AI Tools
Plan and budget LLM projects in your browser. Check whether a model fits your GPU with the LLM VRAM Calculator, work out KV cache and multi-GPU memory, count tokens, plan context windows and RAG chunk sizes, and compare API prices, prompt caching and batch savings. Results are estimates based on the numbers you enter, so confirm current model details and prices with the provider before you commit. Use the topics below to jump straight to the right tool.
Browse by topic
LLM Hardware & Memory
Tokens & Context
API Cost & Savings
RAG & Vector Storage
All tools in this category
LLM VRAM CalculatorEstimate the memory a large language model needs: weights, KV cache and runtime overhead from parameters, quantization and context length.AI ToolsCan My PC Run This LLM?Check whether a model fits your GPU VRAM, unified memory or system RAM, with the headroom or shortfall and a smaller quantization to try.AI ToolsLLM Model Size & Quantization CalculatorCalculate a modelโs weight or file size across FP32, FP16, BF16, INT8 and Q8โQ2 quantization, in GB and GiB.AI ToolsKV Cache Memory CalculatorEstimate KV-cache memory from layers, KV heads, head dimension, context length, precision and batch size, and see what grouped-query attention saves.AI ToolsMulti-GPU LLM Memory PlannerPlan whether a model fits across several GPUs: pooled memory, per-GPU allocation, layer or tensor split, and what pooled VRAM does not guarantee.AI ToolsAI Token Counter & EstimatorCount characters and words and estimate AI tokens for prompts and documents, or get exact OpenAI tokenizer counts, privately in your browser.AI ToolsAI Context Window Budget PlannerPlan how a context window is shared between system prompt, conversation, documents, tools and the reply, with remaining space and overflow warnings.AI ToolsDocument to Context Capacity CalculatorEstimate how many pages, words, characters or documents fit in an AI context window, with conservative, typical and optimistic ranges.AI ToolsAI Prompt Cost ComparatorCompare what the same prompt and reply token workload costs across dated AI model price presets or your own prices, sorted from cheapest.AI ToolsAI API Cost CalculatorEstimate AI API spend per request, per day, per month and per year from token counts, request volume and per-million-token prices.AI ToolsRAG Chunk Size PlannerPlan how many chunks a document corpus becomes for a chunk size and overlap, with stride, duplicated tokens, embedding volume and storage.AI ToolsEmbedding Storage CalculatorCalculate raw embedding storage from vector count, dimensions and precision (FP32, FP16, INT8, binary or custom), in GB and GiB.AI ToolsVector Database Size EstimatorEstimate vector database footprint from vector count, dimensions, precision, metadata, index overhead and replicas, with raw vectors kept separate.AI ToolsRAG Context Budget CalculatorWork out how many retrieved chunks fit in an LLM context window after the prompt, history, tools, reply and a safety margin.AI ToolsFine-Tuning Dataset Token EstimatorEstimate the tokens in a fine-tuning dataset from examples and average tokens, multiply by epochs and, with your own price, estimate training cost.AI ToolsAI Agent Run Cost CalculatorEstimate what a multi-step AI agent run costs from model calls, steps, tokens per call and tool overhead, then per day, month and year.AI ToolsMCP Tool Schema Token Overhead CalculatorEstimate the context and cost overhead of MCP and tool definitions: tokens per tool, share of the context window and daily or monthly cost.AI ToolsPrompt Cache Savings CalculatorEstimate what prompt caching saves from the reusable prefix, hit rate and cache-read and cache-write prices, with break-even.AI ToolsBatch AI Cost Savings CalculatorCompare standard synchronous AI pricing with batch or offline pricing for the same jobs: totals, savings and cost per job.AI ToolsAI Inference Time & Throughput EstimatorEstimate how long an AI response takes from your measured prefill and generation speeds, plus effective tokens per second and requests per minute.AI Tools