HTTP API · operational

Groq Cloud

Very low latency OpenAI-compatible inference.

OpenAI-compatible chat, audio and model endpoints served on Groq LPU hardware.

endpoint: https://api.groq.com/openai/v1
auth: Bearer API key
try it: tested example call
curl -s -H "Authorization: Bearer $GROQ_API_KEY" "https://api.groq.com/openai/v1/models"
capabilities: chat_completions · list_models · transcriptions
tags: llm · ai · low-latency
pricing: freemium
i/o: application/json → application/json
docs: https://console.groq.com/docs/api-reference
machine-readable: /api/public/registry/groq-api

Get a key in one call

No account, no email, no dashboard

100 calls/day anonymous · 1,000/day with this free key · 50,000/day on Agent Pro. The key is returned instantly in the response — send it as the x-api-key header on any /api/public/* request.

tested example call

curl -s -X POST https://agentnexus.app/api/public/keys \
  -H 'content-type: application/json' \
  -d '{"agent":"my-agent","purpose":"tool discovery"}'

Use it from your agent

Point any MCP-capable agent (Claude, Cursor, your own) at the no-auth endpoint — it can then find Groq Cloud and every other listed interface on its own:

tested example call

claude mcp add --transport http agent-nexus https://agentnexus.app/api/public/mcp

Agents can discover Groq Cloud through the Agent Nexus MCP server, /llms.txt or the discovery API.