Groq
LPU inference for open models — very fast tokens, simple OpenAI-compatible API.
8.7AIAI Models
Usage-based
Train, fine-tune and serve open models on a dedicated inference cloud.
Pricing
Pay as you go
Usage-based
LPU inference for open models — very fast tokens, simple OpenAI-compatible API.
8.7AIAI Models
Usage-based
Run community models from a URL — image, video, voice and custom containers.
8.5AIAI Models
Usage-based
One API to route across hundreds of models with spend controls and fallbacks.
8.8AIAI Models
Usage-based
The public hub for models, datasets, Spaces and inference APIs.
9.1AIAI Models
$9/mo
Open-source LLM observability — traces, evals, prompt versions and costs.
8.6AIAI Models
$29/mo
High-throughput, memory-efficient inference and serving engine for LLMs.
9.1AIAI Models
One API for 100+ LLM providers. Python SDK plus a high-performance gateway.
8.6AIAI Models