Browse docs
Overview
POST /v1/embeddings creates vector embeddings through Aurora's provider routing. The request goes through alias resolution, workflow matching, and cache checks.
Request
text
curl http://your-aurora-host/v1/embeddings \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $AURORA_MASTER_KEY" \
-d '{
"model": "text-embedding-3-small",
"input": "The quick brown fox jumps over the lazy dog."
}'
Parameters
Response
text
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [0.0023, -0.0091, ...]
}
],
"model": "text-embedding-3-small",
"usage": {
"prompt_tokens": 8,
"total_tokens": 8
}
}
Notes
- Embedding requests go through workflow matching, so cache policies and usage tracking apply
- Failover currently applies to chat/responses endpoints, not embeddings
- Provider pools with the same embedding model work for load distribution