MindStudio Docs
  • Get Started
    • Overview
    • MindStudio Chrome Extension
    • Quickstart Guide
    • What is an AI Agent?
    • AI Agent Use Cases
  • Free vs. Paid AI Agents
  • Building AI Agents
    • Editor Overview
    • Workflow Generator
    • Writing Prompts
      • Templating
    • AI Models
    • Variables
      • Working with JSON
      • Using Handlebars Templating
    • Dynamic Variables
    • Data Sources
    • Automations
      • Start Block
      • Generate Text Block
      • Generate Image Block
      • Generate Chart Block
      • Generate Asset Block
      • Display Content Block
      • Text to Speech Block
      • Analyze Image Block
      • User Input Block
      • User Context Block
      • Query Data Block
      • Run Function Block
      • Scrape URL Block
      • Extract Text from File Block
      • Post to Slack Block
      • Menu Block
      • Logic Block
      • Checkpoint Block
      • Jump Block
      • Run Workflow Block
      • Terminator Block
    • Integrations
      • Search Bluesky Posts
      • Scrape Facebook Page
      • Scrape Meta Threads Profile
      • Scrape Instagram Comments
      • Scrape Instagram Mentions
      • Scrape Instagram Posts
      • Scrape Instagram Profile
      • Scrape Instagram Reels
      • Create LinkedIn Post
      • Create X Post
      • Search X Posts
      • Search Google
      • Search Google Images
      • Search Google Trends
      • Search Google News
      • Create Google Doc
      • Fetch Google Doc
      • Update Google Doc
      • Create Google Sheet
      • Fetch Google Sheet
      • Update Google Sheet
      • Enrich Company via Domain
      • Find Contact Email for Website
      • Find Email
      • Verify Email
      • Enrich Person via Email
      • Fetch YouTube Captions
      • Fetch YouTube Channel
      • Fetch YouTube Comments
      • Fetch YouTube Video
      • Search YouTube
      • Search YouTube Trends
      • Create Notion Page
      • Update Notion Page
      • Apify
      • Run Scenario
      • Post to Slack
      • HTTP Request
      • Run Node
      • Create Contact
      • Add Note
      • Send Email
      • Send SMS
    • Publishing & Versioning
  • Embedding AI Agents
  • Using Webhooks
  • Workspace Management
    • Workspace Overview
    • Workspace Settings
    • Usage Explorer
    • Billing Settings
    • Account Settings
    • Team Settings & Access Controls
  • Test & Evaluate
    • Testing Suite Overview
    • Evaluations
    • Profiler
    • Debugger
  • Integration Guides
    • Zapier + MindStudio
    • Make.com + MindStudio
    • n8n + MindStudio
  • Developers
    • API Reference
    • NPM Package
    • Custom Workflow Functions
  • Additional Resources
    • Glossary
    • Allowing Access to Mindstudio From Your Network
  • Solutions
    • MindStudio Solutions Partners
    • MindStudio For Developers
    • MindStudio for Enterprises
Powered by GitBook
On this page
  • Select an Underlying AI Model
  • Configuring Model Settings
  • Best Practices for AI Model Configuration
  • Using Multiple AI Models Within a Workflow
  • Considerations When Selecting an AI Model
  • Price
  • Latency
  • Output Quality
  • Context Window
  • AI Models Reference
  • Amazon
  • Anthropic
  • Cohere
  • DeepSeek
  • Google
  • Meta
  • Mistral
  • OpenAI
  • Perplexity
  • Reka
  • X.ai
  • Image Models
  • Text-To-Speech Models
Export as PDF
  1. Building AI Agents

AI Models

Learn about choosing the right AI models for the right task.

MindStudio provides access to over 50 AI models from leading providers, allowing you to tailor your workflows for a variety of tasks and use cases.

Select an Underlying AI Model

The underlying model is the AI model that is inherited by the rest of the workflow. It’s configuration will be used as the default model for all blocks that use AI.

  1. Access Model Settings

    • Navigate to the Model Settings Tab in your workflow editor.

  2. Choose an AI Model

    • Click on the Model Card to view information about the AI Model.

    • NOTE: Some models may be locked and can be unlocked by adding a payment method in your Billing Settings.

  3. Click the Use Button to confirm your selection

  4. (Optional) Click the heart icon to add preferred AI Models to your Favorites section


Configuring Model Settings

There are two configuration options for AI models:

  1. Temperature

    • Controls the randomness of responses:

      • Higher Temperature: More creative, but less predictable.

