Groq
groq.com
Provides fast, low-cost AI inference via an OpenAI-compatible API for running LLMs, speech-to-text, and text-to-speech models.
The Groq API uses api key authentication; has usage based pricing; offers a free tier (Free API key available; "Get started for free and upgrade as your needs grow"). Verified 2026-07-12 with per-field source links.
Pricing
Per-token pricing, e.g. Llama 3.1 8B Instant $0.05/M input, $0.08/M output; Llama 3.3 70B $0.59/M input, $0.79/M output; GPT OSS 120B $0.15/$0.60 per M; ASR Whisper V3 Large $0.111/hour; Batch API 50% lower cost
groq.com ↗Rate limits
not documented null
no sourceOpenAPI spec
not documented null
no sourceMCP server
not documented null
no source