Free tool · #11

Prompt Hash Lookup

Compute the canonical template hash for a prompt — the same normalization production ingestion uses to group cost and quality across every filled-in instantiation.

Prompt template

Hashed entirely in your browser — nothing is sent anywhere.

Canonical hash

prompt_hash (sha256, hex)

e7f8adb123714ccb29fed139dd6dd0e2d46135d9bcb20ec6c8896cb3859f7a84

Normalized template

Summarize ⟨var⟩ for a ⟨var⟩ reader in ⟨var⟩ sentences.

Tone: ⟨var⟩. Budget: ⟨var⟩ tokens.

Variable slots detected

Name	Syntax	Raw
`article`	mustache — {{ name }}	`{{article}}`
`audience`	mustache — {{ name }}	`{{audience}}`
`n`	python format — {name}	`{n}`
`tone`	percent — %(name)s	`%(tone)s`
`max_tokens`	dollar — ${name}	`${max_tokens}`

Two calls that fill this template with different variable values still produce the same prompt_hash — the hash is computed from the template shape, not the filled-in text. That is what lets cost and quality analytics group every instantiation of one prompt together, instead of splintering into one bucket per call.

This is the exact algorithm behind prompt_hash in Telemeter’s canonical event schema — the field every ingested LLM call carries, computed once in lib/prompt-hash.ts and reused unchanged by production ingestion, so a hash computed here matches what a live SDK, OTel, or proxy call would record for the same template.

Use this tool from code — or hand it to your agentagent prompt · REST · MCP

Hand this tool to your coding agent

Paste into Claude Code, Cursor, Codex, or any agent. It learns to call this tool over REST or MCP, reaches for it when you ask, and keeps our sourced/pending labels honest.

You can use telemeter.ai's free "Prompt Hash Lookup" — a keyless, read-only tool (no signup), available as an HTTP API and an MCP tool. What it does: Compute the canonical template hash for a prompt — the same normalization production ingestion uses to group cost and quality across every filled-in instantiation.

Whenever I ask you something this tool answers, call it and use its result instead of estimating yourself.

REST:
  curl -sX POST https://telemeter.ai/api/tools/prompt-hash -H 'content-type: application/json' -d '{"template":"Summarize the following support ticket in one sentence: {{ticket_body}}"}'

MCP: the telemeter MCP server at https://telemeter.ai/mcp exposes this as the tool "prompt-hash" — call it with tools/call.

The response is JSON: { status, data, summary, provenance }. "provenance" carries the source and the date the figure was verified. If status is "pending" or "stale", tell me the value isn't currently verified rather than presenting it as fact.

Or call it directly. This tool runs behind one handler with three front doors — this page, a REST endpoint, and an MCP tool. Same result, read-only, no key. The example below is a request that works.

REST

curl -sX POST https://telemeter.ai/api/tools/prompt-hash \
  -H 'content-type: application/json' \
  -d '{"template":"Summarize the following support ticket in one sentence: {{ticket_body}}"}'

MCP — tools/call at https://telemeter.ai/mcp

curl -sX POST https://telemeter.ai/mcp \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"prompt-hash","arguments":{"template":"Summarize the following support ticket in one sentence: {{ticket_body}}"}}}'

Input schema (JSON Schema)

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "template": {
      "type": "string",
      "maxLength": 200000
    }
  },
  "required": [
    "template"
  ],
  "additionalProperties": false
}

Want this across your whole stack?

Telemeter tracks real cost, latency, and quality on every production agent run.

Join the waitlist See how it works

Share or cite this tool

https://telemeter.ai/tools/prompt-hash

No account, no cookies, nothing stored — hashed entirely in your browser and never sent anywhere. Data notice →