How do I use this MCP with Claude?

You connect to the MCP through the Vinkius platform. Once connected, your Claude client can immediately use the capabilities to perform cost calculations.

Can I compare different AI providers?

Yes. You can use the compare_providers capability to see which model tier is most economical for your specific token usage.

Does this capability handle monthly forecasting?

Yes. The estimate_monthly_spend capability projects your total expenditure over a 30-day period based on your daily request estimates.

Can I calculate the savings from prompt caching?

Yes. The calculate_cache_impact capability shows how much a high cache hit ratio reduces your request costs.

Do I need to provide my own API keys for the providers?

No. This MCP calculates the math based on provider pricing data. It does not execute the actual API calls to the providers.

How is the monthly cost calculated?

The capability calculates the cost of a single request based on your input and output tokens, then multiplies that by your estimated daily requests and 30 days.

Can I compare different models like GPT-4o and Claude?

Yes, by using the compare_providers capability, you can input multiple tier IDs to see a ranked list of costs from cheapest to most expensive.

Does the calculator account for prompt caching?

Yes, you can use calculate_cache_impact to determine how much a specific cache hit ratio will reduce your input token costs.

An astronaut overseeing a futuristic data hub

Download PDF Markdown Version

Connect LLM API Cost Calculator to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Stop guessing how much your AI workloads actually cost.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 4 capabilities

We ship only the actions that matter.

Capability set01 / 01

01-04

4 capabilities in this set.

Part of 4 available through LLM API Cost Calculator.

01
Compute request cost
This capability calculates the exact dollar amount for a single LLM API call based on your token counts.
02
Calculate cache impact
This capability determines how much money you save by using prompt caching for specific requests.
03
Compare providers
This capability runs a side-by-side pricing analysis across different model tiers to find the best value.
04
Estimate monthly spend
This capability projects your total costs over a 30-day window using your estimated daily request volume.

Real work

What teams actually run

Prototyping Costs

Calculate the cost of a single test prompt before deploying it to a large user base.

Scaling Decisions

Compare different model tiers to see if a cheaper model can handle your production volume.

Budget Planning

Forecast how much your monthly API bill will be if you hit certain usage milestones.

Optimization

Determine if implementing prompt caching will actually lower your total spend.

One connector, every AI

LLM API Cost Calculator works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

Building your own app? The connector is yours to use.

You don't need a client to put LLM API Cost Calculator to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

706ms average. Fast in production.

LLM API Cost Calculator is checked daily against the live service.

Daily averagePeak 846ms

Oct 3Today

Fastest day: 568ms
Slowest day: 846ms
14-day trend: Stable-1%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 4 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of LLM API Cost Calculator, so you can see the experience inside your AI.

It does not authenticate your account with LLM API Cost Calculator. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

LLM API Cost Calculator Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_kJ7vtlOfVbB3mYe7tCKK0Sz4MTZKFnSeYxrrgdxC/mcp

Claude Desktop

Follow the steps below to connect in seconds.

1In Claude Desktop, open Settings → Connectors.
2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
3Click Add and start a new chat — LLM API Cost Calculator capabilities are ready to use.

Configuration · claude_desktop_config.jsonCopy

{
  "mcpServers": {
    "llm-api-cost-calculator-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_kJ7vtlOfVbB3mYe7tCKK0Sz4MTZKFnSeYxrrgdxC/mcp"
    }
  }
}

Claude
ChatGPT
Cursor
VS Code
Windsurf
Claude Code
JetBrains
Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up LLM API Cost Calculator in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work LLM API Cost Calculator owners hand off.

This MCP is built for developers and product owners who need to manage the financial side of AI implementation.

01
AI Engineers
They ask the agent to calculate costs during the prototyping phase.
02
Product Managers
They use the agent to forecast monthly operational expenses for new features.
03
DevOps Engineers
They check the impact of prompt caching on overall infrastructure spend.

FAQ

Questions LLM API Cost Calculator owners ask.

01
How do I use this MCP with Claude?
You connect to the MCP through the Vinkius platform. Once connected, your Claude client can immediately use the capabilities to perform cost calculations.
02
Can I compare different AI providers?
Yes. You can use the compare_providers capability to see which model tier is most economical for your specific token usage.
03
Does this capability handle monthly forecasting?
Yes. The estimate_monthly_spend capability projects your total expenditure over a 30-day period based on your daily request estimates.
04
Can I calculate the savings from prompt caching?
Yes. The calculate_cache_impact capability shows how much a high cache hit ratio reduces your request costs.
05
Do I need to provide my own API keys for the providers?
No. This MCP calculates the math based on provider pricing data. It does not execute the actual API calls to the providers.
06
How is the monthly cost calculated?
The capability calculates the cost of a single request based on your input and output tokens, then multiplies that by your estimated daily requests and 30 days.
07
Can I compare different models like GPT-4o and Claude?
Yes, by using the compare_providers capability, you can input multiple tier IDs to see a ranked list of costs from cheapest to most expensive.
08
Does the calculator account for prompt caching?
Yes, you can use calculate_cache_impact to determine how much a specific cache hit ratio will reduce your input token costs.

Explore

More in Productivity

Connect LLM API Cost Calculator to Claude, Cursor, ChatGPT & more

Your AI does the work. We keep it safe and sound.

Each Connector runs inside its own sealed environment.

One switch stops every agent. Instantly.

Spending limits that pause instead of surprise.

We ship only the actions that matter.

01-04

Compute request cost

Calculate cache impact

Compare providers

Estimate monthly spend

What teams actually run

Prototyping Costs

Scaling Decisions

Budget Planning

Optimization

Building your own app? The connector is yours to use.

LLM API Cost Calculator Connector

Claude Desktop

AI Engineers

Product Managers

DevOps Engineers

How do I use this MCP with Claude?

Can I compare different AI providers?

Does this capability handle monthly forecasting?

Can I calculate the savings from prompt caching?

Do I need to provide my own API keys for the providers?

How is the monthly cost calculated?

Can I compare different models like GPT-4o and Claude?

Does the calculator account for prompt caching?

LLM API Cost Estimator AI Connector

Token Cost Estimator AI Connector

AI App Development Cost Estimator AI Connector

Alcohol Cost-per-Buzz Calculator AI Connector

Suggestions

Token Counter and Budget Enforcer AI Connector

Construction Cost Estimator AI Connector

Token Budget Remaining Calculator AI Connector

RAG Implementation Cost Estimator AI Connector