Skip to main content
Glama

Poly-Glot AI Workspace

by io.github.hmoses
OverviewDiscussionsAdmin

Run a custom model

run_custom_model

Run a user-supplied prompt against a developer-provided OpenAI-compatible or custom REST HTTPS model endpoint. Use validate_custom_model to test URL and adapter settings before sending. Returns model-generated text, model name, optional usage, and account state. Requires active trial or Pro and transmits prompt content to the selected provider. Credentials are transient, not persisted; localhost/private networks are not supported.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoModel identifier at the custom provider, when needed.
apiKeyNoTransient authentication key sent to the chosen provider; never log or embed in prompts.
promptYesRequired nonempty prompt to send externally, maximum 30,000 characters.
systemNoOptional system instructions supported by the endpoint.
baseUrlNoRequired public HTTPS base URL for openai-compatible mode.
authModeNoCustom REST authentication mode, default bearer.bearer
endpointNoRequired public HTTPS inference URL for custom-rest mode.
maxTokensNoOptional maximum output token count, subject to model limits.
uiLanguageNoInterface language name or code, e.g. EN; independent of source and response languages.EN
adapterModeYesAdapter for the target endpoint: openai-compatible or custom-rest.
promptFieldNoCustom REST request JSON key for prompt content.prompt
systemFieldNoCustom REST request JSON key for system instructions.system
temperatureNoOptional response sampling randomness between 0 and 2.
apiKeyHeaderNoCustom REST API-key authentication header name.x-api-key
extraHeadersNoExtra HTTP headers required by the provider, if any.
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
responseTextPathNoOptional JSON response field/path containing generated text.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed18 schema fields changed
    • addedInput schema / properties / adapterMode / description
      Added value: +"Adapter for the target endpoint: openai-compatible or custom-rest."
    • addedInput schema / properties / apiKey / description
      Added value: +"Transient authentication key sent to the chosen provider; never log or embed in prompts."
    • addedInput schema / properties / apiKeyHeader / description
      Added value: +"Custom REST API-key authentication header name."
    • addedInput schema / properties / authMode / description
      Added value: +"Custom REST authentication mode, default bearer."
    • addedInput schema / properties / baseUrl / description
      Added value: +"Required public HTTPS base URL for openai-compatible mode."
    • addedInput schema / properties / endpoint / description
      Added value: +"Required public HTTPS inference URL for custom-rest mode."
    • addedInput schema / properties / extraHeaders / description
      Added value: +"Extra HTTP headers required by the provider, if any."
    • addedInput schema / properties / inputLanguage / description
      Added value: +"Language name or code of input text, e.g. es; defaults to EN."
    • addedInput schema / properties / maxTokens / description
      Added value: +"Optional maximum output token count, subject to model limits."
    • addedInput schema / properties / model / description
      Added value: +"Model identifier at the custom provider, when needed."
    • 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: +"Required nonempty prompt to send externally, maximum 30,000 characters."
    • addedInput schema / properties / promptField / description
      Added value: +"Custom REST request JSON key for prompt content."
    • addedInput schema / properties / responseTextPath / description
      Added value: +"Optional JSON response field/path containing generated text."
    • addedInput schema / properties / system / description
      Added value: +"Optional system instructions supported by the endpoint."
    • addedInput schema / properties / systemField / description
      Added value: +"Custom REST request JSON key for system instructions."
    • addedInput schema / properties / temperature / description
      Added value: +"Optional response sampling randomness between 0 and 2."
    • addedInput schema / properties / uiLanguage / description
      Added value: +"Interface language name or code, e.g. EN; independent of source and response languages."
  2. First observed

TDQS

Score is being calculated.

All Poly-Glot AI Workspace toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources