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。
APIPark: Offers an open-source AI gateway for unified API routing and LLM lifecycle management across developer infrastructure. APIPark 记录了 30,742 月访问量,月度环比增长为 +13.4%,定价为免费增值,定价请咨询。ApX Machine Learning 记录了 252,389 月访问量,增长率为 -6.5%,定价为免费增值。
| 维度 / 指标 | ![]() | |
|---|---|---|
| 官方域名 | apipark.com | apxml.com |
| 定价模式 | 免费增值,定价请咨询 | 免费增值 |
| 月访问量 | 3.07万 (30,742) | 25.24万 (252,389) |
| 月度环比流量变化 | +3641 (+13.4%) | -1.74万 (-6.5%) |
| 主要市场与份额 | 🇺🇸 美国 (29%) | 🇺🇸 美国 (14.2%) |
| 直接访问 / 月 | 1.24万 | 6.76万 |
| 用户评分 | 4.4 | 4.2 |
| 支持的平台 | 网站 | 网站 |

开源的 AI 网关与 API 开发者门户
把 REST API 与大模型接口发布在同一网关之后,共享认证、路由与策略执行。
在多家大模型供应商之间路由请求,支持故障转移与按成本路由,无需改动客户端接入。
为 API 使用方提供文档、密钥管理与用量看板,让集成不再依赖人工对接。
设置限流、并发上限与按调用方的配额,并把日志用量转化为账单或内部结算数据。
面向开源权重 LLM 部署的显存、吞吐与 GPU 成本计算器与课程平台
根据模型版本、上下文长度、批大小与量化精度估算权重与 KV 缓存占用,判断某块 GPU 是否真的装得下。
按硬件配置推算首字延迟与每秒 token 吞吐,帮助你按真实流量规划容量。
把显存与性能估算换算为每小时成本与单位 token 成本,便于横向比较硬件方案。
收录 500 多个模型版本与有据可查的硬件基准,让选型输入集中在一处。
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 / 开源简化在自有硬件上本地运行开源权重 LLM 的流程,但缺乏 ApX 明确的 VRAM 计算器和课程。
免费 / 开源ModelScope (魔搭社区) is an open-source AI community and model service platform that hosts thousands of pretrained models, datasets, and ready-to-run demos, backed by Alibaba Cloud infrastructure.
免费 / 开源ModelScope (魔搭社区) is an open-source AI community and model service platform that hosts thousands of pretrained models, datasets, and ready-to-run demos, backed by Alibaba Cloud infrastructure.
OrcaRouter is an OpenAI-compatible AI gateway that grades every prompt and routes it to the best-value model, then layers on failover, guardrails, an agent firewall, and compliance tooling for production AI.
OrcaRouter is an OpenAI-compatible AI gateway that grades every prompt and routes it to the best-value model, then layers on failover, guardrails, an agent firewall, and compliance tooling for production AI.

免费 / 开源Open WebUI is an open-source, self-hosted AI interface that lets individuals and organizations run any model — local or cloud — inside a workspace they fully control. It ships as a one-command install, supports Ollama, OpenAI-compatible and Anthropic endpoints, and extends through Python tools, functions and pipelines.
免费 / 开源Open WebUI is an open-source, self-hosted AI interface that lets individuals and organizations run any model — local or cloud — inside a workspace they fully control. It ships as a one-command install, supports Ollama, OpenAI-compatible and Anthropic endpoints, and extends through Python tools, functions and pipelines.

专项更强Focuses on production LLM observability and evaluation rather than foundational deployment courses or hardware cost calculators.
专项更强Focuses on production LLM observability and evaluation rather than foundational deployment courses or hardware cost calculators.