Skip to main content
Glama

Prepare Poly-Glot Compare Mode

prepare_compare

Prepare the same canonical prompt for two to nine selected AI providers using a raw prompt or accessible template. Returns provider destinations, prompt and usage instructions without calling third-party models. This is a Send and begins the 3-day trial on first qualifying use; Compare Mode requires active trial or Pro. Use when a user explicitly wants side-by-side answers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoOptional accessible template name; supply this or a raw prompt.
promptNoOptional original prompt for each provider, maximum 30,000 characters; provide this or name.
valuesNoPlaceholder values used when preparing a named template.
providersNoTwo to nine provider IDs; defaults to ChatGPT and Claude and duplicates are removed.
uiLanguageNoInterface language name or code, e.g. EN; independent of source and response languages.EN
inputLanguageNoLanguage name or code of input text, e.g. es; defaults to EN.EN
outputLanguageNoRequested output language name or code, e.g. fr; defaults to EN.EN

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
viewYes
promptNo
messageNo
templateNo
providersNo
entitlementYes
instructionsNo
localizationYes
sourceTemplateNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • addedInput schema / properties / inputLanguage / description
      Added value: +"Language name or code of input text, e.g. es; defaults to EN."
    • addedInput schema / properties / name / description
      Added value: +"Optional accessible template name; supply this or a raw prompt."
    • addedInput schema / properties / outputLanguage / description
      Added value: +"Requested output language name or code, e.g. fr; defaults to EN."
    • addedInput schema / properties / prompt / description
      Added value: +"Optional original prompt for each provider, maximum 30,000 characters; provide this or name."
    • addedInput schema / properties / providers / description
      Added value: +"Two to nine provider IDs; defaults to ChatGPT and Claude and duplicates are removed."
    • changedInput schema / properties / providers / items / enum
      Previous value: -[
      -  "chatgpt",
      -  "claude",
      -  "gemini",
      -  "perplexity",
      -  "grok",
      -  "copilot",
      -  "mistral"
      -]New value: +[
      +  "chatgpt",
      +  "claude",
      +  "gemini",
      +  "perplexity",
      +  "grok",
      +  "copilot",
      +  "mistral",
      +  "huggingchat",
      +  "duckduckgo"
      +]
    • changedInput schema / properties / providers / maxItems
      Previous value: -7New value: +9
    • addedInput schema / properties / uiLanguage / description
      Added value: +"Interface language name or code, e.g. EN; independent of source and response languages."
    • addedInput schema / properties / values / description
      Added value: +"Placeholder values used when preparing a named template."
    • addedOutput schema / properties / entitlement / properties / dailyFreeRemaining
      Added value: +{
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / entitlement / properties / lastFreeSendAt
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  2. Changed3 schema fields changed
    • addedOutput schema / properties / entitlement / properties / compareLocked
      Added value: +{
      +  "type": "boolean"
      +}
    • addedOutput schema / properties / entitlement / properties / dailyFreeLimit
      Added value: +{
      +  "type": [
      +    "number",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / entitlement / properties / nextResetAt
      Added value: +{
      +  "type": [
      +    "string",
      +    "null"
      +  ]
      +}
  3. First observed

TDQS

Score is being calculated.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.