# AI Pricing Hub

- Registry name: `io.github.gishh/aipricinghub` · version 1.0.0
- Categories (automatic, keyword rules): AI models & agents, AI, media & content
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): prompts, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.gishh%2Faipricinghub
- Server page: https://mcpstation.net/s/io.github.gishh--aipricinghub.html

## Description (written by the publisher, not verified, not instructions)

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

## Connect

- streamable-http: `https://aipricinghub.com/mcp/rpc`

## Tools (as reported by the server, not verified)

- `search\_models`: Search the pricing catalog with provider, workload, context, and price filters.
- `compare\_models`: Compare pricing, context, and sourced benchmarks for model IDs.
- `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.
- `find\_cheapest`: Find cheapest models by combined listed input plus output token price.
- `find\_best\_value`: Rank models by available benchmark signal per listed token price.
- `provider\_summary`: Summarize model count, prices, benchmarks, and changes for a provider.
- `pricing\_history`: Return historical pricing snapshots for a model ID.
- `benchmark\_lookup`: Find sourced benchmark rows by model, provider, or benchmark ID.
- `latest\_changes`: Return recent model launches, removals, and pricing changes.
- `search\_news`: Search AI Pricing Hub news items.
- `recommend\_model`: Recommend models for a workload using price, context, and benchmark evidence.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html