Pay-as-you-go
Free
- • Qwen 3.6 27B
- • Llama 3.3 70B & Whisper Large V3
- • OpenAI-compatible API
← Back
0 Visits (30d) 17 Outbound clicks (30d) 0 Likes This tool has no active coupons right now. Language model inference API with market-leading speed. Custom LPU chips deliver token generation up to 10x faster than GPUs, with a generous free tier for testing and instant integration via an OpenAI-compatible REST API.
AI APIs & Tokens
Groq
Ultra-fast LLM inference (Llama 3.3, DeepSeek-R1) reaching 500+ tokens/second via custom LPU chips.
Pricing plans
From $0.00