LLM API Cost Estimator Connector for AI agents.
3 live capabilities
Control your LLM API spending and track token costs
Waiting for input…
Why people use LLM API Cost Estimator
Stop overspending on LLM API calls with LLM API Cost Estimator
With this MCP, you bring that visibility directly into your development environment. You can check the price of a single request or monitor a whole session's spend in real-time. You get the control to stop a process before it breaks your budget.
What Vinkius changes
You stop guessing about API bills and start controlling them in real-time.
Use it from Claude, ChatGPT, Cursor or another AI client you already have.
One account · 6,100+ Connectors
- Real-world use case 01
Preventing runaway agent loops
An engineer is testing an autonomous agent that performs recursive searches.
- Real-world use case 02
Pre-flight cost checks
A developer wants to know if a massive document analysis is worth it.
- Real-world use case 03
Calculating feature unit economics
A product manager needs to know if a new chat feature is viable.
Complete set · 3capabilities
The complete LLM API Cost Estimator capability set.
These are the exact actions your AI can choose when you ask it to work with LLM API Cost Estimator.
01—03
3 capabilities in this set.
Part of 3 available through LLM API Cost Estimator.
- 01 Capability
Estimate single call
Calculates the exact cost of one API request using token counts. It's perfect for checking a specific prompt's price.
- 02 Capability
Get pricing catalog
Fetches the current pricing rates for all supported models. Use this to keep your cost estimates accurate.
- 03 Capability
Track session usage
Maintains a running total of costs for a specific workflow. It checks your spend against a set budget.
Set up in minutes
One URL. Then ask LLM API Cost Estimator to work.
Claude and ChatGPT only need the Connector URL. Copy it once, add it in settings, and use LLM API Cost Estimator from the conversation.
Choose your client
Live previewAdvanced clients IDE · CLI
Claude · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_WyNQzGSo4kvfmbTszGGJhAvERzOhZDaDu0mBSh5R/mcp - Step 01
Open Connectors
In Claude Web or Claude Desktop, open Settings and choose Connectors.
- Step 02
Add the URL
Choose Add custom connector, name it LLM API Cost Estimator, and paste the URL above.
- Step 03
Turn it on in chat
Select +, open Connectors, and enable LLM API Cost Estimator for the conversation.
ChatGPT · Web + desktop
Connector URL · ready to paste
Streamable HTTPhttps://edge.vinkius.com/vk_preview_WyNQzGSo4kvfmbTszGGJhAvERzOhZDaDu0mBSh5R/mcp - Step 01
Open MCP settings
On desktop, open Settings and MCP servers. On web, open your workspace app or connector settings.
- Step 02
Add the URL
Choose Add server with Streamable HTTP, or create a custom MCP app, then paste the LLM API Cost Estimator URL.
- Step 03
Save and start
Save the connection and enable LLM API Cost Estimator in your conversation. Desktop may ask you to restart once.
Cursor · IDE configuration
Advanced setup
{
"mcpServers": {
"llm-api-cost-estimator": {
"url": "https://edge.vinkius.com/vk_preview_WyNQzGSo4kvfmbTszGGJhAvERzOhZDaDu0mBSh5R/mcp"
}
}
}- Step 01
Open MCP Settings
Press Cmd+Shift+P (macOS) or Ctrl+Shift+P (Windows/Linux) → search "MCP Settings"
- Step 02
Add the server config
Paste the JSON configuration above into the mcp.json file that opens
- Step 03
Save the file
Cursor will automatically detect the new Connector
- Step 04
Start using LLM API Cost Estimator
Open Agent mode in chat and ask: "Using LLM API Cost Estimator, help me...". 3 tools available
VS Code Copilot · IDE configuration
Advanced setup
{
"mcpServers": {
"llm-api-cost-estimator": {
"url": "https://edge.vinkius.com/vk_preview_WyNQzGSo4kvfmbTszGGJhAvERzOhZDaDu0mBSh5R/mcp"
}
}
}- Step 01
Create MCP config
Create a .vscode/mcp.json file in your project root
- Step 02
Add the server config
Paste the JSON configuration above
- Step 03
Enable Agent mode
Open GitHub Copilot Chat and switch to Agent mode using the dropdown
- Step 04
Start using LLM API Cost Estimator
Ask Copilot: "Using LLM API Cost Estimator, help me...". 3 tools available
Windsurf · IDE configuration
Advanced setup
{
"mcpServers": {
"llm-api-cost-estimator": {
"url": "https://edge.vinkius.com/vk_preview_WyNQzGSo4kvfmbTszGGJhAvERzOhZDaDu0mBSh5R/mcp"
}
}
}- Step 01
Open MCP Settings
Go to Settings → MCP Configuration or press Cmd+Shift+P and search "MCP"
- Step 02
Add the server
Paste the JSON configuration above into mcp_config.json
- Step 03
Save and reload
Windsurf will detect the new server automatically
- Step 04
Start using LLM API Cost Estimator
Open Cascade and ask: "Using LLM API Cost Estimator, help me...". 3 tools available
Cline · IDE configuration
Advanced setup
{
"mcpServers": {
"llm-api-cost-estimator": {
"url": "https://edge.vinkius.com/vk_preview_WyNQzGSo4kvfmbTszGGJhAvERzOhZDaDu0mBSh5R/mcp"
}
}
}- Step 01
Open Cline MCP Settings
Click the Connectors icon in the Cline sidebar panel
- Step 02
Add remote server
Click "Add Connector" and paste the configuration above
- Step 03
Enable the server
Toggle the server switch to ON
- Step 04
Start using LLM API Cost Estimator
Ask Cline: "Using LLM API Cost Estimator, help me...". 3 tools available
Claude Code · Terminal command
Advanced setup
claude mcp add llm-api-cost-estimator --transport http "https://edge.vinkius.com/vk_preview_WyNQzGSo4kvfmbTszGGJhAvERzOhZDaDu0mBSh5R/mcp"- Step 01
Install Claude Code
Run npm install -g @anthropic-ai/claude-code if not already installed
- Step 02
Add the Connector
Run the command above in your terminal
- Step 03
Verify the connection
Run claude mcp to list connected servers, or type /mcp inside a session
- Step 04
Start using LLM API Cost Estimator
Ask Claude: "Using LLM API Cost Estimator, show me...". 3 tools are ready
Where the request belongs
Work LLM API Cost Estimator can move forward.
