---
schema_version: "1"
id: 5d8c2ae1b7ac5e557abc8cc1398258b035983ee5bada2ddab1c2c772259342f3
title: Rate Limits for Models API
collection: developer
version: current
locale: en-us
portal_url: https://docs.salesforce.com/developer/current/en-us/genai/agentforce/guides/models/models-api/models-api-rate-limits.md
canonical_url: https://developer.salesforce.com/docs/ai/agentforce/guide/models-api-rate-limits.html
source_site: developer.salesforce.com
content_type: documentation
content_hash: 101f0f01e870f0eeb9ba2f493f7c0d9b0510fa53c63a9de6c6e970c87d806d78
products:
  - Agentforce Developer Guide
  - Agentforce and Einstein Generative AI
---
# Rate Limits for Models API

The Models API has a standard rate limit for all requests except for requests made via Apex methods in sandbox, demo, and trial orgs. When calling the Models API through Apex in a sandbox, demo, or trial org there are different limits.

## Production Orgs

There’s a rate limit of 2,000 LLM generation requests per minute (RPM) per org for each REST endpoint (or equivalent Apex method) in production orgs. However, depending on a model’s usage and the available capacity from model providers, the RPM limit can vary by model. For the RPM limit per org for individual models, see [Large Language Model Limits](https://help.salesforce.com/s/articleView?id=ai.generative_ai_llm_limits.htm) in Salesforce Help.

The Embeddings and Feedback capabilities have a rate limit of 1,000 requests per minute per org (for embeddings or feedback).

If a rate limit is exceeded, the Models API returns a response with a `429` status and an error object.

To request a rate limit increase, reach out to your Salesforce account executive.

The Apex methods of the Models API are also subject to the Apex [Callout Limits and Limitations](https://developer.salesforce.com/docs/atlas.en-us.apexcode.meta/apexcode/apex_callouts_timeouts.htm).

All Models API requests are subject to Salesforce’s usage and billing rates. See [Agentforce and Generative AI Usage and Billing](https://help.salesforce.com/s/articleView?id=ai.generative_ai_usage.htm).

## Sandbox, Demo, and Trial Orgs

The following limits only apply to requests made through Apex methods in sandbox, demo, and trial orgs. Sandbox, demo, and trial orgs using the Models REST API are subject to the above limit for requests per minute per org for each REST endpoint.

**Sandbox Orgs**

The rate limit value for Apex methods in a sandbox is 500 requests per hour.

**note:** A request from the Agentforce reasoning engine to the Models API in a sandbox is not rate limited. This behavior is a known issue and may change at any time.

**Demo and Trial Orgs**

The rate limit value for Apex methods in a demo or trial org is 150 requests per hour.

## See Also

- _Models API Developer Guide_: [Access Models API with REST](https://developer.salesforce.com/docs/ai/agentforce/guide/access-models-api-with-rest.md)
- _Models API Developer Guide_: [Access Models API with Apex](https://developer.salesforce.com/docs/ai/agentforce/guide/access-models-api-with-apex.md)
- [Supported Models](https://developer.salesforce.com/docs/ai/agentforce/supported-models.md)