overview
Overview
DeepInfra provides developer-friendly APIs for AI inference, offering access to a range of open-source models. It supports tasks such as text generation, embeddings, speech recognition, and image generation. The platform aims to provide cost-efficient serverless inference for open-source frontier models.
DeepInfra offers a unified API to run hundreds of open-source AI models. It includes an OpenAI-compatible API and a free tier. The service focuses on providing API access to a catalog of open-source models across various categories.
