Documentation
HomeAPISign In
  • Getting Started
    • Overview
      • Core Concepts
      • Building your First Workflow
    • API Reference
  • Your Data
    • Brand Kits
    • Knowledge Bases
      • Add Data
        • Upload Files
        • Web Scrape
        • Import from Google Drive
        • Import from SQL Database
        • Import from Shopify
      • Knowledge Base Search
      • Knowledge Base Metadata
      • Knowledge Base API
  • Building Workflows
    • Workflow Concepts
      • Workflow Inputs
        • Input Types
      • Workflow Outputs
      • Variable Referencing
      • Liquid Templating
    • Workflow Steps
      • AI
        • Prompt LLM
          • Model Selection Guide
          • Prompting Guide
        • Transcribe Audio File
      • Web Research
        • Google Search
        • Web Page Scrape
      • Code
        • Run Code
        • Call API
        • Format JSON
        • Run SQL Query
        • Write Liquid Text
      • Flow
        • Condition
        • Iteration
        • Human Review
        • Content Comparison
        • Error
      • Data
        • Read from Grid
        • Write to Grid
        • Search Knowledge Base
        • Write to Knowledge Base
        • Get Knowledge Base File
      • AirOps
        • Workflow
        • Agent
      • Image & Video
        • Generate Image with API
        • Search Stock Images
        • Fetch Stock Image with ID
        • Resize Image
        • Screenshot from URL
        • Create OpenGraph Image
        • Create Video Avatar
      • SEO Research
        • Semrush
        • Data4SEO
      • Content Quality
        • Detect AI Content
        • Scan Content for Plagiarism
      • Content Processing
        • Convert Markdown to HTML
        • Convert PDF URL to Text
        • Group Keywords into Clusters
      • B2B Enrichment
        • Hunter.io
        • People Data Labs
      • CMS Integrations
        • Webflow
        • WordPress
        • Shopify
        • Contentful
        • Sanity
        • Strapi
      • Analytics Integrations
        • Google Search Console
      • Collaboration Integrations
        • Gmail
        • Google Docs
        • Google Sheets
        • Notion
        • Slack
    • Testing and Iteration
    • Publishing and Versioning
  • Running Workflows
    • Run Once
    • Run in Bulk (Grid)
    • Run via API
    • Run via Trigger
      • Incoming Webhook Trigger
      • Zapier
    • Run on a Schedule
    • Error Handling
  • Grids
    • Create a Grid
      • Import from Webflow
      • Import from Wordpress
      • Import from Semrush
      • Import from Google Search Console
    • Add Columns in the Grid
    • Run Workflows in the Grid
      • Add Workflow Column
      • Run Workflow Column
      • Map Workflow Outputs
      • Review Workflow Run Metadata
    • Review Content in the Grid
      • Review Markdown Content
      • Review HTML Content
      • Compare Content Difference
    • Publish to CMS from Grid
    • Pull Analytics in the Grid
    • Export as CSV
  • Copilot
    • Chat with Copilot
    • Edit Workflows with Copilot
    • Fix Errors with Copilot
  • Monitoring
    • Task Usage
    • Analytics
    • Alerts
    • Execution History
  • Your Workspace
    • Create a Workspace
    • Folders
    • Settings
    • Billing
    • Use your own LLM API Keys
    • Secrets
    • Team and Permissions
  • Chat Agents (Legacy)
    • Agent Quick Start
    • Chat Agents
    • Integrate Agents
      • Widget
      • Client Web SDK
  • About
    • Ethical AI and IP Production
    • Principles
    • Security and Compliance
Powered by GitBook
On this page
  • Which Model Should I Use?
  • What to Consider
  • AirOps Popular LLMs
  • Differences between “o-series” vs “GPT” models
  • How much will it cost to run?
  • Token Approximation
  • Cost Approximation

Was this helpful?

  1. Building Workflows
  2. Workflow Steps
  3. AI
  4. Prompt LLM

Model Selection Guide

Determine which large language model to use

Last updated 4 days ago

Was this helpful?

Which Model Should I Use?

What to Consider

Choosing a model depends on the following:

  1. Context Window: the context window refers to the number of tokens you can provide to a LLM. ~1 Token = ~4 characters

  2. Task Complexity: more capable models are generally better suited for complex logic.

  3. Web Access: whether the use case you're building require the model to have web access?

  4. Cost: more capable models are generally more expensive - for example, o1 is more expensive than GPT-4o.

  5. Speed: more capable models are generally slower to execute.

AirOps Popular LLMs

Model
Provider
In-App Description
Context Window
Vision
JSON Mode
Web Research

O1

OpenAI

Advanced multi-step reasoning for complex tasks

200K

-

-

-

O3 Mini

OpenAI

Small reasoning model optimized for complex tasks

200K

-

-

-

GPT-4o

OpenAI

Flagship for complex tasks, vision-capable

128K

✓

✓

-

GPT-4o Mini

OpenAI

Fast and intelligent model for lightweight tasks

128K

✓

✓

-

Claude 3.5 Sonnet

Anthropic

Flagship intelligent model for complex tasks

200K

✓

-

-

Perplexity Sonar

Perplexity

Intelligent model for online web research

128K

-

-

✓

Gemini Pro 2.0

Google

Flagship for complex tasks, vision-capable

2M

-

✓

✓

Differences between “o-series” vs “GPT” models

GPT Models (4o, 4.1): Optimized for general-purpose tasks with excellent instruction following. GPT-4.1 excels with long contexts (1M tokens) while GPT-4o has variants for realtime speech, text-to-speech, and speech-to-text. GPT-4.1 also comes in a mini, and nano variant, while GPT-4o has a mini variant. These variants are cheaper and faster than their full-size counterparts. Strong in structured output

O-series Models (o3, o4-mini): Specialized for deep reasoning and step-by-step problem solving. These models excel at complex, multi-stage tasks requiring logical thinking and tool use. Choose these when accuracy and reasoning depth are paramount. These models also have an optional reasoning_effort parameter (that can be set to low, medium, or high), which allows users to control the amount of tokens used for reasoning. Validates factual accuracy and citation correctness (o4-mini)

How much will it cost to run?

The cost to run a model depends on the number of input and output tokens.

Token Approximation

Cost Approximation

Input tokens: to approximate the total input tokens, copy and paste your system, user, and assistant prompts into

Output tokens: to approximate the total output tokens, copy and paste your output into

OpenAI: divide the input and output tokens by 1000; then multiply by their respective costs *

Anthropic: divide the input and output tokens by 1,000,000; then multiply by their respective costs *

*This is the cost if you . If you choose to use AirOps hosted models, you will be .

the OpenAI tokenizer
the OpenAI tokenizer
based on OpenAI pricing
based on Anthropic pricing
bring your own API Key
charged tasks according to your usage