Skip to main content
Glama

Server Details

LLM API prices and AI agent cost estimates, verified daily. Read-only cost lookup tools.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-06-18
URL
Repository
agentcosthub/agent-cost-hub-mcp
GitHub Stars
0
Server Listing
Agent Cost Hub MCP Server
ChatGPT
–
Claude
–

TDQS

A3.6/5.0

Scored across 5 tools

Disambiguation3/5

Three tools (cheapest_models_for, compare_models, estimate_cost) all center on monthly cost estimation and could be confused at selection time, especially estimate_cost vs compare_models with a single workload. Descriptions do clarify the distinctions (ranking vs. side-by-side vs. single-model), but the boundaries are not immediately obvious.

Naming Consistency4/5

Four of five tools follow a clear verb_noun pattern (compare_models, estimate_cost, get_model_price, list_models). The outlier cheapest_models_for breaks the verb-led convention, but overall naming remains readable and predictable.

Tool Count5/5

Five tools is well-scoped for a model-pricing and cost-estimation server. Each tool covers a distinct facet (list, price lookup, single estimate, comparison, ranking) without bloat.

Completeness4/5

The surface covers the core lifecycle for pricing data: discovering models, fetching prices, estimating, comparing, and ranking by cost. Minor gaps exist (e.g., no provider listing or historical price trend endpoint), but agents can work around them.

Available Tools

5 tools
cheapest_models_forCheapest models for a workloadA
Read-only
Inspect

Rank models by monthly cost for a workload. Use a preset (chatbot, rag, coding_agent, research_agent) or give token numbers.

Inputs: limit, preset, input_tokens, popular_only, +5 more.

compare_modelsCompare modelsB
Read-only
Inspect

Compare 2-5 models on price and (optionally) on the monthly cost of one workload.

Inputs: models (required), preset, input_tokens, calls_per_day, +4 more.

estimate_costEstimate agent costA
Read-only
Inspect

Estimate the monthly API cost of an AI agent or chatbot on one model. Easiest: pass model + preset (chatbot, rag, coding_agent, research_agent). Or give input_tokens, output_tokens and calls_per_day (plus optional steps_per_task, cached_percent); explicit numbers override the preset.

Inputs: model (required), preset, input_tokens, calls_per_day, +4 more.

get_model_priceGet model priceA
Read-only
Inspect

API list price of one model (input, output, cached input per 1M tokens) plus example monthly agent costs. For retired models, rates are last recorded list prices (see pricing_basis/recorded_note).

Inputs: model (required).

list_modelsList modelsA
Read-only
Inspect

List LLMs tracked by Agent Cost Hub with API list prices per 1M tokens. Optional filter by provider or text.

Inputs: search, provider, popular_only.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Live LLM API pricing: current token prices, model comparisons, cheapest-model lookups, and The LLM Price Index for 150+ models across 20+ providers, re-verified daily. No API key required.
      4
      1
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Which AI model to use and what it costs: LiteLLM's price catalogue with every price change since 2023 and Arena ratings by task. Tools to find and compare models, estimate a job's cost and time, show price history and pick local or cloud; no API keys needed.
      11
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables querying sourced list prices for language-model APIs per channel and GPU rental prices per provider in the US and China, plus cost estimates, price comparisons, and price-change checks, directly from an AI assistant. Includes a tool to anonymously contribute prices users pay, only with explicit consent.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.