How many AI models does Moonshot AI serve?
4 tracked models as of 11 August 2026: 4 language models (2 with a public ModelCap Index position), across 5 live endpoints observed through OpenRouter.
Inference provider
Every tracked model Moonshot AI serves through OpenRouter, with Moonshot AI'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 11 August 2026
Moonshot AI serves 4 tracked models through 5 endpoints as of 11 August 2026; the highest-ranked is Kimi K3 (ModelCap Index #4); mean measured uptime is 100.0%.
Ranked models first, in ModelCap Index order. Prices are the lowest Moonshot AI lists for the model; the endpoint count shows how many deployments carry it.
4 tracked models as of 11 August 2026: 4 language models (2 with a public ModelCap Index position), across 5 live endpoints observed through OpenRouter.
Kimi K3 from Moonshot AI is the highest-ranked language model Moonshot AI serves, at ModelCap Index position #4 and $15.00 per 1M output tokens on Moonshot AI. The table lists every model in Index order.
Kimi K2.5 at $3.00 per 1M output tokens ($0.60 per 1M input), the lowest positive language-token price Moonshot AI lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.
Kimi K3, served with a 1M-token context window on Moonshot AI. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.
Mean measured uptime across Moonshot AI 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.
From the OpenRouter catalogue entry for each Moonshot AI endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Moonshot AI exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.
It re-renders within a minute of every dataset refresh; this snapshot was published 11 August 2026. Offers retained from a failed refresh are marked stale in the data and are not counted here.