Free APILLMAPI keyOfficial

Groq API

Fastest open-model inference around, free with no credit card

Groq runs open-weight LLMs (Llama 3.x, gpt-oss, Qwen) on custom LPU hardware at very high tokens-per-second. The developer console issues a free API key with no card required, and the API is OpenAI-compatible so existing SDK code works by changing the base URL.

View docs Get an API key

Free tier

Free Developer tier, no credit card. Daily and per-minute caps per model; upgrade for higher limits plus usage discounts.

Rate limits

Free tier (verified June 2026): llama-3.1-8b-instant = 30 RPM, 14,400 req/day, 6,000 TPM, 500,000 TPD; llama-3.3-70b-versatile = 30 RPM, 1,000 req/day, 12,000 TPM, 100,000 TPD. Limits are per-organization and per-model; larger models have lower token caps.

Auth

API key

Base URL

https://api.groq.com/openai/v1

What you'd build with it

Low-latency agent loops and tool-calling where round-trip speed matters
Real-time chat or voice automations needing sub-second token streaming
Whisper transcription for audio-ingest pipelines on the free tier
High-throughput batch classification within the daily token budget

Key endpoints

POST/chat/completionsOpenAI-compatible chat completion (streaming supported)
POST/audio/transcriptionsWhisper-based speech-to-text transcription
GET/modelsList available models and metadata

Members

Members get the runnable recipe

Create a free account Sign in