LLM Block

Overview

The LLM block sends prompts to AI language models and returns generated text. Use it for content creation, summarization, analysis, or any text-based AI task.

Configuration

Click the model bar at the top of the configuration panel to open the settings. The bar shows the selected model and output format.

Model

Select the AI model in the Model dropdown. The dropdown lists the models currently available in Slate, and the list changes as new models are released. Default: GPT-5.4 mini Different models have different capabilities, speed, and cost. The settings below change based on the model you select.

Output Format

Define how the model returns its response. Options:

Text: Plain text response
JSON: Structured data response

Select JSON when you need structured output in the subsequent blocks. Some models support Text only.

Reasoning Effort

Controls how much reasoning the model applies before it answers. Higher effort can improve quality but takes longer. Available for: GPT models, Gemini 3 models, and DeepSeek models

Models	Label	Options
GPT models	Reasoning Effort	None, Low, Medium (default), High, Extra High
Gemini 3 models	Thinking Effort	Low, High
DeepSeek models	Thinking Effort	None, High, Max

Verbosity

Controls how long and detailed the response is. Available for: GPT-5.x models Options: Low, Medium (default), High

Stream Output

Streams the response to the UI in real time while the block runs. Turn Stream Output off for faster execution without a live preview. Default: Off for new LLM blocks

Enable Thinking

Lets the model think before it responds. Available for: Anthropic models that support thinking (Sonnet, Opus, and Fable models) Enable Thinking turns on automatically when you select one of these models. When it’s on, use Thinking Effort to set how much effort the model puts into thinking: Max, High (default), Medium, or Low.

System Instructions

Define the model’s role, tone, and behavior. Optional field that sets context for all messages in this block. Example:

You are an SEO expert who writes clear, actionable content briefs.
Use professional tone and focus on data-driven insights.

System instructions apply to the entire conversation with the model.

Enable Web Search

Allow the model to search the web for current information. Available for: GPT, Anthropic (Sonnet, Opus, and Fable), and Gemini models When enabled, the model can retrieve up-to-date information from the internet to answer your queries. Useful for queries requiring recent data, news, or facts beyond the model’s training cutoff. Perplexity models don’t show this toggle. See Perplexity models. Note: Web search increases response time and credit usage. If you combine web search with JSON output, describe the exact JSON shape in System Instructions. JSON output isn’t guaranteed when web search is on.

Citations

Include source references in the model’s response. Requirements: For GPT, Anthropic, and Gemini models, turn on Enable Web Search, then select Include Citations. Choose a Citation Format:

Include within the answer: Inline citations using [1], [2] format with a References section at the end

According to recent studies [1], the market grew by 15% [2].

References:
[1] https://example.com/study
[2] https://example.com/market-report

Separate answer and citations: JSON format with separate answer and citations fields

{
  "answer": "The market grew by 15%",
  "citations": [
    {"title": "Market Study", "url": "https://example.com/study"}
  ]
}

Select “Separate answer and citations” format when you need to process citations programmatically in subsequent blocks.

Allowed Domains

Limit web search results to specific domains. Requirements: Enable Web Search must be turned on Maximum: 20 domains The control depends on the model:

GPT models: Allowed Domains (Optional) limits search to the domains you list. Enter domains without the http:// or https:// prefix and without paths.
Anthropic models: Domain Filtering has a Filter Mode of Include Only or Exclude. You can enter domains or full URLs.

Format for Allowed Domains:

Correct: wikipedia.org
Incorrect: https://wikipedia.org

Examples:

wikipedia.org
nature.com
ncbi.nlm.nih.gov

Both fields accept placeholders, such as {{input.domain}}. Use domain filters to ensure responses cite only trusted or relevant sources for your use case.

Perplexity Models

Perplexity models have no Enable Web Search toggle. They always show these settings:

Include Citations: Adds source citations. With Text output, the response ends with numbered references. With JSON output, the response includes a citations array.
Domain Filtering: Choose Include Only or Exclude in Filter Mode, then enter up to 20 domains or full URLs.

Messages

Define the conversation between user and assistant.

User Message (Required)

The prompt sent to the AI model. This is where you reference placeholders and define your request. Example:

Analyze the following search results for {{input.keyword}}:

{{step_1.output}}

Create a content outline with 5 main sections.

Click the { } icon to insert placeholders from previous steps or inputs. Click Add message to add another message. Click a message’s USER or ASSISTANT label to switch its role.

Assistant Message

Optional: Pre-fill the start of the assistant’s response to guide output format or structure. Example:

# Content Outline for {{input.keyword}}

## Section 1:

This guides the model to follow your desired format.

Using Liquid Templating in Prompts

You can use Liquid templating syntax in your prompts to create dynamic, data-driven messages. Liquid lets you reference workflow data, apply filters, use loops, and add conditional logic directly in your prompts.

Basic Variable Output

Reference previous step outputs:

Write a blog post about {{step_1.output.topic}}.

Target keyword: {{step_2.output.Keyword}}
Search volume: {{step_2.output.Search_Volume}}

Using Filters

Transform data with filters:

Write a blog post titled "{{step_1.output.title | upcase}}".

The post should be {{step_2.output.word_count | divided_by: 2}} to {{step_2.output.word_count}} words long.

Topic: {{step_1.output.topic | capitalize}}

Extract and join array values:

Write content about {{step_1.output.main_topic}}.

Target these keywords naturally throughout the content:
{{step_2.output | map: "Keyword" | join: ", "}}

Ensure the content covers all these topics.

Loops in Prompts

Loop through arrays to build dynamic prompts:

Write a comprehensive blog post about email marketing tools.

