Google AI 模型
Veo 3, Imagen 4, Nano Banana, and Gemini — Google's full stack from video generation to multimodal reasoning.
Google offers frontier models spanning video (Veo 3 with synchronized audio), image (Imagen 4, Nano Banana), and language (Gemini multimodal LLMs). Through RunAPI, the entire Google AI stack shares a single key.
- 單一 API key 可跨 provider 共用
- Model skill 將文件與 schema 帶入你的 workspace
- 按次收費，無需承諾
- 失敗的生成不會收費
亮點
Google 的所有模型
Google's multimodal LLM for chat, code generation, reasoning, and long-context tasks.
Voice, character, and multimodal video generation resources for narration, dialogue, and agent media workflows.
Gemini TTS API 支援多講者對話，聲線、口音、演繹風格同語速均可設定。
Photorealistic text-to-image with precise typography, broad style range, and up to 2K resolution.
Fast text-to-image with accurate in-image text rendering and multi-character consistency.
High-fidelity video generation up to 4K with natively synthesized dialogue, sound effects, and ambience.
安裝 Google model skill。
選一個模型並加入其 skill，讓 coding tool 取得文件、schema、價格備註與 setup 步驟。
# Base URL
https://runapi.ai
# Endpoints
POST /v1/chat/completions
POST /v1/responses
POST /v1/messages
POST /v1beta/models/{model}:generateContent
POST /v1beta/models/{model}:streamGenerateContent
curl https://runapi.ai/v1/chat/completions \
-H "Authorization: Bearer $RUNAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-3.5-flash",
"messages": [
{
"role": "user",
"content": "Analyze this codebase and suggest three performance improvements with before/after examples."
}
]
}'from openai import OpenAI
client = OpenAI(
base_url="https://runapi.ai/v1",
api_key="your-runapi-key"
)
response = client.chat.completions.create(
model="gemini-3.5-flash",
messages=[{"role": "user", "content": "Analyze this codebase and suggest three performance improvements with before/after examples."}]
)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://runapi.ai/v1",
apiKey: "your-runapi-key"
});
const response = await client.chat.completions.create({
model: "gemini-3.5-flash",
messages: [{ role: "user", content: "Analyze this codebase and suggest three performance improvements with before/after examples." }]
});Google 的所有變體
| Model | Variant | Billing | From | |
|---|---|---|---|---|
|
Gemini
|
gemini-2.5-flash | 1K tokens | $0.020 | 查看 → |
| gemini-2.5-pro | 1K tokens | $0.080 | 查看 → | |
| gemini-3-flash-preview | 1K tokens | $0.020 | 查看 → | |
| gemini-3.1-pro-preview | 1K tokens | $0.090 | 查看 → | |
| gemini-3.5-flash | 1K tokens | $0.050 | 查看 → | |
|
Gemini Omni
|
gemini-omni-audio | call | $0.0000 | 查看 → |
| gemini-omni-character | call | $0.0000 | 查看 → | |
| gemini-omni-flash-preview | call | $0.600 | 查看 → | |
| gemini-omni-text-to-video | call | $3.60 | 查看 → | |
|
Gemini TTS
|
gemini-2.5-pro-tts | 1K tokens | $0.0014 | 查看 → |
| gemini-3.1-flash-tts | 1K tokens | $0.0014 | 查看 → | |
|
Imagen 4
|
imagen-4 | call | $0.080 | 查看 → |
| imagen-4-fast | call | $0.040 | 查看 → | |
| imagen-4-pro-remix-image | call | $0.180 | 查看 → | |
| imagen-4-ultra | call | $0.120 | 查看 → | |
|
Nano Banana
|
nano-banana | call | $0.040 | 查看 → |
| nano-banana-2 | call | $0.080 | 查看 → | |
| nano-banana-2-lite | call | $0.030 | 查看 → | |
| nano-banana-edit | call | $0.040 | 查看 → | |
| nano-banana-pro | call | $0.180 | 查看 → | |
|
Veo 3.1
|
veo-3.1 | call | $2.50 | 查看 → |
| veo-3.1-fast | call | $0.600 | 查看 → | |
| veo-3.1-lite | call | $0.300 | 查看 → |
關於 Google 的常見問題
這是 Google 的官方整合嗎？
RunAPI 提供託管 API 介面，價格、能力及錯誤行為都清晰透明。
我需要 Google 帳戶嗎？
不用 — 你的 RunAPI 密鑰已足夠使用託管存取。
透過 proxy 會增加多少延遲？
通常少於 20 ms。RunAPI 會將 proxy 層維持在貼近 model 執行區域的位置。
圖片／影片會快取嗎？
生成結果會按 task ID 儲存並可供取回。輸入內容不會快取。
我可以使用自己的 key 嗎？
目前不支援 — 請使用 RunAPI 管理的存取。