​
Welcome to the AI21 Developer Platform!

AI21 provides AI systems and foundation models designed to address high-value, data-intensive workflows and real-world challenges. Our solutions are reliable, efficient, and transparent—especially effective for long-context tasks critical to enterprises, such as:

  • Grounded question answering across lengthy documents
  • Chat completion
  • Financial data analysis
  • Retrieval-Augmented Generation (RAG) workflows

​
AI21 Maestro (coming soon)

AI21 Maestro is an AI system for rapidly creating and deploying RAG agents that automate high-value, data-intensive business tasks. At the core of AI21 Maestro is a new type of agent intelligence, optimized to find the smartest way to search, reason, validate, and adapt in real time to accomplish the task, while staying within your cost and latency requirements.

At its core, AI21 Maestro is a dynamic planning system that determines the optimal sequence of actions to solve a given task during inference time. The system excels at self-validation and correction, continuously evaluating outputs against your specified requirements.

Learn more about AI21 Maestro.

​
Jamba Family of Open Models

Jamba models deliver up to 2.5× faster inference than leading models of similar size. They are available for private deployment, including VPC and on-premises, and are optimized for tasks like:

  • Long-context RAG
  • Grounded QA
  • Data classification

Jamba offers tailored performance for productivity tools, customer service, and internal knowledge agents. Learn more about the Jamba Models.

​
Conversational RAG

A solution that enables you to build conversational experiences that interact with your organizational data. Learn more about Conversational RAG.

​
Flexible Deployments for the Enterprise

You can choose the option that meets your needs here.

​
Accessing our Models and Solutions

You can access our tools and models through several mechanisms:

  • Python SDK: We provide a Python SDK to simplify access to all our models and tools from your Python code. The SDK provides code completion tips, documentation, support for synchronous and asynchronous calls, and much more.
  • REST API: Under the hood, our SDK, playground, and cloud platform implementations access our models through our public REST API.
  • Cloud platforms: We provide model access from all the leading cloud providers. See the full list here.
  • Other third-party services: Our models are also available on other third-party systems such as LangChain and LlamaIndex. Check your toolchain to see if AI21 is available.

​
Next steps

​
Welcome to the AI21 Developer Platform!

AI21 provides AI systems and foundation models designed to address high-value, data-intensive workflows and real-world challenges. Our solutions are reliable, efficient, and transparent—especially effective for long-context tasks critical to enterprises, such as:

  • Grounded question answering across lengthy documents
  • Chat completion
  • Financial data analysis
  • Retrieval-Augmented Generation (RAG) workflows

​
AI21 Maestro (coming soon)

AI21 Maestro is an AI system for rapidly creating and deploying RAG agents that automate high-value, data-intensive business tasks. At the core of AI21 Maestro is a new type of agent intelligence, optimized to find the smartest way to search, reason, validate, and adapt in real time to accomplish the task, while staying within your cost and latency requirements.

At its core, AI21 Maestro is a dynamic planning system that determines the optimal sequence of actions to solve a given task during inference time. The system excels at self-validation and correction, continuously evaluating outputs against your specified requirements.

Learn more about AI21 Maestro.

​
Jamba Family of Open Models

Jamba models deliver up to 2.5× faster inference than leading models of similar size. They are available for private deployment, including VPC and on-premises, and are optimized for tasks like:

  • Long-context RAG
  • Grounded QA
  • Data classification

Jamba offers tailored performance for productivity tools, customer service, and internal knowledge agents. Learn more about the Jamba Models.

​
Conversational RAG

A solution that enables you to build conversational experiences that interact with your organizational data. Learn more about Conversational RAG.

​
Flexible Deployments for the Enterprise

You can choose the option that meets your needs here.

​
Accessing our Models and Solutions

You can access our tools and models through several mechanisms:

  • Python SDK: We provide a Python SDK to simplify access to all our models and tools from your Python code. The SDK provides code completion tips, documentation, support for synchronous and asynchronous calls, and much more.
  • REST API: Under the hood, our SDK, playground, and cloud platform implementations access our models through our public REST API.
  • Cloud platforms: We provide model access from all the leading cloud providers. See the full list here.
  • Other third-party services: Our models are also available on other third-party systems such as LangChain and LlamaIndex. Check your toolchain to see if AI21 is available.

​
Next steps