      • Lower Temperature: More consistent, but less diverse.

  2. Max Response Size

    • Defines the maximum size of the model’s response in tokens.

    • Example: 400 tokens ≈ 300 words.

Best Practices for AI Model Configuration

  • Start the slider in the center for temperature and adjust based on your needs.

  • Use larger response sizes for detailed outputs and smaller sizes for concise ones.


Using Multiple AI Models Within a Workflow

Every block that uses AI has the ability to override the underlying models settings and use its own unique AI model and configuration. This allows you to use different models in the workflow based on the task required at each specific step of the workflow.


Considerations When Selecting an AI Model

Choosing the right AI model is critical to ensuring your workflow meets performance, cost, and quality requirements. MindStudio provides a variety of models with different capabilities, trade-offs, and configurations. When selecting a model, it's often necessary to balance these considerations to align with your workflow's goals and constraints.

Price

AI models come with varying pricing structures based on usage, typically measured in tokens for prompt and response.

Use cost-effective models for high-volume, repetitive tasks (e.g., bulk summarization). Opt for premium models only when high output quality is critical.

Latency

Latency refers to the time the model takes to generate a response. Low-latency models are essential for real-time or interactive workflows.

Prioritize low-latency models for use cases like chatbots or live applications. For non-time-sensitive workflows (e.g., scheduled reports), higher latency models with better quality may be acceptable.

Output Quality

Different models vary in their ability to generate coherent, creative, or factual responses. Output quality depends on the model’s training and capabilities.

Choose advanced models for nuanced tasks like legal summaries or creative writing. Use simpler models for straightforward tasks like data extraction.

Context Window

The context window determines the maximum amount of text the model can process at once. Larger context windows are essential for tasks involving lengthy inputs.

Use models with large context windows for summarizing lengthy documents or analyzing extensive datasets. For shorter inputs, a smaller context window may suffice and reduce costs.

AI Models Reference

Last updated: May 5, 2025

Amazon

Model Name
Input Price
Output Price
Context Length
Max Output Size

Amazon Nova Lite

$0.06/MTok

$0.24/MTok

300,000 Tokens

5,000 Tokens

Amazon Nova Micro

$0.04/MTok

$0.14/MTok

128,000 Tokens

5,000 Tokens

Amazon Nova Pro

$0.80/MTok

$3.20/MTok

300,000 Tokens

5,000 Tokens

Anthropic

Model Name
Input Price
Output Price
Context Length
Max Output Size

Claude

$8.00/MTok

$24.00/MTok

200,000 Tokens

4,096 Tokens

Claude 2

$8.00/MTok

$24.00/MTok

200,000 Tokens

4,096 Tokens

Claude 3 Haiku

$0.25/MTok

$1.25/MTok

200,000 Tokens

4,096 Tokens

Claude 3 Haiku (Bedrock)

$0.25/MTok

$1.25/MTok

200,000 Tokens

4,096 Tokens

Claude 3 Opus

$15.00/MTok

$75.00/MTok

200,000 Tokens

4,096 Tokens

Claude 3 Opus (BedRock)

$15.00/MTok

$75.00/MTok

200,000 Tokens

4,096 Tokens

Claude 3 Sonnet

$3.00/MTok

$15.00/MTok

200,000 Tokens

4,096 Tokens

Claude 3 Sonnet (Bedrock)

$3.00/MTok

$15.00/MTok

200,000 Tokens

4,096 Tokens

Claude 3.5 Haiku

$0.80/MTok

$4.00/MTok

200,000 Tokens

8,192 Tokens

Claude 3.5 Haiku (Bedrock)

$0.80/MTok

$4.00/MTok

200,000 Tokens

4,096 Tokens

Claude 3.5 Sonnet

$3.00/MTok

$15.00/MTok

200,000 Tokens

8,192 Tokens

Claude 3.5 Sonnet (Bedrock)

$3.00/MTok

$15.00/MTok

200,000 Tokens

4,096 Tokens

Claude 3.5 Sonnet (20240620)

$3.00/MTok

$15.00/MTok

200,000 Tokens

8,192 Tokens

Claude 3.5 Sonnet v2 (Bedrock)

$3.00/MTok

$15.00/MTok

200,000 Tokens

8,192 Tokens

Claude 3.7 Sonnet

$3.00/MTok

$15.00/MTok

200,000 Tokens

128,000 Tokens

Claude Instant

$0.80/MTok

$2.40/MTok

200,000 Tokens

4,096 Tokens

Cohere

Model Name
Input Price
Output Price
Context Length
Max Output Size

Command

$1.50/MTok

$2.00/MTok

4,000 Tokens

4,000 Tokens

Command Light

$0.30/MTok

$0.60/MTok

4,000 Tokens

4,000 Tokens

Command R

$0.50/MTok

$1.50/MTok

128,000 Tokens

4,000 Tokens

Command R (Bedrock)

$0.15/MTok

$0.60/MTok

128,000 Tokens

4,000 Tokens

Command R+

$3.00/MTok

$15.00/MTok

128,000 Tokens

4,000 Tokens

Command R+

$2.50/MTok

$10.00/MTok

128,000 Tokens

4,000 Tokens

DeepSeek

Model Name
Input Price
Output Price
Context Length
Max Output Size

DeepSeek-R1

$0.55/MTok

$2.19/MTok

64,000 Tokens

8,000 Tokens

DeepSeek-V3

$0.27/MTok

$1.10/MTok

64,000 Tokens

8,000 Tokens

DeepSeek-V3 (DeepInfra)

$0.40/MTok

$0.89/MTok

64,000 Tokens

8,000 Tokens

Google

Model Name
Input Price
Output Price
Context Length
Max Output Size

Gemini 1.5 Flash

$0.04/MTok

$0.15/MTok

1,000,000 Tokens

8,192 Tokens

Gemini 1.5 Pro

$0.63/MTok

$2.50/MTok

2,000,000 Tokens

8,192 Tokens

Gemini 2.0 Flash

$0.15/MTok

$0.60/MTok

1,000,000 Tokens

8,192 Tokens

Gemini 2.0 Flash-Lite

$0.07/MTok

$0.30/MTok

1,000,000 Tokens

8,192 Tokens

Gemini 2.5 Flash

$0.15/MTok

$0.60/MTok

1,000,000 Tokens

65,536 Tokens

Gemini 2.5 Pro

$2.50/MTok

$15.00/MTok

1,000,000 Tokens

65,536 Tokens

Gemma 2 (Groq)

$0.20/MTok

$0.20/MTok

8,200 Tokens

8,192 Tokens

Gemma 3.2 (DeepInfra)

$0.10/MTok

$0.20/MTok

128,000 Tokens

8,000 Tokens

Meta

Model Name
Input Price
Output Price
Context Length
Max Output Size

Llama 3 70B (Groq)

$0.59/MTok

$0.79/MTok

8,000 Tokens

8,192 Tokens

Llama 3 70B Instruct (DeepInfra)

$0.10/MTok

$0.10/MTok

8,000 Tokens

8,000 Tokens

Llama 3 70B Instruct (Bedrock)

$0.10/MTok

$0.10/MTok

8,000 Tokens

8,000 Tokens

Llama 3 8B (Groq)

$0.05/MTok

$0.08/MTok

8,000 Tokens

8,000 Tokens

Llama 3 8B Instruct (DeepInfra)

$0.30/MTok

$0.60/MTok

8,000 Tokens

8,000 Tokens

Llama 3 8B Instruct (Bedrock)

$0.30/MTok

$0.60/MTok

8,000 Tokens

8,000 Tokens

Llama 3.1 405B Instruct (DeepInfra)

$0.80/MTok

$0.80/MTok

128,000 Tokens

8,000 Tokens

Llama 3.1 405B Instruct (Bedrock)

$2.40/MTok

$2.40/MTok

128,000 Tokens

8,000 Tokens

Llama 3.1 70B Instruct (DeepInfra)

$0.23/MTok

$0.40/MTok

128,000 Tokens

8,000 Tokens

Llama 3.1 70B Instruct (Bedrock)

$0.72/MTok

$0.72/MTok

128,000 Tokens

8,000 Tokens

Llama 3.1 8B Instant (Groq)

$0.05/MTok

$0.08/MTok

128,000 Tokens

8,000 Tokens

Llama 3.1 8B Instruct (DeepInfra)

$0.03/MTok

$0.05/MTok

128,000 Tokens

8,000 Tokens

Llama 3.1 8B Instruct (Bedrock)

