Claude Opus 5.5 API

流传最广的那句提示词

这句提示词由 @stephanlivera 在 2026 年 9 月 25 日发出,原帖浏览超过 200 万,被重跑了成千上万次。拿来测环境是否跑通很合适;但正因为用的人太多,跑出来的东西彼此很像,案例库里那些长 brief 更耐用。

make a dynamic 15-second motion graphics video that shows what an incredible motion designer you are, like it's your showreel for a résumé. go all out.

提示词作者 @stephanlivera,逐字取自原帖 · x.com/stephanlivera

这样跑一次大概花多少:我们自己那条 12 秒的实测,31,786 个输出 token,实扣 $0.368。按每百万 token $2.40 / $12 计,每 1 万个输出 token 是 $0.12,所以一条需要 3 万到 8 万 token 思考和代码的短片,单次大约 $0.36 到 $0.96,另加几分钱输入。渲染在你自己的机器上完成,不花钱。

1. 要的是「带帧协议的程序」,不是「一段视频」

让后面一切成立的只有一条规矩:页面必须暴露 window.renderFrame(t),每次从零画出第 t 秒那一帧,不读时钟、不用随机数、调用之间不留状态。这样脚本可以按任意顺序要第 0 帧、第 1 帧……第 359 帧,每次得到同一张画面,这正是视频编码需要的。自己用 requestAnimationFrame 播放的页面在浏览器里看着没问题,但没法逐帧精确导出。我们还在提示词里把节奏定死(120 BPM,每 0.5 秒一拍),并要求模型把节拍表写成注释;它写了 24 拍,每个转场都落在拍上。

2. 先按时间段讲故事,再讲风格

在任何视觉细节之前,先写清每个时间段发生什么(问题、转折、收尾)。点名你要在画面上出现的文字,也说清楚不许出现什么(我们要求用简单的圆角标签,不要真实公司的 logo)。风格放最后、写短:一个强调色、用哪种缓动、明确一句「最后 3 秒不要杂乱」。我们发出的完整提示词在下面,一字未改。

我们发出的提示词(原文)

You are writing a program that renders a video. Output one complete, self-contained HTML file and nothing else.

Rules for the program (these make it renderable frame by frame):
1. A single <canvas> of exactly 1280x720, no CSS scaling, black page background.
2. Expose a global function window.renderFrame(t) that draws the frame at time t (seconds, 0 <= t < 12) from scratch. Everything on screen must be a pure function of t: no Date.now, no performance.now, no Math.random (use a seeded PRNG if you need noise), no accumulated state between calls, no requestAnimationFrame loop.
3. Also expose window.DURATION = 12 and window.FPS = 30. When the page is opened normally, play it once in a loop with requestAnimationFrame by calling renderFrame, so a human can preview it.
4. No external assets, fonts, images or libraries. Use system-ui for text.
5. The rhythm is 120 BPM: a beat every 0.5 s. Put every major cut, text entrance and impact on a beat time (a multiple of 0.5). List the beat plan as a comment at the top of the script.

The story (tell this, then decide the visuals):
A 12-second promo for "APIMODELS", an API gateway. Problem, then turn, then payoff:
- 0-3 s: a developer's screen is cluttered with many different API keys and SDK logos flying in from every side, overlapping, getting chaotic (draw them as simple rounded labels such as "image", "video", "LLM", "audio", "key_1", "key_2", "sdk", not real company logos).
- 3-4.5 s: everything snaps together on a beat and collapses into one glowing key.
- 4.5-9 s: from that one key, lines fan out to a grid of model cards that light up one per beat (label them "145 models", "image", "video", "LLM", "audio", "one endpoint").
- 9-12 s: clean end card: the word APIMODELS, the line "One key. Every model.", and "apimodels.app" small underneath; hold still for the last second.

Style: dark background, one accent colour (electric violet #7c5cff) plus white, motion with easing (easeOutCubic / easeInOutQuad written by you), subtle depth (scale and blur fall-off), no clutter in the final 3 seconds.

Before the code, do not explain. Return only the HTML.

