rocketkind
AI

Groq

Groq is a hosted inference API built for speed — OpenAI-compatible chat completions, Whisper speech-to-text and speech translation, all on one key.

Authentication

  • API key

Actions

Generic API request. Call any Groq API endpoint on this connection, for the case where no shipped action covers it yet. The connection supplies the base URL, the authentication and the egress route, so only the path, query and body are yours to fill.

  • Audio TranscriptionGroq speech-to-text (OpenAI-compatible Whisper) via connection context and multipart HTTP POST /audio/transcriptions.
  • Audio TranslationTranslate spoken audio into ENGLISH text (OpenAI-compatible Whisper) via connection context and multipart HTTP POST /audio/translations.
  • Chat CompletionsFast Groq chat completions (OpenAI-compatible) via connection context and HTTP POST /chat/completions.
  • Chat Completions (Streaming)Chat Completions (Streaming) for groq (OpenAI-compatible) via connection context.
  • Get modelRetrieve details for a single Groq model (GET /models/{model}).
  • List batchesList the batch jobs submitted on this Groq organization — asynchronous bulk inference runs, as opposed to the synchronous single call made by groq:chatcompletions.
  • List modelsList available Groq models (GET /models) using connection metadata.apiBaseUrl.

Triggers

  • New batch jobStarts when a new asynchronous batch job is submitted on the connected Groq organization, detected from each batch's createdat timestamp.

Product names, logos and brands are the property of their respective owners and are used here for identification only. Their use does not imply endorsement by, or affiliation with, those owners.