$0.22/MTok

$0.22/MTok

128,000 Tokens

8,000 Tokens

Llama 3.2 11B Instruct (Bedrock)

$0.16/MTok

$0.16/MTok

128,000 Tokens

8,000 Tokens

Llama 3.2 1B Instruct (Bedrock)

$0.10/MTok

$0.10/MTok

128,000 Tokens

8,000 Tokens

Llama 3.2 3B Instruct (Bedrock)

$0.15/MTok

$0.15/MTok

128,000 Tokens

8,000 Tokens

Llama 3.2 90B Instruct (Bedrock)

$0.72/MTok

$0.72/MTok

128,000 Tokens

8,000 Tokens

Llama 3.3 70B Versatile (Groq)

$0.59/MTok

$0.79/MTok

128,000 Tokens

32,768 Tokens

Llama 4 Maverick (DeepInfra)

$0.20/MTok

$0.60/MTok

130,000 Tokens

60,000 Tokens

Llama 4 Scout (Groq)

$0.11/MTok

$0.34/MTok

130,000 Tokens

8,000 Tokens

Llama 4 Scout (DeepInfra)

$0.10/MTok

$0.30/MTok

130,000 Tokens

60,000 Tokens

Mistral

Model Name
Input Price
Output Price
Context Length
Max Output Size

Mistral 7B Instruct (DeepInfra)

$0.03/MTok

$0.06/MTok

4,100 Tokens

2,500 Tokens

Mistral 7B Instruct (Bedrock)

$0.15/MTok

$0.20/MTok

4,100 Tokens

2,500 Tokens

Mistral Codestral

$0.20/MTok

$0.60/MTok

32,000 Tokens

16,000 Tokens

Mistral Codestral Mamba

$2.50/MTok

$2.50/MTok

128,000 Tokens

16,000 Tokens

Mistral Large 2

$2.00/MTok

$6.00/MTok

128,000 Tokens

16,000 Tokens

Mistral Large 24.02 (Bedrock)

$4.00/MTok

$12.00/MTok

128,000 Tokens

16,000 Tokens

Mistral Large 24.07 (Bedrock)

$2.00/MTok

$6.00/MTok

128,000 Tokens

16,000 Tokens

Mistral Nemo

$0.15/MTok

$0.15/MTok

128,000 Tokens

64,000 Tokens

Mistral Small 24.02 (Bedrock)

$1.00/MTok

$3.00/MTok

128,000 Tokens

16,000 Tokens

Mistral Small 3.1 (25.03)

