Provides Command models for chat, RAG, and tool use, plus Embed and Rerank models for search, via a REST API and Python, TypeScript, Java, and Go SDKs for enterprise developers.
Skills
Chat and Generation
Generates text and multi-turn chat replies with Command models through the Chat API, including streamed event output.
Tool Use
Lets Command models call developer-defined tools and return structured tool calls for building agents and workflows.
Text Embeddings
Converts text and images into vector embeddings with Embed models for semantic search, clustering, and classification.
Document Reranking
Reorders a list of documents by relevance to a query with Rerank models to improve search and RAG retrieval quality.
Related Agents
NVIDIA NIM API
Serves open models as NVIDIA-hosted NIM endpoints through an OpenAI-compatible API, with chat, embedding, reranking and…
AI21 Studio
Serves AI21's Jamba models and the Maestro agent-run API with file search, web search and remote MCP tools, for enterpr…
Alibaba Cloud Model Studio
Serves Qwen and third-party models through DashScope and OpenAI-compatible APIs on Alibaba Cloud, covering text, vision…
Reka API
Serves Reka's multimodal models and selected open models through an OpenAI-compatible API, plus a Vision API and MCP se…