114 free calculators to estimate, compare and optimize AI costs.
Paste a prompt and see what it costs on every major AI model at once.
Estimate tokens, words and characters for any text.
Convert between words, characters and tokens.
Count characters, words, sentences and estimated tokens.
Estimate the cost of model output length.
See how many tokens $1 buys on any model.
See what percentage of a model's context window you're using.
Check if your document fits a model's context window in one call.
See how resending chat history inflates tokens and cost.
See why non-English text costs more tokens.
Compare token counts for prose, code, JSON and more.
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.
Estimate ingestion, storage and query costs for a RAG system.
Estimate the cost to embed a corpus of text.
Estimate vector storage size and monthly cost.
See how chunk size and overlap change chunk count.
Estimate the cost of a single RAG query.
Estimate the cost of periodically re-embedding a corpus.
Estimate storage and query cost for a vector database.
Compare retrieving top-k chunks vs stuffing the whole corpus.
Estimate the monthly cost of re-embedding changed documents.
Compare vector storage at float32, float16 and int8.
See how a semantic cache cuts repeat-query cost.
Estimate the cost of multi-step AI agents with tool calls.
Estimate the cost of function/tool calling in agents.
Estimate token cost of MCP tool interactions.
See how growing agent memory inflates cost per step.
Estimate the cost of orchestrating multiple agents.
Estimate the cost of a multi-step agent workflow.
See the token cost of sending tool schemas on every call.
Check whether your prompt, history and context fit a model's window.
Budget system, example and user tokens against a model.
Estimate the added cost of few-shot examples.
Estimate combined AWS Lambda and LLM cost per invocation.
Estimate AWS Lambda compute and request cost.
Estimate AWS CloudFront data transfer and request cost.
Estimate DynamoDB on-demand read, write and storage cost.
Estimate Amazon S3 storage, request and transfer cost.
Estimate OpenSearch Serverless compute and storage cost.
Find the volume where self-hosting beats API pricing.
See response time and throughput at a given tokens/sec.
Find the tokens/sec needed to hit a latency target.
Size concurrency and instances for a target request rate.
Check if your traffic fits provider TPM and RPM limits.
Estimate the VRAM needed to run a model locally.
Estimate tokens/sec for a model on your GPU.
Estimate monthly cost of renting cloud GPUs.
Compare model VRAM across fp32, fp16, int8 and int4.
Find how many GPUs you need for a target tokens/sec.
Estimate GPU-hour cost and wall-clock time for a training run.
Estimate the cost of generating AI images at scale.
Estimate the cost of generating AI video (Sora).
Estimate AI text-to-speech cost by characters.
Estimate AI transcription cost by minutes of audio.
Estimate document OCR cost per page.
Estimate combined STT + LLM + TTS cost per call.
Estimate the cost to transcribe, translate and voice-over video.
Estimate the cost of auto-captioning video with AI.
Estimate the cost to transcribe and summarize meetings.
Calculate ROI and payback period for an AI investment.
Estimate labor savings from automating a task with AI.
Estimate savings from an AI support assistant.
Split an AI budget across chat, RAG and other workloads.
See whether a flat subscription or pay-as-you-go API is cheaper for you.
Set a resale price and see your margin per request.
Check margin when you charge per AI request.
Estimate the AI cost per article and per month.
Compare AI translation cost against human translators.
Estimate net revenue from AI-generated sales outreach.
Check per-seat margin for an AI SaaS product.
Estimate energy and CO₂ from your token usage.
Estimate tokens and cost for JSON payloads.
Estimate tokens and cost for source code.
Estimate tokens and cost to process a PDF with an LLM.
Estimate tokens and cost to feed a whole codebase to an LLM.
Compare the cost of every model for the same workload.
Compare context windows across all models.
Compare vision, tools, reasoning and caching support.
Compare input, output and cached prices across models.
Compare the cost of any GPT and Claude model side by side.
Compare Google Gemini and OpenAI GPT costs side by side.
Compare Anthropic Claude and Google Gemini costs side by side.
Compare DeepSeek and OpenAI GPT costs side by side.
Rank embedding models by price and dimensions.
Compare image models by price per image.
Compare speech-to-text models by price per minute.
Compare TTS models by price per million characters.
Compare video models by price per second.