---
title: Rate limits
description: Learn about rate limits for Elastic Inference Service (EIS) models.
url: https://www.elastic.co/elastic/docs-builder/docs/4089/explore-analyze/elastic-inference/eis-rate-limits
applies_to:
  - Elastic Cloud Serverless: Generally available
  - Elastic Stack: Generally available
---

# Rate limits
This page lists the rate limits that apply to Elastic Inference Service (EIS) models.
Exceeding a limit results in HTTP 429 responses from the server until the sliding window moves on further and parts of the limit resets.
Where both a requests-per-minute and a tokens-per-minute limit apply, whichever limit is reached first takes effect.

## Chat models


| Model                                                                                      | Requests/minute | Notes                   |
|--------------------------------------------------------------------------------------------|-----------------|-------------------------|
| Elastic Managed LLMs <applies-to>Elastic Stack: Generally available since 9.3</applies-to> | 2,000           | No rate limit on tokens |


## Embedding models

Embedding models are used for both ingest (indexing documents) and search (query-time retrieval). Limits apply independently per use.

| Model                                                                                          | Requests/minute (search) | Requests/minute (ingest) | Tokens/minute (search) | Tokens/minute (ingest) |
|------------------------------------------------------------------------------------------------|--------------------------|--------------------------|------------------------|------------------------|
| ELSER <applies-to>Elastic Stack: Generally available since 9.0</applies-to>                    | 6,000                    | 6,000                    | 600,000                | 6,000,000              |
| Jina Embeddings v3 <applies-to>Elastic Stack: Generally available since 9.3</applies-to>       | 6,000                    | 6,000                    | 600,000                | 6,000,000              |
| Jina Embeddings v5 Nano <applies-to>Elastic Stack: Generally available since 9.3</applies-to>  | 60,000                   | 30,000                   | 6,000,000              | 30,000,000             |
| Jina Embeddings v5 Small <applies-to>Elastic Stack: Generally available since 9.3</applies-to> | 60,000                   | 30,000                   | 6,000,000              | 30,000,000             |


## Reranking models

Reranking models are used at search time only.

| Model                                                                                    | Requests/minute | Tokens/minute |
|------------------------------------------------------------------------------------------|-----------------|---------------|
| Jina Reranker v2 <applies-to>Elastic Stack: Generally available since 9.3</applies-to>   | 600             | 6,000,000     |
| Jina Reranker v3 <applies-to>Elastic Stack: Generally available since 9.3</applies-to>   | 600             | 6,000,000     |
| Jina Reranker v3.5 <applies-to>Elastic Stack: Generally available since 9.5</applies-to> | 600             | 6,000,000     |