About LLM Forge

LLM Forge is a free, independent collection of tools for developers, founders, and researchers who build with large language models (LLMs). It started as a personal set of calculators we kept rebuilding for every project — “how many tokens is this prompt?”, “what will this cost at scale?”, “which model has the right context window?” — and grew into a single place to answer those questions quickly, without spreadsheets or signups.

What you can do here

The toolkit covers the everyday decisions of LLM development: estimating tokens and costs, comparing models side by side, planning context windows, calculating embedding and fine-tuning budgets, checking rate limits, and understanding how retrieval-augmented generation (RAG) pipelines work. Every tool runs entirely in your browser — your prompts and text never leave your device.

How our data is sourced

Model names, context windows, and prices are compiled from each provider's official documentation and pricing pages, and reviewed periodically — most recently in June 2026. Pricing for AI models changes often, so we treat every figure as an estimate and always recommend confirming the current rate on the provider's site before making budget decisions. Token estimates are based on average character-to-token ratios and are intended for planning, not billing.

Independence

LLM Forge is not affiliated with, endorsed by, or sponsored by OpenAI, Anthropic, Google, Meta, xAI, Mistral, DeepSeek, or any model provider. Product and company names are trademarks of their respective owners and are used here only to identify the tools they make. The site is free to use and supported by advertising, which lets us keep every tool available without a paywall or account.

Get in touch

Spotted an out-of-date price or a bug? Want to suggest a tool? We genuinely want to hear about it — corrections keep the data trustworthy. Reach us via the contact page. You can also read our privacy policy and terms of use.