AI Pricing Hub

io.github.gishhPublished by GitHub account gishhv1.0.0Updated Oct 24, 2026

Source-backed AI model pricing, rankings, history, and benchmark data.

VerifiedStreamable HTTPWeb executableData & AnalyticsAI & ML

Overview

AI-generated overview

A remote MCP server that gives assistants source-backed AI model pricing, cost estimates, benchmark rankings, and pricing history for choosing models.

What you can do
Search the model catalog by provider, workload, context, and price filters, and compare models on pricing, context, and benchmarks. Estimate request cost from input, cached input, output tokens, and request count, including optional batch rates. Find the cheapest models or rank models by benchmark value per token price. Look up provider summaries, benchmark rows, historical pricing snapshots, and recent launches, removals, and price changes. Search news items and get model recommendations for a workload.
When to use it
Useful when comparing AI model costs or capabilities, estimating spend for a planned workload, checking whether a provider's prices changed, or picking a model with benchmark evidence rather than guesswork.
Requirements
A remote streamable HTTP endpoint; no local runtime, account, API key, or headers are declared. Network access to the endpoint is required.
Before you install
Pricing and benchmark data are third-party and may lag real provider rates, so verify costs before relying on them for billing decisions. The tools are read-only lookups and estimates; no credentials are requested.

Installation

In SourceWeft

  1. Open AI Pricing Hub in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.gishh%2Faipricinghub/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "ai-pricing-hub": {
      "type": "http",
      "url": "https://aipricinghub.com/mcp/rpc"
    }
  }
}

README

This repository has no README.

Tools

11

search_models

Search models

Search the pricing catalog with provider, workload, context, and price filters.

Parameterslimitquerycursorproviderworkloadmax_combined_pricemin_context_tokens

compare_models

Compare models

Compare pricing, context, and sourced benchmarks for model IDs.

Parametersmodel_ids

calculate_cost

Calculate cost

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.

Parametersmodel_idrequestsbatch_modeinput_tokensoutput_tokenscached_input_tokens

find_cheapest

Find cheapest

Find cheapest models by combined listed input plus output token price.

Parameterslimitcursorproviderworkload

find_best_value

Find best value

Rank models by available benchmark signal per listed token price.

Parameterslimitcursorproviderbenchmark_id

provider_summary

Provider summary

Summarize model count, prices, benchmarks, and changes for a provider.

Parametersprovider

pricing_history

Pricing history

Return historical pricing snapshots for a model ID.

Parametersmodel_id

benchmark_lookup

Benchmark lookup

Find sourced benchmark rows by model, provider, or benchmark ID.

Parameterslimitcursormodel_idproviderbenchmark_id

latest_changes

Latest changes

Return recent model launches, removals, and pricing changes.

Parameterstypelimitcursorprovider

search_news

Search news

Search AI Pricing Hub news items.

Parameterslimitquerycursorsourcelanguage

recommend_model

Recommend model

Recommend models for a workload using price, context, and benchmark evidence.

Parameterslimitbudgetproviderworkloadmin_context_tokens

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.