Vectors for search and RAG
Embeddings
Generate vector embeddings with OpenAI-compatible embedding models for semantic search, clustering and RAG.
POST /v1/embeddings
input:“refund for a duplicate charge”
BillingShippingAccount
01
OpenAI format
Drop into existing pipelines.
02
Many providers
Pick the model per index.
03
Batch input
Embed many texts in one call.
04
Tracked spend
Costs in the same dashboard.
Built for
Semantic search
Find by meaning, not keywords
RAG
Retrieve the right context
Clustering
Group similar tickets
Embed text
terminal
1curl 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 }'