Fetch vectors

For on-demand indexes, since vector values are retrieved from object storage, fetch operations may have increased latency. If you only need metadata or IDs, consider using the query operation with includeValues set to false instead.

For guidance and examples, see Fetch data.

# To get the unique host for an index,
# see https://docs.pinecone.io/guides/manage-data/target-an-index
PINECONE_API_KEY="YOUR_API_KEY"
INDEX_HOST="INDEX_HOST"

curl -X GET "https://$INDEX_HOST/vectors/fetch?ids=id-1&ids=id-2&namespace=example-namespace" \
  -H "Api-Key: $PINECONE_API_KEY" \
  -H "X-Pinecone-Api-Version: 2025-10"

{
  "vectors": {
    "id-1": {
      "id": "id-1",
      "values": [0.568879, 0.632687092, 0.856837332, ...]
    },
    "id-2": {
      "id": "id-2",
      "values": [0.00891787093, 0.581895, 0.315718859, ...]
    }
  },
  "namespace": "example-namespace",
  "usage": {"readUnits": 1},
}

GET /vectors/fetch

• X-Pinecone-Api-Version (header, string, required) — Required date-based version header
• ids (query, string[], required) — The vector IDs to fetch. Does not accept values containing spaces.
• namespace (query, string) — The namespace to fetch vectors from. If not provided, the default namespace is used.

• 200 — A successful response.
• 400 — Bad request. The request body included invalid request parameters.
• 4XX — An unexpected error response.
• 5XX — An unexpected error response.