TokenPricing

TokenPricing is a free, independent LLM API pricing comparison site. It tracks 625 models across 236 providers and shows input, output and cached token pricing in USD per 1 million tokens, so official developer prices, cloud listings and third-party API offers can be compared side by side. No signup or login is needed. Each offer links to the page where its pricing was published. The first row for each model is its base rate; other rows are additional published provider pricing. Missing pricing stays unknown instead of being shown as zero, and only active, standard base token rates are included. Batch, region-specific, VIP-group and token-tier offers are excluded, and price outliers are kept out of price summaries until verified. Each model page lists the official rate next to additional provider offers, with context window, capability tags, cache write, batch and web search charges where published, plus speed and uptime when a source reports them. A chart plots input against output price so the cheapest providers are easy to spot, and the homepage table can be filtered by 30 days, 90 days or all time. The pricing calculator turns input tokens, output tokens, requests per month and cache hit rate into an estimated monthly bill and cost per request, using published model pricing or your own custom rates. It splits the bill into uncached input, cached input and output, offers Chat app, AI agent and High volume presets, and compares the same workload across other offers. A pricing guide explains tokens, per-million conversion and prompt-cache pricing. The catalog is checked daily. Use TokenPricing to find the cheapest provider for a model, see how prompt caching changes the bill, or budget an AI app or agent before launch. The site is free, with no paid plans, and no signup is required.