Stackmark › APIs

Groq API

Low-latency inference for open models on Groq LPUs.

• Type: API
• Imported from the Stackmark API directory
• Source: https://console.groq.com/docs
• Tags: Groq, inference, llm, fast
• Updated: 2026-10-01

More APIs

• Claude API — Claude models for chat, coding, vision, tool use, and agents.
• AssemblyAI API — Speech-to-text with speaker labels and audio intelligence.
• Azure OpenAI — OpenAI models hosted on Microsoft Azure with enterprise controls.
• Amazon Bedrock — Fully managed access to foundation models from multiple providers on AWS.
• Cerebras Inference — High-speed inference for open models on Cerebras hardware.
• Cohere API — Command models, embeddings, and rerank for enterprise search and RAG.
• Deepgram API — Speech-to-text and voice agent APIs.
• DeepSeek API — DeepSeek chat and reasoning models with an OpenAI-compatible interface.