Skip to main content
kitlocal.dev

AI & LLM

Build prompts, estimate token costs, compare AI models and explore context windows.

11 of 13 run locally
Showing 13 tools

Estimate LLM tokens and costs for various AI models.

Uses network

Build, test, and refine AI prompts with templates and best practices

Runs locally

Estimate API costs across GPT-4, Claude, Gemini, and other models

Runs locally

Compare AI model specifications, pricing, and capabilities side by side

Runs locally

Build effective system prompts with role, instructions, and constraints

Runs locally

Visualize how text is split into tokens by different AI tokenizers

Runs locally

See how a document is split into chunks for RAG: chunk size, overlap, token counts, embedding cost and retrieved context

Runs locally

View and compare LLM performance benchmarks (MMLU, HumanEval, etc.)

Runs locally

Validate an OpenAI API key server-side without exposing the verification request to the browser

Uses network