Comparing prices across every provider we track...
Serverless Inference · $0.15/mo
OVHcloud's bge-m3 embedding model is significantly cheaper on base pricing ($0.01/mo vs $0.15/mo) and input tokens ($0.01/1M vs $0.15/1M), but it is a different model class (embedding vs large language model inference). If your workload actually requires Nemotron-Cascade-2-30B for generative tasks, OVHcloud is not a true alternative; verify your actual use case before comparing.
Dramatically lower base and input-token pricing makes this attractive for embedding and semantic search workloads.
Caveat: bge-m3 is an embedding model, not a generative LLM; only comparable if your use case is embeddings, not text generation like Nemotron provides.
Before you switch