Sign in

v16

latestOpenAPI 3.1.0raw.githubusercontent.com2026-03-032765158.3 KB
Models

Rerank

Reranks the provided documents, according to the provided query.

The results will be sorted by descending order of relevance. For each document, the index and the score will be returned. The index is relative to the documents array that was passed in. The score is the query-document relevancy determined by the reranker model. The results will be returned in descending order of relevance.

Organizations will, by default, have a ratelimit of 2,500,000 bytes-per-minute and 1000 QPM. Ratelimits are refreshed every 15 seconds. If this is exceeded, requests will be throttled into latency: "slow" mode, up to 20,000,000 bytes-per-minute. If even this is exceeded, you will get a 429 error. To request higher ratelimits, please contact founders@zeroentropy.dev or message us on Discord or Slack!

post/models/rerank

Request body

modelstring required

The model ID to use for reranking. Options are: ["zerank-2", "zerank-1", "zerank-1-small"]

querystring required

The query to rerank the documents by.

top_ninteger nullable

If provided, then only the top n documents will be returned in the results array. Otherwise, n will be the length of the provided documents array.

documentsstring[] required

The list of documents to rerank. Each document is a string.

latency'fast' | 'slow' nullable

Whether the call will be inferenced "fast" or "slow". RateLimits for slow API calls are orders of magnitude higher, but you can expect >10 second latency. Fast inferences are guaranteed subsecond, but rate limits are lower. If not specified, first a "fast" call will be attempted, but if you have exceeded your fast rate limit, then a slow call will be executed. If explicitly set to "fast", then 429 will be returned if it cannot be executed fast.

Response

Successful Response

total_bytesinteger required

The total number of bytes in the request. This is used for ratelimiting.

total_tokensinteger required

The total number of tokens in the request. This is used for billing.

actual_latency_mode'fast' | 'slow' required

The type of inference actually used. If auto is requested, then fast will be used by default, with slow as a fallback if your ratelimit is exceeded. Else, this field will be identical to the requested latency mode.

e2e_latencynumber required

The total time, in seconds, between rerank request received and rerank response returned. Client latency should equal e2e_latency + your ping to ZeroEntropy's API.

inference_latencynumber required

The time, in seconds, to actually inference the request. If this is significantly lower than e2e_latency, this is likely due to ratelimiting. Please request a higher ratelimit at founders@zeroentropy.dev or message us on Discord or Slack!