The frontier of open and proprietary AI, ready to call in seconds. Browse the full library, compare context windows and pricing, then switch between any model by changing a single string.
Instruction-tuned and reasoning models for agents, RAG, and assistants.
Multimodal models that read images, documents, and screenshots.
Text-to-image and text-to-video generation and editing.
Speech-to-text, text-to-speech, and audio understanding.
High-dimensional embeddings for search, RAG, and clustering.
Cross-encoders that reorder candidates for precision retrieval.
Filter by task, search by name or provider, and copy the model ID straight into your code. Prices shown per 1M tokens unless noted.
Grab an API key and call any of the 200+ models with the OpenAI SDK you already know.