Our industry-leading small language models (SLMs) have significantly fewer parameters than LLMs which means they are fast and cost-effective. Our selection of models are purpose-built for specific tasks and data.
Try out our SLMs in Model Engine and sign up here for early access to our new intelligent model routing and inference platform, Arcee Conductor.
Explore Model Engine
Our most powerful model, designed for handling complex and varied tasks across domains with exceptional capability.
A versatile, well-rounded model, ideal for a wide range of everyday tasks with balanced performance.
Tailored for quick, efficient responses to simpler tasks, optimized for speed and resource efficiency.
Engineered for advanced integrations, capable of handling complex function calls and tool-based interactions.
Tailored for quick. efficient responses to diverse tasks, optimized for speed and resource efficiency.
Dependable for routine coding needs, offering solid assistance in code-based workflows.
Arcee Orchestra delivers agentic AI that you can customize to do exactly what you need, without compromising on speed or data security.
The Arcee Model Engine is a hosted inference service currently in public beta and available at models.arcee.ai. It provides access to Arcee AI’s suite of specialized Small Language Models (SLMs), designed to work with Arcee Orchestra for intelligent agentic orchestration.
These models are optimized for a wide range of tasks, from general-purpose activities to specialized use cases such as vision-language processing and advanced reasoning. You can easily integrate these models into your workflows or use them as standalone systems for maximum flexibility.
The available models include Virtuoso (Large, Medium, Small) for general-purpose tasks, Caller Large for executing complex workflows and system interactions, and Coder (Large, Small) for programming and development tasks across various languages. Additional specialized models are in the pipeline and will be automatically available to all subscribers.
To get started, you can either chat directly through Arcee Model Engine–where you'll find a built-in chat interface for each model after signing up–or integrate our models into your own applications. Integration is straightforward since all Arcee AI models are compatible with OpenAI's inference format, requiring only a few environment variables to set up. For more information, please check out our announcement blog here.
When you sign up for Model Engine, you'll be charged a $20 monthly subscription fee that goes into your wallet. This allows you to start chatting with Arcee Model Engine models. Upon your first use of a model, 2 million tokens (1M input + 1M output) are deducted from your wallet as an initial charge. Additional charges apply each time you exceed 1M tokens. API calls pause if your wallet hits zero until you add more funds.
Contact us for a custom demo.
Subscribe to our newsletter
.svg)
