Which model runs in our suite?
One from our catalog, for example Qwen3, Gemma 3, Mistral Small, Llama 3.3 or gpt-oss. The plan sets the upper size limit: up to 15B parameters in Suite S, 30B in Suite M, 60B or two models of up to 30B each in Suite L, and 120B in Suite Enterprise, where you can also run models you bring yourself.
