Rerank - Planck

Endpoint

POST https://api.inquantum.ai/v1/rerank

Request

Field	Type	Required	Description
`model`	string	Yes	Exact rerank model ID from the model registry.
`query`	string	Yes	Non-empty query used to rank the documents.
`documents`	string[] or object[]	Yes	Non-empty candidates. Objects must contain a non-empty `text` field.
`top_n`	integer	No	Maximum number of results to return.
`return_documents`	boolean	No	Include document text in normalized results.
`task`	string	No	Optional task instruction for providers that support it.

curl https://api.inquantum.ai/v1/rerank \
  -H "Authorization: Bearer $PLANCK_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "fireworks/qwen3-reranker-8b",
    "query": "How do I reset my API key?",
    "documents": [
      "Open the API Keys page and select Rotate key.",
      "Invoices are available from the Billing page."
    ],
    "top_n": 1,
    "return_documents": true
  }'

Response

{
  "id": "request-id",
  "object": "list",
  "model": "accounts/fireworks/models/qwen3-reranker-8b",
  "provider": "fireworks",
  "results": [
    {
      "index": 0,
      "relevance_score": 0.98,
      "document": {
        "text": "Open the API Keys page and select Rotate key."
      }
    }
  ],
  "usage": {
    "input_tokens": 24
  }
}

See the Reranking guide for provider selection, BYOK behavior, and tracking.

This endpoint uses the shared AI Gateway error envelope. See the Error Handling & Fallback guide for response examples, retry rules, fallback behavior, and streaming errors.