AI Builder Tools

Capacity and cost calculators for engineers building AI agents and LLM applications. Estimate tokens, compare API prices, size GPUs, and see what an agent loop really costs before you ship it. Everything runs in your browser.

LLM Token Counter

Count tokens for GPT, Claude, and Gemini, check context-window fit, and see what the prompt costs.

LLM API Cost Calculator

Compare per-request and monthly API costs across OpenAI, Anthropic, and Google models, with prompt caching.

LLM VRAM Calculator

Estimate GPU memory for weights, KV cache, and fine-tuning, and see which GPUs a model fits on.

AI Agent Cost Calculator

Model the real cost of agent loops: growing context, tool results, prompt caching, retries, and sub-agents.

Coming soon

Prompt Caching Savings Calculator

Soon

Work out when caching pays off, and by how much.

Self-host vs API Break-even

Soon

Compare GPU rental costs against per-token API pricing at your traffic.

Inference Capacity Planner

Soon

Turn QPS and latency targets into GPU counts and rate-limit needs.

RAG Embedding & Storage Cost

Soon

Estimate embedding, vector storage, and retrieval costs for a corpus.

Why agent builders need different math

Pricing pages quote dollars per million tokens, but an agent doesn't make one request. It makes dozens, each re-reading a context that grows with every tool result. Self-hosting has the same problem in a different form: model weights are a fixed cost, but the KV cache grows with every concurrent conversation. These tools make those dynamics visible so you can choose models, caching strategies, and hardware with real numbers.

New to the concepts? Start with tokenization, context windows, and our capacity planning guide.