LLM API Cost Estimator

LLM API Cost Estimator MCP Connector for Claude

A+

Calculate exact API costs and track session budgets for LLM workflows.

3 tools Official Updated Oct 1, 2026 Official Vinkius Partner

Prevent budget overruns in agentic workflows by calculating precise token costs. This MCP provides tools to determine the cost of individual LLM calls and track cumulative spending across entire sessions. Use estimate_single_call to find the cost of a specific request, or track_session_usage to monitor your total spend against a set budget. It supports major providers like OpenAI, Anthropic, and Google with a deterministic pricing matrix.

llmcost-trackingtokensbudgetapi-pricing

3 tools expose this connector's capabilities to your AI agent.

estimate_single_call

Calculates the exact cost of a single API request based on token counts and model type

track_session_usage

Updates the running total of costs for a specific workflow and checks against a defined budget

get_pricing_catalog

Retrieves the current deterministic pricing rates for all supported models

See how to talk to your AI agent using LLM API Cost Estimator.

How much will it cost to run a GPT-4o request with 500 input tokens and 200 output tokens?

The total cost for that request is $0.005.

I have a budget of $5.00 for this session. I just spent $0.50. How much budget is left?

You have $4.50 remaining in your budget.

What are the current pricing rates for Claude 3.5 Sonnet?

Claude 3.5 Sonnet has an input rate of $3.00 per 1M tokens and an output rate of $15.00 per 1M tokens.

You can use the `estimate_single_call` tool by providing the model ID and the number of input and output tokens.

Related Connectors