模型目錄列出甚麼？

目錄列出支援的 AI 模型 API，包括供應商、模態、model ID、能力、價格與可安裝 model skill。

可以用一組 key 呼叫不同供應商嗎？

可以。一組 RunAPI key 可用於支援的影片、圖片、音樂、音訊與 LLM 模型。

我需要每個 provider 都開一個獨立帳戶嗎？

不用 — 一個 RunAPI key 即可解鎖整個 catalog，付款統一計算。

收費如何計算？

按每次呼叫或每單位計量，每月以 USD 結算。失敗的生成不會收費。

我可以自行架設 SDK 嗎？

npm、pip 同 RubyGems 上的 SDK 套件均採用 MIT 授權。

API 問題要回報到哪裡？

到公開 GitHub repo 開 issue，或聯絡支援。

模型目錄

探索 264 個 AI 模型

透過一個統一的 API，瀏覽、比較並整合用於影片、圖像、音樂、音訊和文字生成的頂尖 AI 模型。

取得 API Key 閱讀文件

所有模型均可用 · 即時定價

# Available Endpoints
POST /v1/chat/completions # LLM
POST /v1/images/generations # Image
POST /api/v1/kling/text_to_video # Video
POST /v1/audio/speech # TTS
POST /v1/audio/transcriptions # STT
POST /api/v1/suno/text_to_music # Music

const response = await fetch("https://runapi.ai/v1/chat/completions", {
  method: "POST",
  headers: { Authorization: `Bearer ${RUNAPI_API_KEY}`, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "your-model-id", messages: [{ role: "user", content: "Hello" }] })
})
const result = await response.json()

import os
import httpx

response = httpx.post(
    "https://runapi.ai/v1/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['RUNAPI_API_KEY']}"},
    json={"model": "your-model-id", "messages": [{"role": "user", "content": "Hello"}]}
)

<?php
$ch = curl_init("https://runapi.ai/v1/chat/completions");
curl_setopt_array($ch, [CURLOPT_POST => true, CURLOPT_RETURNTRANSFER => true,
  CURLOPT_HTTPHEADER => ["Authorization: Bearer $RUNAPI_API_KEY", "Content-Type: application/json"],
  CURLOPT_POSTFIELDS => json_encode(["model" => "your-model-id", "messages" => [["role" => "user", "content" => "Hello"]])]);
$result = json_decode(curl_exec($ch), true);

HttpClient client = HttpClient.newHttpClient();
HttpRequest request = HttpRequest.newBuilder(URI.create("https://runapi.ai/v1/chat/completions"))
  .header("Authorization", "Bearer " + RUNAPI_API_KEY)
  .header("Content-Type", "application/json")
  .POST(HttpRequest.BodyPublishers.ofString("{\"model\":\"your-model-id\",\"messages\":[]}")).build();
HttpResponse<String> response = client.send(request, HttpResponse.BodyHandlers.ofString());

require "net/http"
uri = URI("https://runapi.ai/v1/chat/completions")
request = Net::HTTP::Post.new(uri)
request["Authorization"] = "Bearer #{ENV.fetch('RUNAPI_API_KEY')}"
request["Content-Type"] = "application/json"
request.body = {model: "your-model-id", messages: []}.to_json

requestBody := strings.NewReader(`{"model":"your-model-id","messages":[]}`)
request, _ := http.NewRequest(http.MethodPost, "https://runapi.ai/v1/chat/completions", requestBody)
request.Header.Set("Authorization", "Bearer "+os.Getenv("RUNAPI_API_KEY"))
request.Header.Set("Content-Type", "application/json")
response, err := http.DefaultClient.Do(request)
defer response.Body.Close()

# Authenticate once
runapi login

# Inspect available models
runapi models list --modality video

# Use the selected model in your workflow
runapi models show <model-id>

一個 API，接入主流 AI 模型