GPU and token pricing is scattered across provider pages that each define things differently. Pulse publishes a daily median per index with the methodology version attached and a ready-made citation string, so the number in your model arrives with its provenance.
The MCP interface to Pulse, an open compute-pricing reference. It publishes daily medians for GPU rental and inference tokens under a CC-BY licence: four GPU series comparing hyperscaler against neocloud, four further neocloud series, and an inference-token basket anchored on an open Llama model at FP8.
- Every published index with its current value, freshness, methodology version and status
- The full payload for one index — history, per-provider observations, contributing-provider list — filterable to 30d, 90d, 1y or all
- A quick latest value with a cite_as string ready to paste
- Pipeline freshness and per-provider collection health
- Several indices compared side by side
Nothing — the server is hosted at https://pulsebenchmarks.com/mcp, JSON-RPC 2.0 over POST, no auth. Clients without remote support reach it through mcp-remote.
One command — npx -y mcp-remote https://pulsebenchmarks.com/mcp