Groq
TempoLlm2 endpointsFrom $0.0050 /req
Ultra-fast LLM inference — Llama 3.3, DeepSeek R1, Gemma 2, Whisper, and PlayAI TTS. Supports tool use, JSON mode, reasoning, and web search.
View documentationWhen should an agent use this?
Use Groq when your agent needs the fastest possible LLM inference — rapid iteration, high-throughput pipelines, real-time applications, or latency-sensitive workflows. Great for agents that chain multiple LLM calls.
Endpoints
Click any endpoint to see parameters, pricing, and a ready-to-use curl example.
Paid (2)
Ultra-fast chat completions with tool use, JSON mode, reasoning.
Path
/services/groq/groq/chatMethodPOST
PriceDynamic (varies per request)
IndieGent Endpoint
api.indiegent.com/services/groqPayment
USDC · Automatic
Payment protocols handled by IndieGent
Network
Tempo