Gemini Tokenizer
Count Gemini text tokens and inspect boundaries and IDs locally.
AI stack tools
AI stack tools for cost, tokens, and coding workflows
Find practical tools and decision pages for counting prompt tokens, estimating API cost, comparing LLM providers, and choosing AI coding tools.
AI workload costs
Estimate the workload you actually run
Start from a representative workflow instead of guessing from a model price alone. Adjust tokens, calls, and cache assumptions on each calculator.
Workload calculator
Customer support chatbot
Estimate monthly LLM API cost for a customer support chatbot with repeated context, concise answers, and steady request volume.
Model this workload Workload calculatorRAG question answering
Compare LLM API costs for retrieval-augmented generation with document context, grounded answers, and repeat traffic.
Model this workload Workload calculatorDocument summarization
Estimate the cost of summarizing long documents with a large input-to-output ratio across tracked AI models.
Model this workload Workload calculatorAI agent loops
Model monthly LLM API spend for agent workflows that make repeated planning, tool-use, and follow-up calls.
Model this workload Workload calculatorCode review assistant
Estimate LLM API costs for code review prompts containing diffs, repository context, and structured review output.
Model this workload Workload calculatorClassification and routing
Compare API spend for short classification, moderation-routing, and intent-detection requests at high volume.
Model this workloadCost and stack decisions
Start with the decision you need to make
Use a calculator or comparison first, then measure prompt and document size when you need a more grounded input estimate.
API spend
LLM API cost calculator
Estimate monthly model cost from input tokens, output tokens, requests, and caching.
Estimate API cost Seat planningCoding tool team cost
Model developer seats and subscription fees before a coding-tool rollout.
Plan team cost Stack selectionCompare AI models
Compare providers and models by workload cost, pricing, and documented tradeoffs.
Compare optionsPrompt measurement
Measure tokens by model family
Tokenizer pages are the measurement layer: use them to understand input size before turning a representative request into a cost estimate.
OpenAI Tokenizer
Count plain-text tokens with current or legacy OpenAI encodings, then inspect each token boundary and ID in your browser.
Gemma Tokenizer
See how Gemma 3 splits plain text into tokens, inspect token IDs, and keep the text in your browser.
Qwen Tokenizer
Tokenize text with the pinned Qwen 3.5 tokenizer, inspect token boundaries and IDs, and keep your input local.
DeepSeek Tokenizer
Count tokens with the pinned DeepSeek V4 Pro tokenizer and inspect the token pieces and IDs without uploading your text.
Llama Tokenizer
See how a Llama 3 tokenizer splits plain text, inspect token IDs, and keep your text in the browser.
Mistral Tokenizer
Paste text, a prompt, or code to count tokens with the pinned Mistral Medium 3.5 tokenizer, then inspect the exact token pieces and IDs in your browser.
Team cost tools
Plan coding assistant seats
Estimate subscription cost before a pilot or team rollout. Each calculator states which fees and usage charges are excluded.
Seat calculator
GitHub Copilot
Estimate monthly and annual GitHub Copilot subscription cost by developer count and individual plan.
Calculate cost Seat calculatorCursor
Estimate Cursor monthly and annual cost for individual Pro or Teams seats before rollout.
Calculate cost Seat calculatorWindsurf
Estimate Windsurf subscription cost for Pro, Max, or the tracked Teams base-plus-seat plan.
Calculate cost Seat calculatorClaude Code
Estimate the subscription cost of providing Claude Code access through tracked Pro and Max individual plans.
Calculate cost Seat calculatorTabnine
Estimate Tabnine annual-commitment seat cost for Code Assistant and Agentic Platform plans.
Calculate costStackLens tools
Start with the calculators
Use these first when you need token counts or a quick cost model before choosing a provider.
AI model rankings
Inspect measured tokenizer efficiency, a fixed API cost workload, and separate quality evidence.
Explore model rankingsAI model directory
Browse source-tracked model pricing, profiles, context windows, and cost examples.
Browse AI modelsToken counter
Count tokens, inspect token boundaries, and view token IDs in your browser.
Open token counterTokenizer comparison
Compare fixed English, Chinese, JSON, and code samples across seven tokenizers.
Compare tokenizersJSON token counter
Format or minify JSON, then compare its token count across seven tokenizers.
Count JSON tokensCode token counter
Paste code and compare token counts per line across seven local tokenizers.
Count code tokensFile token counter
Count tokens across text, JSON, Markdown, CSV, and code files locally.
Count file tokensURL token counter
Extract readable text from a public webpage and count its OpenAI tokens.
Count webpage tokensImage token calculator
Calculate image input tokens and estimated cost for OpenAI, Claude, and Gemini.
Calculate image tokensGemini tokenizer
Count Gemini-compatible text tokens and inspect token boundaries and IDs locally.
Open Gemini tokenizerLLM API cost calculator
Estimate monthly LLM API spend from tokens, requests, and model prices.
Open cost calculatorContext window calculator
Check whether a prompt and planned output fit a model's tracked context window.
Check context fitPrompt caching cost
Model standard versus cached-input pricing for repeated prompt context.
Model cache savingsAI coding tools
Compare coding assistants by decision path
Jump to pricing, alternatives, and comparison pages for tools used in developer workflows.
Cursor
GitHub Copilot
Windsurf
Claude Code
Tabnine
Codeium
LLM API providers
Check provider pricing and tradeoffs
Use these pages to compare source-tracked pricing, provider alternatives, and API tradeoffs.
OpenAI API
Anthropic API
Google Gemini API
DeepSeek API
Planned StackLens guides
Cost control and routing
These areas are planned as practical guides. They are listed here without links until the pages exist.
Model routing
Planned guide
Prompt caching
Planned guide
LLM observability
Planned guide
Budget alerts
Planned guide
Usage logs
Planned guide