How many AI models does Cerebras serve?
2 tracked models as of 2 October 2026: 2 language models (2 with a public ModelCap Index position), across 2 live endpoints observed through OpenRouter.
Inference provider
Cerebras: AI models and API pricing
Every tracked model Cerebras serves through OpenRouter, with Cerebras'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
Cerebras serves 2 tracked models through 2 endpoints as of 2 October 2026; the highest-ranked is Qwen3.8 27B (ModelCap Index #39); mean measured uptime is 99.93%.
Models served
2
On the ModelCap Index
2
Cheapest output price
$0.75/1M
Language models on Cerebras (2)
Ranked models first, in ModelCap Index order. Prices are the lowest Cerebras lists for the model; the endpoint count shows how many deployments carry it.
Cerebras on ModelCap: common questions
What is the best model available on Cerebras?
Qwen3.8 27B from Qwen is the highest-ranked language model Cerebras serves, at ModelCap Index position #39 and $1.49 per 1M output tokens on Cerebras. The table lists every model in Index order.
What is the cheapest model on Cerebras?
gpt-oss-120b at $0.75 per 1M output tokens ($0.35 per 1M input), the lowest positive language-token price Cerebras lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.
Which Cerebras model has the largest context window?
gpt-oss-120b, served with a 131K-token context window on Cerebras. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.
How reliable is Cerebras?
Mean measured uptime across Cerebras endpoints is 99.93% 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 Cerebras prices come from?
From the OpenRouter catalogue entry for each Cerebras endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Cerebras 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.