---
title: Limits and quotas
description: Every rate limit, size limit, expiration, and constraint in Avra Core in one place, with what happens when you reach each one.
---

This page gathers the limits in Avra Core: rate limits, sizes, URL lifetimes, and the constraints on batches, versions, and webhooks. Each table says what happens when you reach a limit and links to the page that explains it. Read it when you size an integration, and come back to it when a request is refused.

Some limits are exact and some are approximate. The prediction rate limit is enforced at Avra's network edge, so treat it as approximate. The others are enforced by the API itself, and the error tells you which one you reached.

## Time windows at a glance

Several of Core's limits are lengths of time. They range from the 10 seconds a key stays blocked after a rate-limited prediction to the hour an upload URL stays valid.

<svg class="fig" viewBox="0 0 640 236" role="img" aria-label="Six bars on a logarithmic time scale from 1 second to 1 hour: rate-limit block, 10 seconds; prediction timeout, 30 seconds; signature tolerance, 5 minutes; result URL, 15 minutes; key rotation overlap, 30 minutes; upload URL, 1 hour.">
  <text class="small end" x="190" y="42">Rate-limit block</text>
  <rect class="soft" x="200" y="30" width="101" height="16" rx="3" />
  <text class="small label" x="309" y="42">10 s</text>
  <text class="small end" x="190" y="70">Prediction timeout</text>
  <rect class="soft" x="200" y="58" width="149.5" height="16" rx="3" />
  <text class="small label" x="357.5" y="70">30 s</text>
  <text class="small end" x="190" y="98">Signature tolerance</text>
  <rect class="soft dash" x="200" y="86" width="250.7" height="16" rx="3" />
  <text class="small label" x="458.7" y="98">5 min, suggested</text>
  <text class="small end" x="190" y="126">Result URL</text>
  <rect class="soft" x="200" y="114" width="298.9" height="16" rx="3" />
  <text class="small label" x="506.9" y="126">15 min</text>
  <text class="small end" x="190" y="154">Key rotation overlap</text>
  <rect class="soft" x="200" y="142" width="329.4" height="16" rx="3" />
  <text class="small label" x="537.4" y="154">30 min</text>
  <text class="small end" x="190" y="182">Upload URL</text>
  <rect class="solid" x="200" y="170" width="360" height="16" rx="3" />
  <text class="small label" x="568" y="182">1 hour</text>
  <line class="rule" x1="200" y1="200" x2="560" y2="200" />
  <line class="rule" x1="200" y1="196" x2="200" y2="204" />
  <line class="rule" x1="301" y1="196" x2="301" y2="204" />
  <line class="rule" x1="380" y1="196" x2="380" y2="204" />
  <line class="rule" x1="481" y1="196" x2="481" y2="204" />
  <line class="rule" x1="560" y1="196" x2="560" y2="204" />
  <text class="small label mid" x="200" y="220">1 s</text>
  <text class="small label mid" x="301" y="220">10 s</text>
  <text class="small label mid" x="380" y="220">1 min</text>
  <text class="small label mid" x="481" y="220">10 min</text>
  <text class="small label mid" x="560" y="220">1 hour</text>
</svg>

How long each window lasts, on a logarithmic scale. The 5-minute signature window is a suggested default for your webhook receiver; the others are set by Avra.

When a limit refuses a request, the error names it. Wait at least 10 seconds after a `429` on a prediction, and the seconds in `Retry-After` after a `429` on the files endpoints. Retry a timed-out prediction with backoff, split an upload request that has too many files, wait for a batch to complete or fail before you ask for its result, and request a new URL when one expires.

## Live predictions

| Limit | Value | When you reach it | Details |
|---|---|---|---|
| **Requests per API key** | About 100 per 10 seconds | `429` with `rate_limited`, and the key is blocked for 10 seconds | [Live predictions](/pt-BR/core/predictions#limits) |
| **Records per request** | One | Send more records through a batch | [Batch inference](/pt-BR/core/batch-inference) |
| **Time to answer** | 30 seconds | `500` with `prediction timed out` | [Handle errors](/pt-BR/core/predictions#handle-errors) |

Batch jobs don't count against the prediction rate limit. For anything more than a few thousand records at once, use batch inference.

