 RPC 协议，以及嵌入用的 SDK。
Relace is an inference provider serving open-weight frontier models through a per-token API, known for aggressive pricing and top-tier throughput on OpenRouter.
No subscription or minimum commitment — you are billed only for the input, cached input and output tokens you consume.
Reusing a cached prefix costs a fraction of the standard input price, which lowers cost for repetitive or agentic workloads.
Serve popular open models such as DeepSeek, Kimi and GLM families through one consistent endpoint.
Optimized scheduling and GPU utilization help Relace rank among the top providers by daily token volume on OpenRouter.
免费 / 开源由 DeepSeek-V4 与 R1 驱动的高效开源权重与托管推理 AI，token 成本极低。
免费 / 开源The industry-standard source code editor with flexible plugin support, requiring extensions for advanced agentic coding.
专项更强An autonomous software engineer that handles end-to-end repository tasks, but operates as a cloud service rather than locally.
一款以终端机为先的 AI 编码代理，针对开放权重模型进行了优化，提供类似的命令行开发者体验。
Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.
Together AI is the AI Native Cloud — a full-stack platform for running, fine-tuning and training open-source models. It spans serverless inference APIs, dedicated endpoints, GPU clusters, post-training and storage, all backed by in-house systems research.
免费 / 开源Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.
免费 / 开源Unsloth is an open-source toolkit for running and training large language models locally. It provides faster, more memory-efficient fine-tuning, a local chat and agent environment with browser use, image and video generation, and an OpenAI-compatible API your existing tools can connect to.
高可信前沿推理，端到端加密
