Live prompt pricing across 40+ AI models. Compare, budget, and optimize every API call — before it costs you a cent.
Estimated cost
$0.0000
Claude Sonnet 4.6 · 0 tokens
Input: 0 tknEst. output: 0 tkn
Anthropic
OpenAI
Google
Claude Sonnet 4.6
$0.0000
Claude Opus 4.6
$0.0000
Current Cost
$0.0000
Total Accumulated
$0.0000
0 prompts
Claude Opus 4 – $15/$75 per 1M tokensGPT-4o – $2.50/$10 per 1M tokensGemini 2.0 Flash – $0.10/$0.40 per 1M tokensClaude Sonnet 4 – $3/$15 per 1M tokensGPT-4.1 mini – $0.40/$1.60 per 1M tokensClaude Haiku 4.5 – $0.80/$4 per 1M tokens
// capabilities
Built for people who actually pay the bill.
Client-side only
Your prompts never leave your browser. All token counting and cost math runs locally. Zero data transmitted.
Live as you type
Cost updates with every keystroke. No submit buttons, no waiting. See the price form in real time like a financial ticker.
40+ models
Every major provider in one view. Claude, GPT, Gemini, Llama, Mistral, DeepSeek — all with live pricing data.
Budget guardrails
Set daily or per-prompt spend caps. Get visual warnings before expensive prompts go out. Never get a surprise bill.
Smart suggestions
PromptPricer recommends the cheapest model that can handle your prompt complexity. Save without sacrificing quality.
API + extension
Chrome extension for in-browser pricing. REST API for integrating cost checks into your own pipelines and agents.
01
Three lines of code. Infinite savings.
Drop PromptPricer into any workflow with our lightweight SDK. Get cost estimates before every API call — then route to the cheapest model that meets your quality threshold.
47%
average savings with smart model routing
import{ estimate }from'promptpricer'// Get cost before you sendconst cost = await estimate({prompt: userMessage,model: 'claude-sonnet-4',maxOutput: 2048})// cost.usd → 0.0034// cost.tokens.input → 847// cost.tokens.output → 400// cost.cheaperOption → "claude-haiku-4.5"