LLM API Cost Calculator

Apne token counts se GPT, Claude aur Gemini API costs estimate karein. Aapke prompts aapke device se bahar nahi jaate.

Token counting aur cost math locally aapke browser mein chalte hain aur kuch bhi upload nahi hota, par prompt box mein secrets ya production data paste karne se bachein.

Precise token counts chahiye? Token Counter kholein.

LLM Cost Calculator ke baare mein

Yeh LLM cost calculator token counts ko OpenAI, Anthropic aur Google APIs ke liye ek dollar estimate mein badal deta hai. Ek model chunein — GPT-4o, GPT-4.1, o1, Claude 3.5 Sonnet, Gemini 1.5 Pro aur bahut kuch — phir input aur output token counts enter karein, ya ek prompt paste karein aur tool ko sahi tokenizer se uske input tokens count karne dein. Yeh tokens ko har model ke per-million price se multiply karta hai aur input, output aur total cost dikhata hai, batch ya monthly projections ke liye ek optional requests multiplier ke saath. Prices indicative hain aur aksar badalte hain, isliye har figure ek as-of marker ke saath labelled hota hai aur aap kisi bhi model ke liye input aur output price per million ko cached, batch ya naye rates se match karne ke liye override kar sakte hain. Token counting aur math poori tarah aapke browser mein chalte hain, isliye aap jo prompts paste karte hain woh aapke device par process hote hain aur kabhi aapke device se bahar nahi jaate.

Features

LLM Cost Calculator kaise use karein

  1. Provider ke hisaab se grouped dropdown se ek model chunein.
  2. Input tokens enter karein, ya Count from prompt toggle karke apna prompt paste karein.
  3. Expected output tokens enter karein aur, agar zaroorat ho, requests ki ek sankhya.
  4. Input, output aur total cost USD mein padhein.
  5. Apne actual rate se match karne ke liye $/1M input ya output price override karein.

Example

Input

Model: GPT-4o
Input tokens: 1,000
Output tokens: 500
Requests: 1

Output

Input cost:  $0.0025
Output cost: $0.0050
Total cost:  $0.0075

1,000 input @ $2.50/M + 500 output @ $10/M = $0.0075 per request.

Common errors aur troubleshooting

Aksar pooche jaane wale sawaal

LLM API cost kaise calculate hoti hai?
Yeh aapke input tokens ko model ke input price per million se aur aapke output tokens ko output price per million se multiply karta hai, phir unhe jodta hai. Batch ya monthly spend project karne ke liye requests field se multiply karein.
Kya prices current hain?
Woh indicative hain aur ek as-of date ke saath marked hain kyunki provider pricing aksar badalti hai. Hamesha OpenAI, Anthropic ya Google ke pricing page par live rate confirm karein, aur exact numbers daalne ke liye override fields use karein.
Kya main andaaza lagane ki jagah ek real prompt se tokens count kar sakta hoon?
Haan. Count from prompt toggle karein aur apna text paste karein; calculator use selected model ke tokenizer se tokenize karta hai aur use input token count ke roop mein use karta hai. OpenAI counts exact hote hain jabki Claude aur Gemini approximate.
Kya isme cached input ya batch pricing shaamil hai?
Nahi. Estimate standard text-tier rates use karta hai aur cached-input discounts, batch pricing, aur image ya audio tokens ko chhod deta hai. Un cases ko model karne ke liye apna discounted rate $/1M override mein enter karein.
Kya mere prompts ya API keys kahin bheje jaate hain?
Nahi. Calculator kabhi API key nahi maangta, aur token counting plus cost math locally aapke browser mein chalte hain, isliye aap jo bhi prompt paste karte hain woh aapke device par process hota hai aur kabhi upload nahi hota.

Related tools

Saare ArrayKit tools