Live pricing for 232+ models, refreshed automatically, plus calculators that turn token prices into real‑world齐 workloads. API Cost Calculator lets you compare any workload across all models, applying caching and batch discounts. Chatbot Cost simulates real conversations, growing history, resent context, and cache hits.

Agent Cost shows multi‑step loops, tool schemas, and retries—why agents can cost 10–30× more. RAG Cost separates indexing, retrieval, and generation; embeddings are pennies. Voice AI Cost breaks down STT, LLM, and TTS per minute, call, month.

GPU Rental Pricing lists H100, A100, RTX 4090 across 10 providers, showing a 5× price spread. Image API Pricing ranges from $0.003 to $0.17 per image, with three market tiers and a batch calculator. Token Counter gives tokens and cost in the browser.

Cost‑Cutting Guides explain prompt caching (−90% input) and the Batch API (−50% everything). The flagship model pricing per 1M tokens is updated 2026‑08‑02. How AI API pricing works: you pay per token—roughly ¾ of a word—with separate rates for input and output; output is usually 3–5× more expensive.

Prompt caching cuts repeated input costs by up to 90%; batch processing slashes costs by ~50%.