WOLFRAM

Wolfram Language & System Documentation Center

LLMFunction[prompt]

represents a template for a large language model (LLM) prompt.

LLMFunction[{prompt1,prompt2,…}]

represents a combination of multiple prompts.

LLMFunction[prompt,form]

includes the interpreter form to apply to the response.

LLMFunction[…][params]

give the LLM service response for prompt applied to parameters params.

Details and Options
Details and Options Details and Options
Examples  
Basic Examples  
Scope  
Options  
Authentication  
LLMEvaluator  
Properties & Relations  
See Also
Related Guides
History
Cite this Page

LLMFunction

This functionality requires LLM access »

LLMFunction[prompt]

represents a template for a large language model (LLM) prompt.

LLMFunction[{prompt1,prompt2,…}]

represents a combination of multiple prompts.

LLMFunction[prompt,form]

includes the interpreter form to apply to the response.

LLMFunction[…][params]

give the LLM service response for prompt applied to parameters params.

Details and Options

  • An LLMFunction can be used to generate text using a large language model (LLM). It can create content, complete sentences, extract information and more.
  • LLMFunction requires external service authentication, billing and internet connectivity.
  • The prompti supports the following values:
  • "string"static string template
    LLMPrompt["name"]a repository prompt
    StringTemplate[…]templated text
    TemplateObject[…]template for creating a prompt
    {prompt1,…}a list of prompts
  • A prompt "string" is equivalent to StringTemplate["string"].
  • Prompts created with TemplateObject can contain text and images. Not every LLM supports image input.
  • The supported values of form are the same as Interpreter.
  • When a form is specified, the LLM will be instructed to respect it.
  • Specifying an output interpretation adds the corresponding schema information to the LLM prompt.
  • LLMFunction supports the following options:
  • InsertionFunctionTextStringfunction or format to apply before inserting expressions
    CombinerFunctionStringJoinfunction to apply to combine pieces within a prompt
    Authentication Automaticauthentication scheme
    LLMEvaluator $LLMEvaluatorLLM configuration to use
  • LLMEvaluator can be set to an LLMConfiguration object or an association with any of the following keys:
  • "MaxTokens"maximum amount of tokens to generate
    "Model"base model
    "PromptDelimiter"string to insert between prompts
    "Prompts"initial prompts
    "StopTokens"tokens on which to stop generation
    "Temperature"sampling temperature
    "ToolMethod"method to use for tool calling
    "Tools"list of LLMTool objects to make available
    "TopProbabilities"sampling classes cutoff
    "TotalProbabilityCutoff"sampling probability cutoff (nucleus sampling)
  • Valid forms of "Model" include:
  • namenamed model
    {service,name}named model from service
    <|"Service"service,"Name"name,"Task"task|>fully specified model
  • The generated text is sampled from a distribution. Details of the sampling can be specified using the following properties of LLMEvaluator:
  • "Temperature"tAutomaticsample using a positive temperature t
    "TopProbabilities"kAutomaticsample only among the k highest-probability classes
    "TotalProbabilityCutoff"pAutomaticsample among the most probable choices with an accumulated probability of at least p (nucleus sampling)
  • Multiple prompts are separated by the "PromptDelimiter" property of the LLMEvaluator.
  • Possible values for Authentication are:
  • Automaticchoose the authentication scheme automatically
    Environmentcheck for a key in the environment variables
    SystemCredentialcheck for a key in the system keychain
    ServiceObject[…]inherit the authentication from a service object
    "string"provide an explicit API key
  • With AuthenticationAutomatic, the function checks the variable ToUpperCase[service]<>"_API_KEY" in Environment and SystemCredential; otherwise, it uses ServiceConnect[service].
  • LLMFunction uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.

Examples

open all close all

Basic Examples  (3)

Create a function for getting cooking instructions:

Wolfram Language code: LLMFunction["Describe how to cook `1`"]

Create a helper function:

Wolfram Language code: findbyproperty = LLMFunction["What is something that is `1` and `2`"]

Use the function:

Wolfram Language code: findbyproperty["Blue", "Round"]

Create a function that returns a city as an Entity:

Wolfram Language code: cityfinder = LLMFunction["Find a city between `1` and `2`. Answer with the city name only", "City"]

Use the function:

Wolfram Language code: cityfinder["St. Louis", "Chicago"]

Scope  (5)

Evaluate a function combining multiple prompts:

Wolfram Language code: LLMFunction[{LLMPrompt["Yoda"], "What is something that is `1` and `2`", "answer in one sentence"}]["Blue", "Round"]

Use named parameters:

Wolfram Language code: teamfinder = LLMFunction["What team did `Pitcher` and `Catcher` play for?"]