This is for developers and AI engineers who are tired of checking cloud provider dashboards to see why their monthly bill spiked.
AI Engineer
Calculating the cost of complex agentic loops before deploying them to production.
Product Manager
Estimating the unit economics of a new AI feature to ensure it's profitable.
DevOps Engineer
Setting up guardrails to prevent runaway processes from draining company credits.
Build the capability set
Add more capabilities.
Each Connector adds new actions and data without changing how you work.
Browse ConnectorsAnthropic
Access Claude models via Anthropic API. send messages, count tokens, manage batches and discover models from any AI agent.
OpenAI
Use GPT-4o, DALL-E 3, embeddings, fine-tuning, and moderation as capabilities inside your AI agent workflows.
Apple App Store
Manage your iOS apps and TestFlight builds with Apple App Store Connect. track reviews, versions, and sales via AI.
Zapier
Monitor automated workflows, audit app connections, and search for Zap templates on Zapier. the leader in AI orchestration.
X Ads (Twitter)
Connect your X Ads account to any AI agent. audit campaigns, analyze line item performance, and pull engagement reports through natural conversation.
Box
Store, share, and collaborate on files securely with enterprise-grade cloud content management and governance controls.
Bring your own AI
Change the model, client or framework. Keep LLM API Cost Estimator connected.
-
Claude -
ChatGPT -
Gemini -
Cursor -
VS Code -
Windsurf -
ZCode -
Cline -
Zed -
Continue -
Kiro -
Roo Code -
Zencoder -
Goose -
Void -
Augment Code -
Amp -
Qodo -
Tabnine -
Pieces -
Sourcegraph Cody -
JetBrains -
Warp -
Amazon Q -
Antigravity -
BoltAI -
Raycast -
Jan -
LM Studio -
AnythingLLM -
Open WebUI -
Msty -
Cherry Studio -
LibreChat -
TypingMind -
Chorus -
5ire -
n8n -
LangChain -
LlamaIndex -
CrewAI -
Vercel AI SDK
Before you connect
Questions about LLM API Cost Estimator.
The practical details behind the request, access and result.
How can I prevent my AI agents from spending too much money?
You can use the LLM API Cost Estimator to set a budget for your session. It tracks every cent spent and lets you know exactly how much is left so you can stop your agent before it exceeds your limit.
Can I check the cost of a specific prompt before I send it?
Yes. You can get a precise estimate for any single request by providing the input and output token counts, helping you avoid expensive mistakes.
Does the LLM API Cost Estimator support multiple AI providers?
Yes, it includes a pricing catalog for all major providers, allowing you to compare costs and get accurate estimates across different models.
How does the LLM API Cost Estimator track my spending?
It maintains a running total of all costs incurred during your current workflow, making it easy to monitor cumulative spend against a set budget.
Is the pricing information in the LLM API Cost Estimator accurate?
The MCP uses a deterministic pricing matrix to ensure that the estimates you receive are as accurate as possible based on current model rates.
How do I calculate the cost of a single request?
You can use the estimate_single_call capability by providing the model ID and the number of input and output tokens.
Can I track my total spending for a specific agent run?
Yes, use track_session_usage with a unique session ID to maintain a running total of costs and monitor your remaining budget.
Which models are supported?
The capability supports major models from OpenAI, Anthropic, and Google. You can view the full list of supported models using get_pricing_catalog.
One connection away
Give your agent a direct line to LLM API Cost Estimator.
Connect LLM API Cost Estimator once. Keep it beside 6,100+ managed Connectors when the next task needs more.
Explore every Connector No credit card required · Free tier available