# PromptSpend: LLM API cost estimator

> Estimate what an LLM API workload will cost across 131 models from 16 providers.
> Every price names its source and the date it was last confirmed. Free, open source, no accounts.

This is the markdown version of https://promptspend.com/, written for AI agents. Catalog behind this build: 2026-11-18T19:15:12.088Z.

## What it does

The calculator at https://promptspend.com/ prices a real workload: conversation length, prompt
caching, batch discounts and reasoning overhead, on any model in the catalog, and
compares the monthly bill across models side by side.

**All rates are USD per 1,000,000 tokens**, standard tier, global endpoint, list
price. Regional and data-residency premiums, priority tiers, server-side tool
fees and negotiated discounts are **not** included.

These are list prices, not a quote.
Check the vendor before committing money to a number.

## Where to look

- [Every model, by price](https://promptspend.com/models/): the whole catalog, cheapest first
- [By provider](https://promptspend.com/providers/): 16 providers
- [Head-to-head comparisons](https://promptspend.com/compare/): 229 pairs costed on the same workloads
- [PromptSpend Receipt](https://promptspend.com/receipt/): a visible, one-response cost-audit object to paste into a conversation
- [llms.txt](https://promptspend.com/llms.txt): the short index for AI assistants
- [llms-full.txt](https://promptspend.com/llms-full.txt): the full catalog as one markdown table

## For programs and coding tools

- [Pricing API](https://promptspend.dev): keyless, CORS-open, OpenAPI 3.1 described
- [Raw catalog](https://promptspend.com/data/pricing.json)
- [MCP server](https://www.npmjs.com/package/@promptspend/mcp): `claude mcp add promptspend -- npx -y @promptspend/mcp`; hosted at https://promptspend.dev/mcp
- [Agent Skill](https://github.com/AndrewAvery7/promptspend/tree/main/skills)

Prefer the API or the MCP server over scraping pages.
