Built by Metorial, the integration platform for agentic AI.
Retrieve API usage history with detailed insights including token counts, response times, costs, source IPs, and model/provider information for each request. Useful for auditing, billing analysis, and optimization.
Browse and filter the catalog of available AI models across all providers. Filter by type (language, vision, image, voice, embedding), provider, capabilities, and more. Returns pricing, latency, context window, and availability information for each model.
Send conversational prompts to hundreds of AI language models through a unified endpoint. Supports advanced features including web search grounding, RAG augmentation, persistent memory, hallucination reduction via integrity checking, and function calling/tools.
Perform web searches and scrape web page content. Use search to find relevant web results for a query, and scrape to extract clean text content from specific URLs. These can be used independently or together.
Convert text into natural-sounding speech using TTS models from OpenAI and ElevenLabs. Access a wide range of voices and customize voice parameters.
Create images using AI models from various providers such as DALL-E 3, Stable Diffusion, Flux, and more. Supports generating original images from text prompts and editing existing images.
Generate vector embeddings from text using embedding models from multiple providers. Useful for semantic search, text clustering, similarity comparison, and retrieval-augmented generation workflows.
Upload documents to RAG collections, list existing collections, and delete collections. Documents are automatically vectorized and can be referenced in chat completions using the "ragTune" parameter to augment model responses with your own data.