How many AI models does Nebius serve?
19 tracked models as of 19 November 2026: 19 language models (16 with a public ModelCap Index position), across 19 live endpoints observed through OpenRouter.
Inference provider
Every tracked model Nebius serves through OpenRouter, with Nebius's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Models with a position on a ModelCap board link to their model page, where every provider's deployment is listed side by side.
Snapshot as of 19 November 2026
Nebius serves 19 tracked models through 19 endpoints as of 19 November 2026; the highest-ranked is Kimi K3.1 Pro (ModelCap Index #11); mean measured uptime is 100.0%.
Ranked models first, in ModelCap Index order. Prices are the lowest Nebius lists for the model; the endpoint count shows how many deployments carry it.
19 tracked models as of 19 November 2026: 19 language models (16 with a public ModelCap Index position), across 19 live endpoints observed through OpenRouter.
Kimi K3.1 Pro from Moonshot AI is the highest-ranked language model Nebius serves, at ModelCap Index position #11 and $10.00 per 1M output tokens on Nebius. The table lists every model in Index order.
Nemotron 3 Nano 30B A3B at $0.24 per 1M output tokens ($0.06 per 1M input), the lowest positive language-token price Nebius lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.
Kimi K3.1 Pro, served with a 1M-token context window on Nebius. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.
Mean measured uptime across Nebius 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 Nebius endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Nebius exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.
This page uses the published ModelCap snapshot dated 19 November 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.