Copilot

Copilot is your in-editor assistant that helps you build and edit workflows with Sim Copilot, as well as understand and improve them. It can:

Explain: Answer questions about Sim and your current workflow
Guide: Suggest edits and best practices
Edit: Make changes to blocks, connections, and settings when you approve

Copilot is a Sim-managed service. For self-hosted deployments, generate a Copilot API key in the hosted app (sim.ai → Settings → Copilot)

Go to sim.ai → Settings → Copilot and generate a Copilot API key
Set COPILOT_API_KEY in your self-hosted environment to that value

Use the @ symbol to reference various resources and give Copilot more context about your workspace:

Copilot context menu showing available reference options

The @ menu provides access to:

Chats: Reference previous copilot conversations
All workflows: Reference any workflow in your workspace
Workflow Blocks: Reference specific blocks from workflows
Blocks: Reference block types and templates
Knowledge: Reference your uploaded documents and knowledgebase
Docs: Reference Sim documentation
Templates: Reference workflow templates
Logs: Reference execution logs and results

This contextual information helps Copilot provide more accurate and relevant assistance for your specific use case.

Modes

Ask

Q&A mode for explanations, guidance, and suggestions without making changes to your workflow.

Agent

Build-and-edit mode. Copilot proposes specific edits (add blocks, wire variables, tweak settings) and applies them when you approve.

Depth Levels

Fast

Quickest and cheapest. Best for small edits, simple workflows, and minor tweaks.

Auto

Balanced speed and reasoning. Recommended default for most tasks.

Advanced

More reasoning for larger workflows and complex edits while staying performant.

Behemoth

Maximum reasoning for deep planning, debugging, and complex architectural changes.

Mode Selection Interface

You can easily switch between different reasoning modes using the mode selector in the Copilot interface:

Copilot mode selection showing Advanced mode with MAX toggle

The interface allows you to:

Select reasoning level: Choose from Fast, Auto, Advanced, or Behemoth
Enable MAX mode: Toggle for maximum reasoning capabilities when you need the most thorough analysis
See mode descriptions: Understand what each mode is optimized for

Choose your mode based on the complexity of your task - use Fast for simple questions and Behemoth for complex architectural changes.

Billing and Cost Calculation

How Costs Are Calculated

Copilot usage is billed per token from the underlying LLM:

Input tokens: billed at the provider's base rate (at-cost)
Output tokens: billed at 1.5× the provider's base output rate

copilotCost = (inputTokens × inputPrice + outputTokens × (outputPrice × 1.5)) / 1,000,000

Component	Rate Applied
Input	inputPrice
Output	outputPrice × 1.5

Pricing shown reflects rates as of September 4, 2025. Check provider documentation for current pricing.

Model prices are per million tokens. The calculation divides by 1,000,000 to get the actual cost. See the Cost Calculation page for background and examples.