Language model prices

517 models, priced at every host that sells them. The cheapest model that scores 70% on GPQA Diamond is GLM 5.3 Flash at $0.054 per 1M tokens on Openinference.

ContextReads imagesHas a quality score

517 models. Prices are the cheapest host’s list price per 1M tokens.

How many times more the dearest host asks than the cheapest, for the same model, per 1M input tokens. Models with three or more hosts, compared only with hosts that serve the same stated precision (fp8 with fp8).

Blended price: three input tokens for every output token, per 1M tokens. Arena is the LMArena text rating; GPQA is the Epoch AI GPQA Diamond score. 180 models have three or more hosts.Show every listed variant (1,493)CSV

Quality data: LMArena (CC BY 4.0), Epoch AI (CC BY 4.0). Prices: OpenRouter, LiteLLM (MIT), provider pages. List prices in US dollars before discounts and taxes; other currencies converted at the European Central Bank reference rate. The figures on these pages are free to reuse under CC BY 4.0 with a link to this page.