AI Model Cost Comparator - Compare GPT, Claude, Gemini and Llama Prices
Paste a prompt and compare per-call, per-day and per-month cost across 12 AI models
| Model | $/1M in | $/1M out | Per call | Per day | Per month | Fits? |
|---|---|---|---|---|---|---|
GPT-4o mini OpenAI ยท 128k ctx | $0.15 | $0.6 | $0.000303 | $0.3030 | $9.09 | โ |
Llama 3.3 70B Meta (via Groq) ยท 128k ctx | $0.59 | $0.79 | $0.000407 | $0.4068 | $12.204 | โ |
DeepSeek V3 DeepSeek ยท 64k ctx | $0.27 | $1.1 | $0.000555 | $0.5554 | $16.662 | โ |
Gemini 2.5 Flash Google ยท 1000k ctx | $0.3 | $2.5 | $0.001256 | $1.256 | $37.68 | โ |
Claude Haiku 4.5 Anthropic ยท 200k ctx | $1 | $5 | $0.002520 | $2.52 | $75.60 | โ |
Mistral Large 2 Mistral ยท 128k ctx | $2 | $6 | $0.003040 | $3.04 | $91.20 | โ |
Gemini 2.5 Pro Google ยท 1000k ctx | $1.25 | $10 | $0.005025 | $5.025 | $150.75 | โ |
GPT-4o OpenAI ยท 128k ctx | $2.5 | $10 | $0.005050 | $5.05 | $151.50 | โ |
o1-mini OpenAI ยท 128k ctx | $3 | $12 | $0.006060 | $6.06 | $181.80 | โ |
Claude Sonnet 4.5 Anthropic ยท 200k ctx | $3 | $15 | $0.007560 | $7.56 | $226.80 | โ |
o1 (reasoning) OpenAI ยท 200k ctx | $15 | $60 | $0.0303 | $30.30 | $909.00 | โ |
Claude Opus 4 Anthropic ยท 200k ctx | $15 | $75 | $0.0378 | $37.80 | $1,134.00 | โ |
์ฌ์ฉ๋ฒ
- 1Paste your prompt
The tool estimates input tokens (~4 characters per token in English). Enter exact token counts on the right for precise numbers.
- 2Set expected output tokens and call volume
Roughly how long the responses will be, and how many calls you make per day.
- 3Adjust the cache hit rate
If you use Anthropic, OpenAI or DeepSeek prompt caching, drag the slider up to see the discounted cost.
- 4Read the sorted table
Models are sorted cheapest first, with per-call, per-day and per-month totals and whether the context window fits your prompt.
AI Model Cost Comparator - Compare GPT, Claude, Gemini and Llama Prices ์๊ฐ
Free AI model cost comparator. Paste your prompt or enter exact input tokens, set expected output length and calls per day, and see per-call and monthly cost across Claude Opus, Sonnet and Haiku, GPT-4o, o1, Gemini 2.5, Llama 3.3, Mistral Large and DeepSeek V3. Factor in prompt caching. Helps you pick the right model for your budget without spinning up 12 accounts. 712 Tools์ AI Model Cost Comparator - Compare GPT, Claude, Gemini and Llama Prices์ ์ต์ JavaScript API๋ฅผ ์ฌ์ฉํด ์ฌ๋ฌ๋ถ์ browser์์ ์์ ํ ๋์ํฉ๋๋ค - server๊ฐ ์ฌ๋ฌ๋ถ์ ๋ฐ์ดํฐ๋ฅผ ๋ณผ ์ผ์ด ์ ๋ ์์ต๋๋ค. ์ฆ, ์ฆ๊ฐ์ ์ธ ๊ฒฐ๊ณผ, ์์ ํ ํ๋ผ์ด๋ฒ์, ๊ทธ๋ฆฌ๊ณ ์ ๋ก๋ ์ ํ์ด ์์ต๋๋ค.
debugging ์ธ์ , ๋น ๋ฅธ sanity check, ๋๋ ํ๋ก๋์ ์ธ์๋ํธ - ์ด๋ค ์ํฉ์ด๋ ์ด ํด์ ์ํ๋ ๋งํผ ๋ฌด๋ฃ๋ก ์ฌ์ฉํ ์ ์์ต๋๋ค. ์ํฐ๋งํฌ ์์, ๊ฐ์ ์์, ํด ๋ด ๊ด๊ณ ์์.
์์ฃผ ๋ฌป๋ ์ง๋ฌธ
How accurate are the token estimates?
The character-based estimate is within 10 to 15% for English text. Different models tokenize slightly differently, so for a precise budget, use the exact input token field or run a small sample through the real API.
Are these prices current?
Prices are public list prices at the time of the last update. Providers change pricing periodically; check the provider's pricing page before committing large volumes.
What is prompt caching?
Anthropic, OpenAI and DeepSeek offer a discount (roughly 90%) on input tokens that are repeated across calls, such as a long system prompt. If most of your prompt is a stable prefix, the cache hit rate is high and cost drops sharply.
Is my prompt uploaded anywhere?
No. All calculation runs in your browser. Your prompt text is not sent to any server.
๋ ์ฝ๊ธฐ
๊ด๋ จ ํด
Percentage Calculator
What is X% of Y, X is what % of Y, percent increase, decrease, and change
Mortgage Calculator
Estimate your monthly mortgage payment, total interest, and full amortization schedule
Loan / EMI Calculator
Calculate monthly EMI, total interest, and total payable for any personal, auto, or student loan
BMI Calculator
Calculate Body Mass Index from height and weight - metric (cm/kg) or imperial (ftยทin/lb)
Age Calculator
Calculate exact age in years, months, and days from any date of birth to any date
Date Calculator
Calculate days between two dates, or add/subtract days, weeks, months, or years from any date