Gemini Cost Simulator
Server Details
Gemini 4 agent-run cost simulator over MCP: true per-turn totals vs naive estimates.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- Repository
- gowinder/geminicost-mcp
- GitHub Stars
- 0
- Server Listing
- Gemini Cost Simulator
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: estimate_agent_run simulates a multi-turn agent run, while get_gemini_pricing retrieves the pricing segment and rates for a date/model. An agent can easily tell which tool to use for cost simulation versus pricing lookup.
Both names use consistent snake_case with a clear verb-led pattern: estimate_agent_run and get_gemini_pricing. The convention is predictable and readable.
Two tools is small, but for a narrowly scoped Gemini cost simulator it is reasonable: one tool retrieves pricing data and one tool uses it to simulate run cost. It is slightly thin but not inappropriate for the domain.
The surface covers the core lifecycle: looking up pricing segments and estimating turn-by-turn agent run costs, including pre- and post-price-change scenarios. Minor gaps exist around batch comparisons or broader model exploration, but the advertised purpose is well covered.
Available Tools
2 toolsestimate_agent_runEstimate the cost of one Gemini 4 agent runBInspect
Turn-by-turn cost of a Gemini 4 agent run: every turn re-sends the growing context as input, thinking tokens are billed at the output rate. Returns the rates in force on the chosen date, the simulated total, the naive first-turn × turns estimate and their multiplier. Before the 2026-12-01 price change it also returns afterIncrease: the same run priced at the announced 2026-12-01 rates.
Inputs: turns (required), modelId (required), thinkingLevel (required), outputTokensPerTurn (required), +4 more.
get_gemini_pricingGet Gemini 4 list prices for a dateAInspect
Price segment in force on a date for every recorded Gemini 4 model, or for one model: input and output USD per 1,000,000 tokens, the segment start and end dates and its status. Segments marked announced-unpriced have no published values and are reported as such.
Inputs: date, modelId.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Agent Cost Allocator MCP — multi-tenant LLM cost attribution for chargeback billing. Companion to
Agent Token Budget MCP — hard per-session token + spend cap with signed budget-exhausted
Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.
Two sample multi-agent blueprints over MCP, no signup. Main server: agentblueprint.ai/mcp
Related MCP Servers
- AlicenseAqualityCmaintenanceMCP server that scores tool descriptions, estimates token costs, simulates agent tool selection, and generates reliability reports to help AI agents choose the right tools and reduce wasted tokens.59 npmMIT
- AlicenseNot gradedqualityDmaintenanceLLM cost optimization and provider usage visibility for MCP-capable agents.88 npmMIT
- AlicenseBqualityDmaintenanceTrack LLM token costs across Claude, GPT and Gemini. MCP server + CLI with optimization hints and $ savings estimates.81MIT
- AlicenseNot gradedqualityCmaintenanceLocal-first cost tracking and model routing for MCP agents with offline token counting, budget alerts, and spend reports.83 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.