一個驗證,對應所有 provider
一組 RunAPI key 即可解鎖整個 catalog。無需分開帳戶,亦無需為每個整合輪換密鑰。
It looks like you may prefer a different language. Switch anytime.
透過 RunAPI 使用 Seedream API,包含 model skill、統一驗證與按用量計費。
curl -X POST https://runapi.ai/api/v1/seedream/edit_image \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedream-v4-text-to-image",
"source_image_urls": [
"https://cdn.runapi.ai/public/samples/image.jpg"
],
"prompt": "Create a social media graphic for a coffee shop sale with the text '50% OFF' in bold, warm tones, 4K."
}'
import { SeedreamClient } from "@runapi.ai/seedream";
const client = new SeedreamClient();
const result = await client.editImage.run({
model: "seedream-v4-text-to-image",
source_image_urls: ["https://cdn.runapi.ai/public/samples/image.jpg"],
prompt: "Create a social media graphic for a coffee shop sale with the text '50% OFF' in bold, warm tones, 4K.",
});
<?php
require __DIR__ . "/vendor/autoload.php";
use RunApi\Seedream\SeedreamClient;
$client = new SeedreamClient();
$result = $client->editImage->run([
'model' => 'seedream-v4-text-to-image',
'source_image_urls' => ['https://cdn.runapi.ai/public/samples/image.jpg'],
'prompt' => 'Create a social media graphic for a coffee shop sale with the text \'50% OFF\' in bold, warm tones, 4K.',
]);
require "runapi/seedream"
client = RunApi::Seedream::Client.new
result = client.edit_image.run(
model: "seedream-v4-text-to-image",
source_image_urls: ["https://cdn.runapi.ai/public/samples/image.jpg"],
prompt: "Create a social media graphic for a coffee shop sale with the text '50% OFF' in bold, warm tones, 4K."
)
npx skills add runapi-ai/seedream -g
# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursor
Seedream is an image generation and editing model with strong typography rendering and up to 4K output resolution. It supports text-to-image and image editing workflows with fine-grained style control.
| 變體 | 計費 | 定價 | |
|---|---|---|---|
| seedream-4.5-edit | call | $0.100 | 查看 → |
| seedream-4.5-text-to-image | call | $0.100 | 查看 → |
| seedream-5-lite-edit | call | $0.080 | 查看 → |
| seedream-5-lite-text-to-image | call | $0.080 | 查看 → |
| seedream-5-pro-edit | call | $0.170 | 查看 → |
| seedream-5-pro-layer-decomposition | call | $0.140 | 查看 → |
| seedream-5-pro-text-to-image | call | $0.110 | 查看 → |
| seedream-v4-edit | call | $0.080 | 查看 → |
| seedream-v4-text-to-image | call | $0.080 | 查看 → |
| Endpoint | 解析度 | 時長 | 價格 | |
|---|---|---|---|---|
| edit_image | — | — | $0.10 / image |
以下為 seedream-4.5-edit 的定價。其他變體保留各自的 endpoint 定價。
挑選符合輸出類型、品質門檻與延遲目標的模型與變體。
設定 RunAPI key,並在 coding workspace 安裝 model skill。
使用 skill 指引,在你的 app 內加入模型功能。
透過 task ID 查詢、在支援時串流,或處理 webhook callback。
一組 RunAPI key 即可解鎖整個 catalog。無需分開帳戶,亦無需為每個整合輪換密鑰。
按次以 USD 收費,每月結算。失敗的生成不會收費。
型別化 schema 與 setup 備註打包在 model skill 內,讓實作從正確契約開始。
文字生成圖像最高支援 4K 解像度。圖像編輯可以喺 v4 上輸出 1K、2K 或 4K。
Seedream has strong typography support — it reliably renders text like headlines, logos, and labels within generated images, especially in v4.5 and v5.
文字生成圖像係從零開始創建。編輯模式接受一張或多張來源圖片加上文字指令,進行有針對性嘅指令引導編輯,同時保留圖像嘅其餘部分。
Yes — Seedream 5 Lite can perform real-time web search for time-sensitive prompts, generating images informed by current events and trends.
Seedream 4.5 generates in a few seconds. Seedream 5 Lite is faster and ~15% cheaper.
先選最平而且符合你質素要求的版本。大多數團隊會先用快速版本,之後再升級到 pro 用於正式生產。