Groq · GraphQL Specification

Groq GraphQL API

Groq provides ultra-fast LLM inference via their Language Processing Unit (LPU) hardware. The API is OpenAI-compatible and covers chat completions, audio transcription, and batch processing with models including Llama, Mixtral, and Gemma.

Documentation Endpoint View on GitHub AILLMInferenceLPULow LatencyGraphQL

Overview

Groq GraphQL API is a GraphQL API specification published by Groq on the APIs.io network.

Groq provides ultra-fast LLM inference via their Language Processing Unit (LPU) hardware. The API is OpenAI-compatible and covers chat completions, audio transcription, and batch processing with models including Llama, Mixtral, and Gemma.

The GraphQL endpoint is available at No. documentation is published at https://console.groq.com/docs.

The specification includes 2 reference links.

Tagged areas include AI, LLM, Inference, LPU, and Low Latency.

Endpoint

No

References

Related API Specs

Groq Chat Completions API (OpenAPI) Groq Reasoning API (OpenAPI) Groq Vision API (OpenAPI) Groq Speech-to-Text API (OpenAPI) Groq Text-to-Speech API (OpenAPI) Groq Content Moderation API (OpenAPI) Groq Batch API (OpenAPI) Groq Flex Processing API (OpenAPI) Groq Files API (OpenAPI) Groq Models API (OpenAPI) Groq Tools API (OpenAPI) Groq LoRA Inference API (OpenAPI) Groq Prompt Caching (OpenAPI)
Back to Groq · All GraphQL Specs · GitHub