AI Pricing Hub

Last 30 days

Uptime

100%

Response time

243 ms typical, 243 ms slowest 5%

Last check

3 h ago

Next check

in 3 h

How to call it

Add it to any MCP client that supports remote servers.

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

11 tools

• 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.

Security scan

• No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks