Developer utility · Local-first history

Claude API cost calculator

Pre-loaded with Anthropic-style tiers. Tune tokens and batch size to see where Haiku saves budget versus Sonnet quality.

Pricing data loads from config/models.php and /api/pricing. Verify against provider pages before billing decisions.

Calculator

Cost = (prompt ÷ 1000 × Pin) + (completion ÷ 1000 × Pout), then × requests.

Usage presets

Multi-model comparison

Toggle models to compare the same workload. The cheapest option is highlighted.

Monthly cost simulator

Project from average daily requests (uses tokens above).

Uses primary model rates for projections.

Token estimator

Rough heuristic: ~4 characters ≈ 1 token for Latin text (indicative only).

Estimated tokens: 0 · Cost @ primary: —

API budget planner

Set a monthly cap to see how many identical requests fit (primary model).

Max requests (approx): —

Prompt optimization analyzer

Collapse whitespace and tighten wording to preview savings at the primary model.

Suggested shorter form:


                    
Token delta: 0 · Est. savings / 1k calls: —

                


                

                    
Fine-tuning cost sketch

                    
Order-of-magnitude helper: training tokens × epochs × rate + storage.

                    

                        

                            
                            
                        

                        

                            
                            
                        

                        

                            
                            
                        

                        

                            
                            
                        

                        

                            
                            
                        

                        

                            
Est. training + 1 mo storage: —

                        

                    

                


                

                    
Team usage calculator

                    
Multiply per-person daily volume by team size (primary model).

                    

                        

                            
                            
                        

                        

                            
                            
                        

                        

                            
Team monthly (22d): —

                        

                    

                


                

                    
Cost per feature

                    
Price a single product surface (e.g., one chat turn or one generated article).

                    

                        

                            
                            
                        

                        

                            
                            
                        

                    

                    
Uses prompt & completion tokens from the calculator for one invocation.

                    
Cost per use: — · Monthly @ that cadence: —

                


                

                    
Share & export

                    
Serialize inputs in the URL hash or copy a text summary.

                    

                        
                        
                    

                    

                


                

                    
Calculation history

                    
Stored in your browser only (LocalStorage).

                    

                        
                        
                    

                    
    
                
    
            
    

            
        
    

        
    
                        
    
                
    
                    
    Guide
    
                    
    
                        Tokens, pricing & how to use this calculator
                    
    
                    
    
                        Plain-language reference for engineers planning LLM spend. Skim the cards below or jump to a specialized page at the end.
                    
    
                
    

                
    
                    
    
                        
                        
    What are tokens?
    
                        
    
                            Tokens are the chunks of text models read and write—often a few characters or part of a word. You are billed separately for input (your prompt) and output (the model’s reply). Big JSON payloads, long system prompts, and high max_tokens all push cost up.
                        
    
                    
    

                    
    
                        
                        
    How API pricing works
    
                        
    
                            Providers usually quote dollars per million or thousand tokens for input and output. Output is often pricier than input. This app applies the standard formula: scale your token counts to match the per-1K rate in config, sum input + output for one call, then multiply by your number of requests.
                        
    
                    
    

                    
    
                        
    
                            
                            
    Tips to reduce API cost
    
                        
    
                        
      
                            
    • 
                                
                                Cap completion length and tighten system prompts so the model stays concise.
                            
      • 
                            
    • 
                                
                                Cache stable context server-side instead of resending huge prompts every turn.
                            
      • 
                            
    • 
                                
                                Route simple tasks to smaller models; reserve large models for hard paths.
                            
      • 
                            
    • 
                                
                                Use the comparison table here to see which configured model is cheapest for the same tokens.
                            
      • 
                        
    
                    
    

                    
    
                        
                        
    Model comparison & keeping rates fresh
    
                        
    
                            Line up OpenAI, Anthropic, and DeepSeek rows from
                            config/models.php.
                            After deploy, the UI reads that config; scripts can also pull
                            /api/pricing.
                            Replace numbers whenever vendors publish new tables—this tool does not replace official billing consoles.
                        
    
                    
    

                                            
                    
                    

                    
    
        
    Common questions about tokens & pricing
    
        
    
            Short answers mirror the structured data on this page for search engines and readers.
        
    
        
    
                                                                
    
                        
    What is an AI token cost calculator?
    
                        
    An AI token cost calculator estimates how much you pay for large language model (LLM) API calls by multiplying input and output token counts by each model’s per-thousand-token price, then scaling by the number of requests or monthly traffic.
    
                    
    
                                                                                
    
                        
    How accurate are the estimates on this site?
    
                        
    Figures follow the rates you configure in config/models.php and are intended for planning and comparison. Always confirm current pricing on each provider’s official billing page before making financial or procurement decisions.
    
                    
    
                                                                                
    
                        
    What are input tokens vs output tokens?
    
                        
    Input tokens are the prompt and context the model reads; output tokens are the generated completion. Providers usually price them differently, with output often more expensive per token.
    
                    
    
                                                                                
    
                        
    Does this tool store my prompts or API keys?
    
                        
    Calculations run in your browser. Optional history uses LocalStorage on your device only and is not sent to our servers. Do not paste secrets or production API keys into any public website.
    
                    
    
                                                                                
    
                        
    How do I estimate Claude API costs?
    
                        
    Choose Anthropic Claude models from the list, enter your token mix and request volume, and review per-request and monthly projections alongside other providers in the comparison table.