Credits & Usage

Credits are the currency used on Markifact to run workflows and use advanced features. Certain actions—like fetching external data or using AI models—cost credits. Others are free. The more credits you have, the more automations and AI tasks you can run. All subscription plans include a base number of credits. You can also purchase extra credits anytime.

---

​

Workflows

Workflow credits are charged per execution and per paid node.

• Every workflow run consumes 1 credit, no matter how it’s triggered.
• External/data nodes like Google Analytics, Google Ads, Google Sheets, or Slides start at 1 credit per successful execution.
• AI node costs vary by model (see model tables below).
• Utility nodes—such as lists tools, date pickers, loops, and account selection—are free and never consume credits.
• Only successful nodes are charged. If a node fails, no credit is consumed for that node. Other successful nodes in the same workflow will be charged.

💡 Before running a workflow, you can see the credit estimate for each node directly in the node settings sidebar, in the footer area. This is an estimate, not a guaranteed cost.

• AI nodes vary based on model.
• Data nodes may vary based on account count or request size.

For full details, check each node help page or ask AI Copilot in the app.

​

Workflow Credit-Saving Tips

When testing workflows, avoid running the entire flow:

1. Click the dropdown on a specific node.
2. Select Run Node to execute only that part.

⚠️ Note: If the node has downstream connections, those will also run and may consume credits.

​

AI Model Credit Costs

Two numbers matter per model:

• Node credits: the flat cost of one workflow AI node run on that model.
• Agent multiplier: what the model multiplies agent token usage by. See Agents below.

​

OpenAI Models

​

Gemini Models

​

Claude Models

​

Deepseek Models

​

Image and Video Models

These run as workflow AI nodes and are charged per run, not per token.

---

​

Agents

Agent usage is separate from workflow execution and follows agent-specific rules.

• Markifact Copilot costs 1 credit per message.
• Task Agent usage is based on tokens consumed and the selected model multiplier.

​

Task Agent: How Credit Usage Works

• Each response uses input + output tokens.
• Different models apply different multipliers to token usage. See the Agent multiplier column in the model tables above.
• Example: gpt-5.6-terra and gpt-5.2 are treated as 1x, gpt-5.6-luna and claude-haiku-4-5 are 0.5x, while top reasoning models cost far more per token: claude-opus-5 is 13x and claude-fable-5 is 20x.

​

Why Long Agent Threads Cost More

• Longer conversations consume more tokens because history and context are included.
• Markifact automatically compacts conversation history to reduce token usage.
• Even with compaction, very long threads can become more expensive over time.

​

Agent Credit-Saving Tips

• Start a fresh task when switching to a different objective.
• Use lower-cost models for simple tasks. gpt-5.6-luna (0.5x) and claude-haiku-4-5 (0.5x) cost half of a 1x model per token.
• Reserve the premium reasoning models (claude-fable-5, claude-opus-5, gpt-5.6-sol) for complex reasoning or heavy document work such as deep PDF and PPT tasks. At 13x to 20x, a single long thread on those adds up fast.
• For balanced quality and cost, default to gpt-5.6-terra (1x) for everyday tasks and switch up only when needed.
• Bring your own API keys when possible to reduce platform AI credit usage.

​

Using Your Own API Keys

You can bring your own API keys for AI models and significantly reduce your credit costs. Markifact supports three AI providers:

• OpenAI
• Google Gemini
• Anthropic (Claude)

To add your own API keys, navigate to the Connections page in your account settings and configure your preferred AI provider.

​

Credit Costs with Custom API Keys

When using your own API keys:

• All AI nodes (Ask, Structure, Analyze Data, Analyze Image, Generate Image, Edit Image) consume 0 credits
• AI Agent node costs 1 credit flat per run, regardless of how many tools are used or time spent on the task
• Task Agent AI tokens are billed through your provider key

This makes it extremely cost-effective to run AI-heavy workflows when you have your own API keys. You’ll pay for the AI usage directly through your provider account, while only consuming minimal credits on Markifact for orchestration.

---

​

MCP Servers

MCP lets you use Markifact operations from external AI clients like Claude, ChatGPT, and Cursor. Credit usage for MCP is simple:

• Discovery and utility tools are free. find_operations, get_operation_inputs, list_connections, get_file_url, and read_file cost 0 credits.
• Running operations (run_operation and run_write_operation) costs credits based on the specific operation — the same as the equivalent workflow node.

​

Examples

The rule of thumb: utility and discovery operations (account selection, listing fields, searching) are free. Data operations (pulling reports, reading/writing to platforms) cost credits, typically 1 credit per operation. MCP credit consumption appears in the Usage Dashboard under the MCP service type.

---

​

Tracking Credit Usage

You can monitor credit usage in the Usage Dashboard (also available from the sidebar). In the Usage Dashboard, you can view:

• Credit consumption by service (for example: Workflows, Agents, and Copilot)
• Credit consumption by team member
• Usage over time
• Recent activity for Agents, Workflows, and Copilot

If you send a message to an Agent and want to check how much it cost, you can find that entry in Recent activity table in the dashboard. For workflows, you can also track credits directly while running them:

• During a workflow run, each node displays its credit consumption.
• After the run finishes, the total credits used are shown in the footer.

As shown in the image below, the workflow total and each node’s individual credit consumption are both visible.