Include information about these tools:
{% for tool in step_1.output %}
- {{tool.name}}: {{tool.description}}
{% endfor %}

Compare their features and pricing.

Loop with conditions:

Create a keyword strategy document.

Focus on these high-volume keywords:
{% for kw in step_1.output %}
  {% if kw.Search_Volume > 10000 %}
- {{kw.Keyword}} ({{kw.Search_Volume}} monthly searches)
  {% endif %}
{% endfor %}

Provide content ideas for each keyword.

Conditional Logic

Adjust prompts based on data:

Write a content brief for "{{step_1.output.Keyword}}".

Search volume: {{step_1.output.Search_Volume}}

{% if step_1.output.Keyword_Difficulty_Index > 70 %}
This is a highly competitive keyword. Focus on:
- Long-tail variations
- Unique angles and perspectives
- Building topical authority
{% elsif step_1.output.Keyword_Difficulty_Index > 40 %}
This is a moderately competitive keyword. Focus on:
- High-quality, comprehensive content
- Strong on-page SEO
- Supporting internal links
{% else %}
This is a low-competition keyword. Focus on:
- Basic optimization
- Quick content production
- Capturing traffic quickly
{% endif %}

Complex Prompt Example

Combine multiple Liquid features:

Create an SEO content strategy for "{{step_1.output.main_keyword}}".

## Primary Keyword Analysis
- Keyword: {{step_1.output.main_keyword | capitalize}}
- Volume: {{step_1.output.Search_Volume}}
- Difficulty: {{step_1.output.Keyword_Difficulty_Index}}/100

## Related Keywords
{% assign related_keywords = step_2.output | map: "Keyword" %}
Target these {{related_keywords | size}} related terms:
{% for kw in step_2.output limit:10 %}
{{forloop.index}}. {{kw.Keyword}} ({{kw.Search_Volume}} searches)
{% endfor %}

## Competitor Analysis
{% for competitor in step_3.output %}
- {{competitor.Domain}}: {{competitor.Organic_Keywords}} ranking keywords
{% endfor %}

## Content Requirements
{% if step_1.output.Search_Volume > 50000 %}
Create pillar content (3000+ words) with comprehensive coverage.
{% elsif step_1.output.Search_Volume > 10000 %}
Create standard long-form content (1500-2000 words).
{% else %}
Create focused content (800-1200 words).
{% endif %}

Include:
- Main sections addressing search intent
- {{related_keywords | slice: 0, 5 | join: ", "}} naturally integrated
- Examples and use cases
- Call-to-action

Tone: Professional and informative

Learn More

See Liquid Templating for complete syntax guide including:

All available filters (string, number, array)
Control flow (if/elsif/else, for loops, unless, case/when)
Variables and assignments
Common patterns and examples
Input/output samples for all syntax

Error Handling

Define what happens if the LLM block fails. Options:

Terminate workflow: Stop execution immediately
Continue execution: Proceed to next step despite error
Retry: Run the block again until it succeeds, up to the Number of retries you choose (1–5). If every retry fails, the workflow stops at this block.

Select based on whether subsequent steps can handle missing data.

Best Practices

Use specific, clear prompts for better results
Reference previous step outputs using {{step_n.output}} syntax
Use system instructions to maintain consistent tone across runs
Test with different models to find the best balance of quality and speed
Enable web search for queries requiring current information or recent events
Use allowed domains to limit sources to trusted, authoritative sites
Choose “Separate answer and citations” format when processing citations in LLM blocks
Note that web search adds latency and increases credit usage per request

Common Use Cases

Use Case	Configuration Tips
Content summarization	Clear system instructions
Creative writing	Tone and style guidance in system instructions
Data extraction	JSON output format, structured user prompt
SEO content briefs	Detailed system role
Research with sources	Enable web search, citations on, allowed domains for trusted sources
Current event analysis	Enable web search, citations for verification
Fact checking	Enable web search, structured citations format for data processing

What’s Next

Now that you understand the LLM block:

Get AI-generated search summaries with Google AI Overview
See how to connect blocks in Building Workflows
Use placeholders in Placeholder Referencing

Getting Started

Cowork

Insights

Work

Agency

Automate

Assets

Integrations

Settings

Overview

Configuration

Model

Output Format

Reasoning Effort

Verbosity

Stream Output

Enable Thinking

System Instructions

Enable Web Search

Citations

Allowed Domains

Perplexity Models

Messages

User Message (Required)

Assistant Message

Using Liquid Templating in Prompts

Basic Variable Output

Using Filters

Loops in Prompts

Conditional Logic

Complex Prompt Example

Learn More

Error Handling

Best Practices

Common Use Cases

What’s Next

​Overview

​Configuration

​Model

​Output Format

​Reasoning Effort

​Verbosity

​Stream Output

​Enable Thinking

​System Instructions

​Enable Web Search

​Citations

​Allowed Domains

​Perplexity Models

​Messages

​User Message (Required)

​Assistant Message

​Using Liquid Templating in Prompts

​Basic Variable Output

​Using Filters

​Loops in Prompts

​Conditional Logic

​Complex Prompt Example

​Learn More

​Error Handling

​Best Practices

​Common Use Cases

​What’s Next

Overview

Configuration

Model

Output Format

Reasoning Effort

Verbosity

Stream Output

Enable Thinking

System Instructions

Enable Web Search

Citations

Allowed Domains

Perplexity Models

Messages

User Message (Required)

Assistant Message

Using Liquid Templating in Prompts

Basic Variable Output

Using Filters

Loops in Prompts

Conditional Logic

Complex Prompt Example

Learn More

Error Handling

Best Practices

Common Use Cases

What’s Next