AI Tools

LLM Token Counter

Estimate token counts for GPT, Claude, Gemini, Llama and Mistral — instantly, in your browser.

LLM Prompt Cost Estimator

Estimate the daily and monthly USD cost of running prompts across GPT-4, Claude, Gemini, Llama and Mistral.

Tokens Per Second Visualizer

Visualize queue time, first-token latency, and token throughput for AI responses.

Context Window Visualizer

See how system prompts, examples, retrieval chunks, and output reserve fit inside a model context window.

Prompt Word to Token Ratio Calculator

Convert human word counts into LLM token estimates and compare models side-by-side.

AI Output Detector Readability Score

Score text for readability and heuristic AI-likeness signals — useful for editorial QA.

System Prompt Builder

Build stable system prompts with role, goal, constraints, tone, examples, and output format.

Temperature & Top-P Explainer

Compare temperature and top-p settings to see how they affect randomness and control.

AI Image Prompt Formatter

Format image prompts into subject, style, lighting, camera, and negative prompt sections.

Embeddings Dimension Reference

Look up common embedding models and their vector dimensions for search and RAG planning.

LLM Latency Budget Calculator

Estimate request latency from prompt size, output size, throughput, queue time, and safety margin.