Skip to content
AuraMatrix
Use in your AI

Use in your AI

Ask your assistant, get a sourced price.

The index is an MCP server. Connect it once and your assistant can look up any model's price on any channel, compare channels, find the cheapest, and see what changed, always with the source and time.

The address

https://auramatrix.ai/mcp

Streamable HTTP, read-only, no account or key. One request at a time per client, small responses, rate-limited.

Connect

Claude Code

claude mcp add --transport http auramatrix https://auramatrix.ai/mcp

Run in a terminal, then ask Claude Code about token prices.

Codex

codex -c 'mcp_servers.auramatrix.url="https://auramatrix.ai/mcp"'

Starts Codex with the index attached for this session.

Cursor / other

{
  "mcpServers": {
    "auramatrix": {
      "url": "https://auramatrix.ai/mcp"
    }
  }
}

Paste into the MCP settings of Cursor, Windsurf or any client that takes a JSON config.

The five tools

  • list_models: every model with its official input and output price, lowest channel and page. Filter by vendor or text.
  • get_price: one model, every channel: region, pricing mode, cached and batch rates, tiers, announced changes, trust status, observation time, source snapshot.
  • compare_channels: the same model across channels, sorted by input price, each with its difference from the official list price.
  • cheapest: models ordered by their lowest input price on any channel, optionally by vendor or channel type.
  • price_changes: observed changes between records and vendor-announced changes with effective dates.

Every answer ends with the same boundary the pages carry: list prices as published at the observed time, the channel's own page is authoritative, aggregator prices are never the reference, missing means unknown.

Without MCP

Plain HTTP, JSON back: https://auramatrix.ai/prices/v1/quote?model=openai/gpt-6.1-sol. Add &channel=azure-datazone-eu for one channel; model=list returns the ids. The whole dataset is at https://auramatrix.ai/prices/index.json, and a short guide for agents at https://auramatrix.ai/prices/v1/llms.txt.

What to expect

  • Each record carries trust_status: VERIFIED means a second person checked it against the source; UNVERIFIED means recorded, not yet checked.
  • Field names are stable, but the HTTP endpoint is not yet a frozen API version. A v1 with history and change events is planned; see Methodology.