
Runware is an AI inference platform that exposes an enormous model catalog — images, video, audio, LLMs and 3D — through a single API endpoint, alongside serverless GPU compute and reserved capacity running on modular data centers the company designs and operates itself. It is aimed at developers and product teams who want to ship generative features without managing infrastructure.
| 面向/指標 | ![]() | |
|---|---|---|
| 官方網域 | janitorai.com | runware.ai |
| 定價模式 | 免費增值 | 付費 |
| 每月造訪次數 | 1.25億 (125,494,484) | 40.29萬 (402,862) |
| 月流量變化量 | -677.05萬 (-5.1%) | +8.58萬 (+27.1%) |
| 主要市場與市佔 | 🇺🇸 美國 (38.7%) | 🇺🇸 美國 (27.3%) |
| 每月直接造訪 | 8952.77萬 | 18.98萬 |
| 使用者評分 | 4.2 | 4.5 |
| 支援平台 | 網站 | 網站 |
可自訂的 AI 角色扮演平台,提供免費 JanitorLLM 聊天、邏輯腳本與多模型 API 路由。
提供由 JanitorAI 自有 LLM 驅動的無限免費角色聊天(免費帳號約 9K 上下文視窗),並有可切換的 JLLM-short 模式,用於產生短約 70%、節奏更快的對話式回覆。
讓 Janitor+ 訂閱者透過內建的按 token 錢包以 10% 折扣直接使用第三方前沿模型,同時保留完整的 BYOK 反向代理支援,並具備設定複製與推理標籤顯示。
允許創作者建構最大 1 MB 的複雜角色,包含多個開場情境,以及可用全字比對與內建除錯工具觸發動態設定或行為規則的可程式化 Scripts。
在聊天選單中公開底層取樣參數,包括自訂 Top-K、Top-P、頻率與重複懲罰、禁用詞彙清單以及回覆預填指令。

Runware is an AI inference platform that exposes an enormous model catalog — images, video, audio, LLMs and 3D — through a single API endpoint, alongside serverless GPU compute and reserved capacity running on modular data centers the company designs and operates itself. It is aimed at developers and product teams who want to ship generative features without managing infrastructure.
Image, video, audio, LLM and 3D tasks all POST to a single endpoint as an array, so mixed-modality batches can travel in one request with shared auth and billing.
Browse hosted, partner and community models through one addressing scheme, control parameters such as stacked LoRAs and swapped VAEs on open models, and add your own uploads.
Bring your own container and weights to serverless GPUs billed by the second that scale to zero when idle, or commit to reserved capacity and bare-metal clusters for a lower per-hour rate.
Purpose-built modular data centers plus an orchestration layer that keeps weights preloaded across regions and routes requests to pods that already hold the model in memory.

Features massive user-generated persona libraries with voice playback for casual character chatting.

Combines adult-focused character chat, storytelling, and image generation for creative roleplay users.
Combines adult-focused character chat, storytelling, and image generation for creative roleplay users.

免費 / 開源Provides privacy-focused, uncensored open-source model APIs that advanced users can route for private roleplay.
提供無限制的動漫與奇幻角色聊天,符合 JanitorAI 寬鬆的內容政策。

專項更強RunningHub is a cloud platform for running ComfyUI workflows online, building AI apps, and generating images and videos with hosted models and APIs.
專項更強RunningHub is a cloud platform for running ComfyUI workflows online, building AI apps, and generating images and videos with hosted models and APIs.

提供類似的開發者優先雲端平台以進行超快速生成式多媒體推理,但定價級別有所不同。
Enables custom persona creation and open-ended roleplay adventures in a similar community environment.
An independent platform for custom character creation and open-ended roleplay sessions with minimal restrictions.