PromptSpend

io.github.AndrewAvery7/promptspendVersion 0.1.11

LLM pricing where every rate carries its source and the date it was last confirmed.

Status

Responds110 msNov 14, 2026, 14:35 UTCAnswered our handshake without sign-in.

We could not refresh it, so this page shows the last copy.

Data from the official MCP Registry, checked by run.zero. How we check

Streamable HTTP

https://promptspend.dev/mcpResponds110 msNov 14, 2026, 14:35 UTC

No sign-in

claude mcp add --transport http promptspend https://promptspend.dev/mcp

1
2
3

Settings > Connectors > Add custom connector
Name: promptspend
Remote MCP server URL: https://promptspend.dev/mcp

{
  "mcpServers": {
    "promptspend": {
      "url": "https://promptspend.dev/mcp"
    }
  }
}

code --add-mcp '{"name":"promptspend","type":"http","url":"https://promptspend.dev/mcp"}'

Streamable HTTP

npm: @promptspend/mcp 0.1.11

Package only

claude mcp add promptspend -- npx -y @promptspend/mcp@0.1.11

Built your own server? run.zero hosts MCP servers on European infrastructure.

3 tools

Tools of PromptSpend
	Description		Read-only	Idempotent	Open world
`estimate_cost`Monthly cost of a described workload, or of measured usage, on each model. Accounts for history compounding, cache writes, long-context tiers and reasoning tokens. Use this instead of multiplying prices by hand.	Monthly cost of a described workload, or of measured usage, on each model. Accounts for history compounding, cache writes, long-context tiers and reasoning tokens. Use this instead of multiplying prices by hand.	Not declared	Yes	Not declared	Yes
`find_cheaper`Cheaper models that score at or above the given one on capability, costed on the same workload. Returns candidates to test, not a recommendation.	Cheaper models that score at or above the given one on capability, costed on the same workload. Returns candidates to test, not a recommendation.	Not declared	Yes	Not declared	Yes
`get_price`List price for one LLM in USD per million tokens, with its source and last-confirmed date. Returns disputed=true when two sources disagree, and close matches when the model is unknown. To cost a workload, use estimate_cost.	List price for one LLM in USD per million tokens, with its source and last-confirmed date. Returns disputed=true when two sources disagree, and close matches when the model is unknown. To cost a workload, use estimate_cost.	Not declared	Yes	Not declared	Yes

Registry status: Active
Published: Oct 29, 2026
Updated: Oct 29, 2026
Website: https://promptspend.com/⁠ (opens in a new tab)
Repository: https://github.com/AndrewAvery7/promptspend⁠ (opens in a new tab)
Categories (suggested): AI modelsSuggested categories are assigned automatically from the registry text and may be wrong. Verified operators can correct them.
GDPR: Not declared