$0.10/MTok

$0.30/MTok

128,000 Tokens

16,000 Tokens

Mixtral 8x7B Instruct

$0.45/MTok

$0.70/MTok

4,100 Tokens

2,500 Tokens

OpenAI

Model Name
Input Price
Output Price
Context Length
Max Output Size

GPT-4

$30.00/MTok

$60.00/MTok

8,200 Tokens

5,000 Tokens

GPT-4 Turbo

$10.00/MTok

$30.00/MTok

128,000 Tokens

4,096 Tokens

GPT-4.1

$2.00/MTok

$8.00/MTok

200,000 Tokens

100,000 Tokens

GPT-4.1 Mini

$0.40/MTok

$1.60/MTok

1,000,000 Tokens

32,768 Tokens

GPT-4.1 Nano

$0.10/MTok

$0.40/MTok

1,000,000 Tokens

32,768 Tokens

GPT-4.5

$75.00/MTok

$150.00/MTok

128,000 Tokens

8,000 Tokens

GPT-4o

$2.50/MTok

$10.00/MTok

128,000 Tokens

4,096 Tokens

GPT-4o Mini

$0.15/MTok

$0.60/MTok

128,000 Tokens

16,383 Tokens

o1

$15.00/MTok

$60.00/MTok

200,000 Tokens

100,000 Tokens

o1-mini

$3.00/MTok

$12.00/MTok

128,000 Tokens

65,536 Tokens

o1-pro

$150.00/MTok

$600.00/MTok

200,000 Tokens

100,000 Tokens

o3

$10.00/MTok

$40.00/MTok

200,000 Tokens

100,000 Tokens

o3-mini

$1.10/MTok

$4.40/MTok

200,000 Tokens

100,000 Tokens

o4-mini

$1.10/MTok

$4.40/MTok

200,000 Tokens

100,000 Tokens

Perplexity

Model Name
Input Price
Output Price
Context Length
Max Output Size

Sonar

$1.00/MTok

$1.00/MTok

127,000 Tokens

32,768 Tokens

Sonar Deep Research

$2.00/MTok

$8.00/MTok

127,000 Tokens

8,000 Tokens

Sonar Large Chat

$1.00/MTok

$1.00/MTok

127,000 Tokens

32,768 Tokens

Sonar Large Online

$1.00/MTok

$1.00/MTok

127,000 Tokens

28,000 Tokens

Sonar Pro

$3.00/MTok

$15.00/MTok

200,000 Tokens

8,000 Tokens

Sonar Reasoning

$1.00/MTok

$5.00/MTok

127,000 Tokens

32,768 Tokens

Sonar Reasoning Pro

$2.00/MTok

$8.00/MTok

127,000 Tokens

8,000 Tokens

Sonar Small Chat

$0.20/MTok

$0.20/MTok

127,000 Tokens

32,768 Tokens

Sonar Small Online

$0.20/MTok

$0.20/MTok

127,000 Tokens

28,000 Tokens

Reka

Model Name
Input Price
Output Price
Context Length
Max Output Size

Reka Core

$2.00/MTok

$2.00/MTok

128,000 Tokens

128,000 Tokens

Reka Edge

$0.10/MTok

$0.10/MTok

128,000 Tokens

128,000 Tokens

Reka Flash

$0.20/MTok

$0.80/MTok

128,000 Tokens

128,000 Tokens

X.ai

Model Name
Input Price
Output Price
Context Length
Max Output Size

Grok 3

$3.00/MTok

$15.00/MTok

131,000 Tokens

8,192 Tokens

Grok 3 Fast

$5.00/MTok

$25.00/MTok

131,000 Tokens

8,192 Tokens

Grok 3 Mini

$0.30/MTok

$0.50/MTok

131,000 Tokens

8,192 Tokens

Grok 3 Mini Fast

$0.60/MTok

$4.00/MTok

131,000 Tokens

8,192 Tokens

Image Models

Provider
Model Name
Price
Prompt Length

Amazon

Amazon Nova Canvas

$0.08 / image

1,000 Tokens

Black Forest Labs

FLUX 1.1 [pro]

$0.06 / image

10,000 Tokens

Black Forest Labs

FLUX 1.1 [pro] Ultra

$0.06 / image

10,000 Tokens

Ideogram

Ideogram Upscale

$0.06 / image

10,000 Tokens

Ideogram

Ideogram V1

$0.06 / image

10,000 Tokens

Ideogram

Ideogram V1 Remix

$0.06 / image

10,000 Tokens

Ideogram

Ideogram V2

$0.08 / image

10,000 Tokens

Ideogram

Ideogram V2 Remix

$0.08 / image

10,000 Tokens

Luma Labs

Photon 1

$0.02 / image

1,000 Tokens

Luma Labs

Photon 1 Flash

$0.00 / image

1,000 Tokens

OpenAI

DALL-E 2

$0.02 / image

1,000 Tokens

OpenAI

DALL-E 3

$0.08 / image

4,000 Tokens

OpenAI

GPT Image 1

$0.00 / image

4,000 Tokens

Stability

Stable Diffusion 3

$0.08 / image

10,000 Tokens

Stability

Stable Diffusion 3

$0.08 / image

10,000 Tokens

Stability

Stable Image Core

$0.04 / image

10,000 Tokens

Stability

Stable Image Core

$0.04 / image

10,000 Tokens

Stability

Stable Image Ultra

$0.08 / image

10,000 Tokens

Stability

Stable Image Ultra

$0.14 / image

10,000 Tokens

X.ai

Grok 2

$0.07 / image

131,000 Tokens

Text-To-Speech Models

Provider
Model Name
Input Price
Output Price
Prompt Length

ElevenLabs

ElevenLabs TTS

$240.00 / 1M chars

$0.10 / 1M chars

Unlimited

OpenAI

GPT-4o-mini TTS

$0.60 / 1M chars

$2.40 / 1M chars

2,000 Characters

OpenAI

TTS

$15.00 / 1M chars

$0.10 / 1M chars

4,100 Characters

OpenAI

TTS HD

$30.00 / 1M chars

$0.10 / 1M chars

4,100 Characters

Last updated 9 days ago