What's free
Starter (free) plan: 5M tokens/mo for embedding models (llama-text-embed-v2, multilingual-e5-large) and 500 requests/mo for the bge-reranker-v2-m3 rerank model
Rate limits
5M embedding tokens/mo; 500 rerank requests/mo on Starter
The catch
Free rerank limited to bge-reranker-v2-m3; overages are pay-as-you-go. Not OpenAI-compatible. No card required.