OpenAI-Compatible Embeddings
Turn text into vectors for semantic search, clustering, and RAG — through the same gateway you already use for chat.
LLM Gateway now exposes an OpenAI-compatible /v1/embeddings endpoint. Same base URL, same API key, same SDK — point your existing OpenAI client at the gateway and embeddings.create() just works.
1curl -X POST "https://api.llmgateway.io/v1/embeddings" \2 -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "text-embedding-3-small",6 "input": "The quick brown fox jumps over the lazy dog."7 }'1curl -X POST "https://api.llmgateway.io/v1/embeddings" \2 -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "text-embedding-3-small",6 "input": "The quick brown fox jumps over the lazy dog."7 }'- Drop-in replacement for
openai.embeddings— no code changes if you're already on the OpenAI SDK - Use it for semantic search, clustering, recommendations, and RAG pipelines
- Billed on input tokens only — no output tokens, no surprises
- Full usage and cost tracking in your dashboard, alongside your chat traffic