How many AI models does CoreWeave serve?
12 tracked models as of 11 August 2026: 12 language models (9 with a public ModelCap Index position), across 12 live endpoints observed through OpenRouter.
Inference provider
CoreWeave: AI models and API pricing
Every tracked model CoreWeave serves through OpenRouter, with CoreWeave'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
CoreWeave serves 12 tracked models through 12 endpoints as of 11 August 2026; the highest-ranked is GLM 5.2 (ModelCap Index #13); mean measured uptime is 99.70%.
Models served
12
On the ModelCap Index
9
Cheapest output price
$0.10/1M
Language models on CoreWeave (12)
Ranked models first, in ModelCap Index order. Prices are the lowest CoreWeave lists for the model; the endpoint count shows how many deployments carry it.
CoreWeave on ModelCap: common questions
What is the best model available on CoreWeave?
GLM 5.2 from Z.ai is the highest-ranked language model CoreWeave serves, at ModelCap Index position #13 and $2.42 per 1M output tokens on CoreWeave. The table lists every model in Index order.
What is the cheapest model on CoreWeave?
Granite 4.1 8B at $0.10 per 1M output tokens ($0.05 per 1M input), the lowest positive language-token price CoreWeave lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.
Which CoreWeave model has the largest context window?
GLM 5.2, served with a 262K-token context window on CoreWeave. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.
How reliable is CoreWeave?
Mean measured uptime across CoreWeave endpoints is 99.70% 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 CoreWeave prices come from?
From the OpenRouter catalogue entry for each CoreWeave endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where CoreWeave 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?
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.
Explore further
- All inference providers67 providers compared
- Cheapest LLMsRanked models by listed price
- Compare AI modelsHead-to-head on benchmarks, price and context
- GLM 5.2 vs Gemma 4 31BBoth served by CoreWeave
- Qwen3.6 27B vs Qwen3.6 35B A3BBoth served by CoreWeave
- GLM 5.2 on every providerHighest-ranked model CoreWeave serves