OpenAI API

Call GPT models with token billing; the featured gpt-6.1-sol model has no Free tier.

···
html
<div class="price-card ring"><div class="title"><b>gpt-6.1-sol</b><span>USD / 1M tokens</span></div><div class="visual"><div id="graphic" class="graphic"><i id="input-fill"></i><i id="output-fill"></i></div><div class="amount"><strong id="total">$0.00</strong><small>monthly total · short requests</small></div></div><div class="sliders"><label>INPUT <output id="input-label"></output><input id="input" type="range" min="0" max="1000000" step="50000" value="500000" aria-label="Monthly input tokens"></label><label>OUTPUT <output id="output-label"></output><input id="output" type="range" min="0" max="500000" step="25000" value="100000" aria-label="Monthly output tokens"></label></div><p class="note">2026-10-06 공식 가격 기준 · 단순화(세금·지역 할증 제외)</p></div>
css
.price-card{width:min(96vw,760px);height:min(94vh,350px);padding:clamp(7px,1.8vmin,17px);border:1px solid var(--line);border-radius:14px;background:var(--surface);display:flex;flex-direction:column;gap:clamp(3px,1vmin,9px);font:600 clamp(10px,2.2vmin,14px)/1.15 system-ui,sans-serif}.title{display:flex;justify-content:space-between;gap:6px;align-items:center}.title b{color:var(--accent);font-size:clamp(12px,2.6vmin,18px)}.title span,.amount small,.note{color:var(--muted)}.visual{flex:1;min-height:0;display:flex;align-items:center;justify-content:space-around;gap:8px}.graphic{position:relative;width:42%;height:76%;min-height:32px}.columns .graphic{display:flex;align-items:flex-end;gap:12%;padding:4px 8%}.columns .graphic i{width:42%;height:20%;background:var(--accent);border-radius:5px 5px 0 0;transition:height .4s}.columns .graphic i+ i{background:var(--accent-2)}.ring .graphic{width:clamp(42px,14vmin,90px);height:clamp(42px,14vmin,90px);border-radius:50%;background:conic-gradient(var(--accent) 0 60%,var(--accent-2) 60% 80%,var(--line) 80%);transition:background .4s}.ring .graphic:after{content:'';position:absolute;inset:24%;border-radius:50%;background:var(--surface)}.ring .graphic i{display:none}.steps .graphic{display:flex;flex-direction:column;justify-content:flex-end;gap:5px}.steps .graphic i{display:block;height:38%;width:30%;background:var(--accent);clip-path:polygon(0 100%,0 45%,35% 45%,35% 20%,70% 20%,70% 0,100% 0,100% 100%);transition:width .4s}.steps .graphic i+ i{height:30%;background:var(--accent-2);transform:scaleX(-1)}.amount{min-width:42%;display:flex;flex-direction:column;gap:2px}.amount strong{font:800 clamp(19px,6vmin,38px)/1 system-ui,sans-serif;color:var(--fg);white-space:nowrap}.amount small{font-size:clamp(9px,1.9vmin,12px)}.sliders{display:grid;grid-template-columns:1fr 1fr;gap:8px}.sliders label{display:flex;flex-wrap:wrap;justify-content:space-between;gap:2px}.sliders output{color:var(--accent)}.sliders input{width:100%;margin:0;accent-color:var(--accent);height:14px}.note{font-size:clamp(8px,1.5vmin,11px);margin:0;line-height:1.15}@media (min-width:600px){.price-card,.price-scene,.limit-card,.compute-card,.credit-card,.plan-card,.credit-ledger,.claude-card,.comparison{width:min(96vw,1080px);font-size:15px}.fine,.note,.comparison .fine{font-size:11px}.comparison header b{font-size:18px}}
js
const input=document.getElementById('input');const output=document.getElementById('output');const graphic=document.getElementById('graphic');const fills=[document.getElementById('input-fill'),document.getElementById('output-fill')];let tick=0;let timer;function draw(){const a=Number(input.value),b=Number(output.value);document.getElementById('input-label').textContent=(a/1000).toFixed(0)+'k';document.getElementById('output-label').textContent=(b/1000).toFixed(0)+'k';document.getElementById('total').textContent='$'+((a*2+b*10)/1000000).toFixed(2);fills[0].style.height=Math.max(8,a/1000000*100)+'%';fills[1].style.height=Math.max(8,b/500000*100)+'%';fills[0].style.width=Math.max(14,a/1000000*100)+'%';fills[1].style.width=Math.max(14,b/500000*100)+'%';graphic.style.background=graphic.classList.contains('graphic')&&graphic.parentElement.parentElement.classList.contains('ring')?'conic-gradient(var(--accent) 0 '+(a/1000000*65)+'%,var(--accent-2) '+(a/1000000*65)+'% '+(a/1000000*65+b/500000*30)+'%,var(--line) 0)':''}draw();timer=setInterval(()=>{tick=(tick+1)%4;input.value=String([250000,500000,750000,1000000][tick]);output.value=String([50000,100000,150000,250000][tick]);draw()},1100);[input,output].forEach(el=>el.addEventListener('input',()=>{clearInterval(timer);draw()}))

OpenAI API gives an app access to GPT models and tool calling. Check input and output rates for the chosen model and context length.

As of 2026-10, gpt-6.1-sol Standard costs $2 per million input tokens and $10 per million output tokens; cached input is $0.10. Batch rates are $1 input and $5 output per million. This model does not support the Free tier.

If one request exceeds 272k input tokens, the whole request uses double input and 1.5 times output rates. The demo aggregates uncached monthly tokens from shorter requests; check per-request length and tool charges before budgeting.

When to use

Choose it when you need GPT models or OpenAI tools. Match expected output as well as input volume when comparing Claude and Gemini.

Open as page ↗