Directory

Low-latency hosted inference API for open-weight models on Groq's LPU hardware, OpenAI-compatible, with speech-to-text, text-to-speech, tool use and batch tiers

French model provider offering open-weight and proprietary models through the Studio API, OCR and speech models, the Vibe agent for productivity and coding, and self-deployment options

Cloud platform for open-source models: serverless and dedicated inference, fine-tuning, GPU clusters, batch jobs and code sandboxes behind an OpenAI-compatible API