AI & Machine Learning APIs

Claude models for text, code, vision and tool use, with prompt caching and batch processing.

GPT models for text, images, audio and embeddings.

Gemini multimodal models through Google AI Studio, with a free tier for experimentation.

Open-weight and commercial models from Mistral for chat, code and embeddings.

Command models, embeddings and reranking aimed at enterprise search and RAG.

Run thousands of open models through one API routed to multiple inference providers.

Run open-source image, video, audio and language models with pay-per-second pricing.

Text-to-speech, voice cloning and speech-to-text in many languages.

Fast speech-to-text and text-to-speech for real-time and batch audio.

Speech-to-text with speaker labels, summaries and audio intelligence features.