Apply it using an Association:

Wolfram Language code: teamfinder[<|"Pitcher" -> "Whitey Ford", "Catcher" -> "Yogi Berra"|>]

Set a default for a parameter:

Wolfram Language code: recipe = LLMFunction[StringTemplate["Create a short recipe including `Veggie` annd `Spice`", <|"Spice" -> "Chili Powder"|>]]
Wolfram Language code: recipe[<|"Veggie" -> "Corn"|>]

Use a multi-part prompt with images:

Wolfram Language code: LLMFunction[TemplateObject@{"what is this?", TemplateSlot[1]}][[image]]

Use an Interpreter to both constrain and validate the result:

Wolfram Language code: f = LLMFunction["Generate `` random instances", RepeatingElement["Color"]]
Wolfram Language code: f[10]

Options  (6)

Authentication  (4)

Provide an authentication key for the API:

Wolfram Language code: SystemCredential["OPENAI_API_KEY"] = "<my-key>"

Look for the key in the system keychain:

Wolfram Language code: LLMFunction["the product of `1` and `2` is ", LLMEvaluator -> <|"Model" -> {"OpenAI", Automatic}|>, Authentication -> SystemCredential ]

Store the API key in an environment variable:

Wolfram Language code: SetEnvironment["OPENAI_API_KEY" -> "<my-key>"]

Look for the key in the system environment:

Wolfram Language code: LLMFunction["the product of `1` and `2` is ", LLMEvaluator -> <|"Model" -> {"OpenAI", Automatic}|>, Authentication -> Environment ]

Authenticate via a service object:

Wolfram Language code: so = ServiceConnect["OpenAI"]
Wolfram Language code: LLMFunction["the product of `1` and `2` is ", LLMEvaluator -> <|"Model" -> {"OpenAI", Automatic}|>, Authentication -> so]

Provide an authentication key for the API:

Wolfram Language code: LLMFunction["the product of `1` and `2` is ", LLMEvaluator -> <|"Model" -> {"OpenAI", Automatic}|>, Authentication -> "<my-key>" ]

LLMEvaluator  (2)

Specify the service and the model to use for the generation:

Wolfram Language code: LLMFunction["Generate `` random color", LLMEvaluator -> <|"Model" -> {"Anthropic", Automatic}|>]

Specify that the sampling should be performed at zero temperature:

Wolfram Language code: fZero = LLMFunction["Generate a random `` color", "Color", LLMEvaluator -> <|"Temperature" -> 0|>]
Wolfram Language code: fZero /@ {"warm", "warm", "cool", "cool"}

Specify a high temperature to get more variation in the generation:

Wolfram Language code: fRandom = LLMFunction["Generate a random `` color", "Color", LLMEvaluator -> <|"Temperature" -> 1.5|>]
Wolfram Language code: fRandom /@ {"warm", "warm", "cool", "cool"}

Properties & Relations  (1)

LLMFunction with no parameters sends the prompt directly to the LLM:

Wolfram Language code: LLMFunction["Hello"][]

This is equivalent to LLMSynthesize with zero temperature:

Wolfram Language code: LLMSynthesize["Hello", LLMEvaluator -> <|"Temperature" -> 0|>]
Wolfram Research (2023), LLMFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/LLMFunction.html (updated 2025).

Text

Wolfram Research (2023), LLMFunction, Wolfram Language function, https://reference.wolfram.com/language/ref/LLMFunction.html (updated 2025).

CMS

Wolfram Language. 2023. "LLMFunction." Wolfram Language & System Documentation Center. Wolfram Research. Last Modified 2025. https://reference.wolfram.com/language/ref/LLMFunction.html.

APA

Wolfram Language. (2023). LLMFunction. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/LLMFunction.html

BibTeX

@misc{reference.wolfram_2026_llmfunction, author="Wolfram Research", title="{LLMFunction}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/LLMFunction.html}", note=[Accessed: 13-June-2026]}

BibLaTeX

@online{reference.wolfram_2026_llmfunction, organization={Wolfram Research}, title={LLMFunction}, year={2025}, url={https://reference.wolfram.com/language/ref/LLMFunction.html}, note=[Accessed: 13-June-2026]}