How many AI models does Liquid serve?
1 tracked model as of 2 October 2026: 1 language model, across 1 live endpoint observed through OpenRouter.
Inference provider
Liquid: AI models and API pricing
Every tracked model Liquid serves through OpenRouter, with Liquid's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.
Snapshot as of 2 October 2026
Liquid serves 1 tracked model through 1 endpoint as of 2 October 2026; mean measured uptime is 100.0%.
Models served
1
On the ModelCap Index
0
Cheapest output price
—
Language models on Liquid (1)
Ranked models first, in ModelCap Index order. Prices are the lowest Liquid lists for the model; the endpoint count shows how many deployments carry it.
Liquid on ModelCap: common questions
What is the best model available on Liquid?
None of the Liquid models currently holds a public ModelCap Index position; the table lists them alphabetically.
What is the cheapest model on Liquid?
Liquid lists no positive language-token price in the current snapshot.
Which Liquid model has the largest context window?
LFM2.5-2.6B, served with a 66K-token context window on Liquid. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.
How reliable is Liquid?
Mean measured uptime across Liquid endpoints is 100.0% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.
Where do the Liquid prices come from?
From the OpenRouter catalogue entry for each Liquid endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Liquid exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.
How current is this page?
This page uses the published ModelCap snapshot dated 2 October 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.