3. 用流式调用 Opus 5.5,不要限制 max_tokens

Opus 5.5 先思考再写,思考过程计入输出。这条提示词下,回答的第一个字在 110 秒后才出现,整个回复用了 6 分 37 秒:31,786 个输出 token,换来约 16,000 字符的 HTML。请求要用流式,保持连接不断;也不要传一个小的 max_tokens,你不传网关就不会替你加,模型按自己的上限处理。这次调用按每百万 token $2.40 / $12 计,实扣 $0.368,准确金额可以用 GET /v1/records/{id} 查到。

curl https://api.apimodels.app/v1/chat/completions \
  -H "Authorization: Bearer $APIMODELS_API_KEY" \
  -H "Content-Type: application/json" \
  -d "$(jq -n --rawfile p prompt.md \
        '{model:"claude-opus-5-5", stream:true, messages:[{role:"user", content:$p}]}')" \
  --no-buffer > stream.txt
# no max_tokens on purpose: this run used 31,786 output tokens, mostly thinking

4. 用无头 Chrome 渲染每一帧

打开页面、停掉它自带的预览循环,然后对每一帧调用 renderFrame(i / 30),把 canvas 读成 PNG。360 帧在笔记本上用了 14 秒,页面零报错。再用 H.264 加 faststart 编码,得到一个 1.8 MB、哪里都能播的文件。

// render.mjs — pnpm add puppeteer-core; uses the Chrome you already have
import puppeteer from 'puppeteer-core'
import { mkdirSync, writeFileSync } from 'node:fs'

mkdirSync('frames', { recursive: true })
const browser = await puppeteer.launch({
  executablePath: '/Applications/Google Chrome.app/Contents/MacOS/Google Chrome',
})
const page = await browser.newPage()
await page.setViewport({ width: 1280, height: 720 })
await page.goto('file://' + process.cwd() + '/promo.html')
await page.evaluate(() => { window.requestAnimationFrame = () => 0 }) // stop the preview loop
const { DURATION, FPS } = await page.evaluate(() => ({ DURATION, FPS }))
for (let i = 0; i < DURATION * FPS; i++) {
  const png = await page.evaluate((t) => {
    window.renderFrame(t)
    return document.querySelector('canvas').toDataURL('image/png')
  }, i / FPS)
  writeFileSync(`frames/f${String(i).padStart(4, '0')}.png`, Buffer.from(png.split(',')[1], 'base64'))
}
await browser.close()

ffmpeg -framerate 30 -i frames/f%04d.png -c:v libx264 -pix_fmt yuv420p -crf 20 -movflags +faststart promo.mp4
# add a soundtrack afterwards if you have one:
# ffmpeg -i promo.mp4 -i beat.mp3 -c:v copy -shortest promo-with-audio.mp4

5. 先看关键帧,再评价成片

在故事节点抽几帧拼成一张图,和需求对照:这里是 2.3 秒(混乱)、3.5 秒(一把钥匙)、7.2 秒(模型卡逐个点亮)、11.3 秒(结尾品牌卡)。四帧第一次就全对上了。要改的话按时间码和拍点提(「7.5 秒时第六张卡带脉冲点亮」),并要求它返回完整文件,免得帧协议被改坏。

我们遇到的限制

• 没有声音。程序只画画面;配乐用 ffmpeg 事后合进去,节拍用你给模型的那个 BPM。
• 首字慢。这类提示词大约要等两分钟才出第一个字;流式能保住连接,客户端超时设短了就会断。
• 它不检查自己的输出。模型没有运行过这个页面,是我们运行的。一定要渲染、看帧,把 HTML 当成未经测试的代码。

这次运行的文件

• 12 秒 MP4 成片
• Opus 5.5 原样返回的 HTML(打开即可预览)
• 四帧拼图

相关指南

• 用 Opus 5.5 做视频:能做什么、不能做什么
• Opus 5.5 动效设计提示词(7 份原文)
• 60 个别人用 Opus 5.5 做的视频案例(附提示词)
• 在 Claude Code 里用 Opus 5.5:配置与花费
• Opus 5.5 vs Sonnet 5.5