ZeroReader BGE Small EN v1.5 Embedding

Choose this endpoint when you need fast, cost-efficient English text embeddings and latency or throughput matters more than maximum quality. Prefer the BGE Large EN v1.5 sibling when embedding quality is paramount. Use this model for high-volume RAG chunking, real-time semantic search, or resource-constrained pipelines where the small model's speed advantage is valuable.

• Empty or missing 'text' field returns a 400 validation error
• Input text exceeding model token limit may be truncated or return an error
• Network timeout for very large batches of strings
• Payment failure via x402 protocol results in 402 response blocking the call
• Non-English text may produce lower-quality embeddings due to model training scope