## Files and uploads

| Limit | Value | When you reach it | Details |
|---|---|---|---|
| **Files endpoints, per organization** | 1,500 requests per minute | `429` with `too many requests`, and a `Retry-After` header with the seconds to wait | [Batch inference](/pt-BR/core/batch-inference#limits-and-practices-that-help) |
| **Files endpoints, per caller** | 300 requests per minute for each API key, and for each member in the dashboard | The same `429` | [Batch inference](/pt-BR/core/batch-inference#limits-and-practices-that-help) |
| **Files per upload request** | 1,000 | `400` with `too many files in one request` | [Prepare the input files](/pt-BR/core/batch-inference#prepare-the-input-files) |
| **Upload URL lifetime** | 1 hour, until the `expiration` in the response | The upload is refused. Request new URLs | [Batch inference](/pt-BR/core/batch-inference#run-a-batch-from-python) |
| **Checksum** | A base64-encoded, 128-bit MD5 digest for every file | `400` with `md5 must be a base64-encoded 128-bit digest` | [Prepare the input files](/pt-BR/core/batch-inference#prepare-the-input-files) |

The files endpoints are `/v1/api/files/*`: requesting upload URLs and listing uploaded files.

## Batches

| Limit | Value | When you reach it | Details |
|---|---|---|---|
| **Availability** | Enabled per organization | Ask your Avra team to turn it on | [Batch inference](/pt-BR/core/batch-inference) |
| **File formats** | Parquet or CSV, one format for every file in a batch | `400` with `batch input files must all have the same format` | [Prepare the input files](/pt-BR/core/batch-inference#prepare-the-input-files) |
| **Parquet layout** | At most 100k rows per row group and 5 GB per file, as guidance | Very large jobs may need sizing beforehand, so reach out to your Avra team | [Prepare the input files](/pt-BR/core/batch-inference#prepare-the-input-files) |
| **Reference date** | A `YYYY-MM-DD` date. In the dashboard, up to two years back | `400` with `invalid reference date` | [Run a batch from the dashboard](/pt-BR/core/batch-inference#run-a-batch-from-the-dashboard) |
| **Result availability** | Once the batch has completed or failed | `409` with `batch result is not ready` | [Download the result](/pt-BR/core/batch-inference#download-the-result) |
| **Result URL lifetime** | 15 minutes, until the `expires_at` in the response | Request the result again for a new URL | [Download the result](/pt-BR/core/batch-inference#download-the-result) |
| **Cancellation** | Not available through the v2 API | Contact Avra support to stop a batch | [Batch statuses](/pt-BR/core/batch-inference#batch-statuses) |

Batches run in queues with resource quotas, so a batch can wait as `queued` before it runs.

## Versions and aliases

| Limit | Value | When you reach it | Details |
|---|---|---|---|
| **Aliases per version** | One | `409` with `model version already has an alias`. Remove the version's alias first | [Promote and roll back](/pt-BR/core/model-versioning#promote-and-roll-back) |
| **Versions per alias** | One, per model, across your organization | `409` with `model alias already in use`, unless you reassign it | [Aliases](/pt-BR/core/model-versioning#aliases) |
| **Alias names** | Lowercase letters, digits, and hyphens | Other characters are converted or dropped | [Aliases](/pt-BR/core/model-versioning#aliases) |
| **Versions that serve calls** | Active versions only | `400` with `model version is not active` | [The life of a version](/pt-BR/core/model-versioning#the-life-of-a-version) |

## Webhooks

| Limit | Value | When you reach it | Details |
|---|---|---|---|
| **Delivery** | At least once | The same event can arrive more than once. Deduplicate on `idempotency_key` | [Retries](/pt-BR/core/webhooks#retries) |
| **Retries** | With exponential backoff, after a non-2xx response or a timeout | Once the retries run out, the delivery is marked failed and can be replayed | [Retries](/pt-BR/core/webhooks#retries) |
| **Signature timestamp** | Reject deliveries outside your tolerance window; 5 minutes is a sensible default | Your receiver refuses the delivery | [Verify deliveries](/pt-BR/core/webhooks#verify-deliveries) |
| **Scope** | Your whole organization | Endpoints receive the organization's events | [Configure endpoints](/pt-BR/core/webhooks#configure-endpoints) |

## API keys and embeddings

| Limit | Value | Details |
|---|---|---|
| **API key scope** | One workspace | [Live predictions](/pt-BR/core/predictions#before-you-start) |
| **Rotation overlap** | The old key can keep working for up to 30 minutes after a rotation | [API reference](/api-reference) |
| **Embedding dimensions** | 1024, shortened only to 512, 256, 128, 64, 32, or 16 | [Technical guide](/pt-BR/gfm/embeddings/technical-implementation) |

## Requesting a higher limit

If your production traffic needs more, contact your Avra account manager with your expected request volume and traffic pattern. For large batch jobs, reach out before you send them, so your Avra team can size the job.

## Where to go next

**[Live predictions](/pt-BR/core/predictions)**

Retry with backoff after a `429`.

**[Batch inference](/pt-BR/core/batch-inference)**

Upload, run, and download within the limits.

**[Webhooks](/pt-BR/core/webhooks)**

Handle retries and duplicate deliveries.

**[API reference](/api-reference)**

Every endpoint and status code.
