AI Pricing Hub
Server Details
Source-backed AI model pricing, rankings, history, and benchmark data.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Most tools have clearly distinct purposes: cost calculation, benchmark lookup, news search, and historical changes are well separated. However, several model-discovery tools (search_models, find_cheapest, find_best_value, recommend_model, compare_models) overlap in filtering or ranking models, which could occasionally cause misselection.
All names use snake_case consistently, which is readable. However, the pattern is not uniformly verb_noun: several are noun phrases (benchmark_lookup, pricing_history, provider_summary, latest_changes), creating minor inconsistency in verb style.
11 tools is well within the ideal range for a pricing hub. Each tool serves a clear function, and the set feels appropriately scoped without obvious redundancy.
The surface covers core pricing workflows: search, cost estimation, comparison, recommendation, benchmarks, history, changes, provider summaries, and news. Minor gaps exist, such as no direct tool to fetch a single model's full details or list all providers, but agents can work around these via existing tools.
Available Tools
11 toolsbenchmark_lookupBenchmark lookupBRead-onlyInspect
Find sourced benchmark rows by model, provider, or benchmark ID.
Inputs: limit, cursor, model_id, provider, +1 more. Returns: object
calculate_costCalculate costBRead-onlyInspect
Estimate cost from total input tokens, their cached subset, output tokens and request count. Optional batch_mode uses available batch rates with standard-rate fallback.
Inputs: model_id, requests, batch_mode, input_tokens, +2 more. Returns: object
compare_modelsCompare modelsBRead-onlyInspect
Compare pricing, context, and sourced benchmarks for model IDs.
Inputs: model_ids. Returns: object
find_best_valueFind best valueBRead-onlyInspect
Rank models by available benchmark signal per listed token price.
Inputs: limit, cursor, provider, benchmark_id. Returns: object
find_cheapestFind cheapestBRead-onlyInspect
Find cheapest models by combined listed input plus output token price.
Inputs: limit, cursor, provider, workload. Returns: object
latest_changesLatest changesARead-onlyInspect
Return recent model launches, removals, and pricing changes.
Inputs: type, limit, cursor, provider. Returns: object
pricing_historyPricing historyARead-onlyInspect
Return historical pricing snapshots for a model ID.
Inputs: model_id. Returns: object
provider_summaryProvider summaryARead-onlyInspect
Summarize model count, prices, benchmarks, and changes for a provider.
Inputs: provider. Returns: object
recommend_modelRecommend modelBRead-onlyInspect
Recommend models for a workload using price, context, and benchmark evidence.
Inputs: limit, budget, provider, workload, +1 more. Returns: object
search_modelsSearch modelsCRead-onlyInspect
Search the pricing catalog with provider, workload, context, and price filters.
Inputs: limit, query, cursor, provider, +3 more. Returns: object
search_newsSearch newsCRead-onlyInspect
Search AI Pricing Hub news items.
Inputs: limit, query, cursor, source, +1 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Current AI model rankings, API prices, benchmark results and history from BenchLM.
AI model prices per provider, benchmarks, own AI behavior tests and AI economy data, with sources.
Sourced AI-model pricing and capability data — compare and route to the cheapest capable model.
Live prices, rankings, licences and privacy of AI models: best model per task, costs, alternatives.
Related MCP Servers
AlicenseNot gradedqualityBmaintenanceLive, sourced pricing and benchmark data across image, language, video, and audio AI models, seven tools for comparison, competitor lookups, and cost-aware routing. Also powers the free Modelglass VS Code extension.1MIT- AlicenseAqualityDmaintenanceGive your AI assistant real-time LLM/VLM knowledge. Pricing, benchmarks, and recommendations — updated every hour, not every training cycle.490 npm2MIT
- AlicenseAqualityBmaintenanceGlobal price benchmarking for AI inference across 2,600+ SKUs from 47 vendors. Query live pricing, market indexes, and model specs via 8 tools. Free tier available.8MIT
- AlicenseAqualityBmaintenanceWhich 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.11MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.