Estimate LLM API and chatbot costs per request and month.
Estimate the cost of any LLM API call per request and per month.
Estimate OpenAI GPT-4o, GPT-4o mini and o-series API costs.
Estimate Anthropic Claude API costs with caching and batch pricing.
Estimate the monthly cost of running an AI chatbot at scale.
Estimate Google Gemini 2.5 Pro, Flash and Flash-Lite costs.
Estimate DeepSeek V4 Flash and V4 Pro API costs.
Estimate Mistral Large, Medium and Small API costs.
Estimate hosted Llama 4 Maverick and Scout API costs.
Estimate Cohere Command A, R+ and R API costs.
Estimate Amazon Nova Premier, Pro, Lite and Micro costs.
Estimate xAI Grok 4.5 and Grok 4.3 API costs.
Estimate Perplexity Sonar, Sonar Pro and Reasoning Pro token costs.
See how much prompt caching cuts your input cost.
Compare real-time vs batch API pricing.
See what a fixed system prompt costs at scale.
See savings from shortening your prompts.
Estimate LLM cost and margin per conversation.
See how summarizing old chat turns cuts token cost.
Estimate the cost of fine-tuning a model on your data.
Find the break-even point between fine-tuning and few-shot prompts.
Project your AI spend as usage grows.
Turn total AI spend into a per-active-user number.
Price a workload per 1,000 (or per million) requests.
Estimate cost when routing traffic between two models.
See how a price increase or cut hits your bill.
Account for hidden reasoning tokens on o-series and thinking models.
See how many chat sessions a budget buys.