Learn how to put your digital team to work with MuleSoft for Agentforce.
Register now
Contact Us 1-800-596-4880
  1. Homepage
  2. IDP

  3. Supported Models

Supported Models

Einstein supports these predictive multimodal models:

  • OpenAI’s GPT-4o (gpt-4o-2024-08-06) LLM

  • OpenAI’s GPT-4o Mini (gpt-4o-mini-2024-07-18) LLM

  • Google’s GEMINI-2.0 Flash 001 LLM

When creating a document action, you can select the model and extraction settings such as PII masking or image recognition. Each model performs differently under various conditions, so select the one that aligns with your specific requirements.

Model Name Description Stability Image Recognition Prompt Output Limits Notes

Einstein OpenAI GPT-4o 0806

Suitable for most tasks, performing well on documents in non-Latin languages. Can compare font sizes and identify certain font styles.

High

  • Standard performance

  • Standard credit consumption

  • Low accuracy on reading checkboxes in forms

~4,000 words

  • Ask the model to not make up information to prevent hallucinations.

  • List of languages supported by OpenAI models.

Einstein OpenAI GPT-4o Mini 0718

Fast and useful for focused tasks. Tends to exhibit lazy reasoning.

High

  • Standard performance

  • High credit consumption

  • Low accuracy on reading checkboxes in forms

~4,000 words

  • Ask the model to not make up information to prevent hallucinations.

  • List of languages supported by OpenAI models.

Einstein GEMINI-2.0 Flash 001

Best for analyzing images given its lower credit consumption and increased accuracy in this type of documents.

Standard

  • Low credit consumption

  • High accuracy on reading checkboxes in forms

~6,000 words

  • Currently, the Gemini model doesn’t show an accurate confidence score and is set to 80% by default.

  • For the Einstein generic document action with customized schema, errors such as LLM Generation wasn’t a valid JSON might occur. In such cases, create a new generic document action without a customized schema to obtain results.

  • List of languages supported by Gemini models.

Model Errors

In some scenarios, the LLMs stop generating a response and provide an error code to understand the reason that caused this behavior. If the error occurs during the execution of a document action, IDP provides this error in the statusMessage attribute of the response object.

These are some of the most common error codes and their suggested fixes:

Error Code Error Description Suggested Fix

length

The request exceeded the maximum input token limit.

See Using long context under GPT-4.1 prompting best practices to understand how to refine your prompts.

MAX_TOKENS

The response exceeded the maximum output token limit.

Split the document or select an OpenAI model for this extraction.

SPII

The document potentially contains Sensitive Personally Identifiable Information (SPII).

Delete the conflicting field, or use GPT models to abstract the information.

For a complete list of error codes, refer to each of the model provider’s documentation:

See Also