Skip to content

LLM Token Counter & Pricing Calculator

Count tokens, compare costs, and optimize your AI API usage. Everything runs in your browser.

Token Counter

Count tokens for any LLM model. Exact counts for OpenAI, estimates for Claude & Gemini.

Try it

Pricing Calculator

Compare API costs across all major LLM providers. Find the cheapest model for your workload.

Try it

Model Comparison

Compare 2-4 models side-by-side on context window, pricing, and capabilities.

Try it

Context Window Visualizer

See how much of a model's context window your text fills. Spot limits before hitting them.

Try it

API Cost Estimator

Project daily, monthly, and yearly API costs. Calculate profit margins for your AI product.

Try it

System Prompt Builder

Build system prompts from templates. See token count and cost per API call instantly.

Try it

RAG Pipeline Cost Calculator

Calculate full RAG pipeline costs: embedding, vector DB, retrieval, and generation.

Try it

VRAM Calculator

Check if an LLM fits on your GPU. Supports quantization, context length, and Apple Silicon.

Try it

Multi-Modal Token Calculator

Calculate tokens and costs for images, audio, and video across GPT-4o, Claude, and Gemini.

Try it

Embeddings Cost Calculator

Compare embedding costs across OpenAI, Cohere, Voyage, and Google with chunking estimates.

Try it

Rate Limit Calculator

Check RPM and TPM limits by provider and tier. Find bottlenecks and estimate batch job time.

Try it

Function Calling Token Calculator

Calculate token overhead from tool/function schemas. Compare across models and optimize.

Try it