Home
New to AI
All 47 tools →
Features
Use cases
Live demo
Impact analytics
Pricing
Blog
FAQ
About
CLAUDE.md Generator
Few-Shot Example Set Builder
MCP Config Wizard
System Prompt Generator
Prompt Optimizer
RAG Chunking & Retrieval Planner
ReAct Prompt Converter
Skill File Generator
Structured Output Schema Builder
Subagent & Slash Command Generator
Tool / Function Schema Generator
Workflow to Agent Blueprint
Free tool
Context Window Budget Planner
See exactly what fills up a model's context window each turn, the headroom you actually have, and why a chat session's cost grows the way it does.
Get started-
Breaks the window down into every real contributor — system prompt, tool definitions, retrieved documents, conversation history, and the output reserve — not one vague total.
-
Shows the cost-growth curve over a full session with and without truncation, which is the actual reason chat applications get expensive as conversations run on.
-
Names a truncation strategy — sliding window, summarize-and-drop, or retrieval-only — matched to what's actually filling up your budget, not a generic recommendation.
Frequently asked questions
None — this tool never calls a model to generate anything. It only counts real tokens for your pasted system prompt (same tokenizer as the Token Counter) and prices the result against Costiva's admin-editable price list.
Most model APIs are stateless — every call resends the ENTIRE conversation so far, not just the newest message. Without truncation, each turn's input grows by roughly a turn's worth of tokens, so per-turn cost grows linearly and total session cost grows quadratically. This tool's growth-curve chart plots exactly that, next to what a bounded retention policy looks like instead.
This tool is about whether everything you want in context actually FITS the window, and how fast an uncapped conversation gets expensive. The Caching Analyzer is about the mechanics of one specific prompt's cacheable prefix. Use this one first to size your budget, then hand your system prompt to the Caching Analyzer to see what restructuring it for caching would save.
Pricing, and each model's context-window size, come from Costiva's admin-editable price list, shown on this page as "pricing last verified". Always confirm against Anthropic's official documentation before making a purchasing decision.