Try our new intelligent model routing solution, Arcee Conductor. Sign up today and get a $20 credit (~400M free tokens).
A new standard for intelligent model routing.
Conductor intelligently routes your prompt to the best model, to efficiently deliver precise results, for any task.
The right model for each prompt, every time.
With new AI models released daily, it's hard to keep up with which model is best for your business. Our pioneering work in small language models (SLMs) gives us unique insights into which model is the right one for your tasks or queries.
That's why we built Arcee Conductor, a model-agnostic platform that gives you access to a complete suite of top-performing SLMs, as well as other industry-leading LLMs.
Arcee Conductor intelligently routes your query to the optimal model based on factors like industry/specialty, complexity, efficiency, and cost–all in an easy-to-use interface that requires no technical expertise.
Automatically routes your prompt or query based on complexity, type of task, industry or domain, language, and whether it involves tool / function calling.
Cost-per-query reduced by 85%+, thanks to simpler prompts getting routed to the smaller models. You're no longer paying premium prices for routine queries, and you get live visibility into query costs.
The intelligent router evaluates your prompt or query, then routes it to an Arcee SLM (like Arcee-Blitz, Virtuoso-Medium, or Virtuoso-Large), or to a leading LLM (like Claude-Sonnet-3.7, GPT-4o, or DeepSeek-R1).
Supports chain-of-thought reasoning for enhanced analytical capabilities, and automatic compute scaling for task-specific optimization.
The only routing platform that utilizes open-source and closed-source models, including our proprietary Arcee SLMs and our distilled DeepSeek models.
User-defined preferences for routing parameters and model prioritization, with preset profiles for different tasks.
Arcee Al creates powerful, highly efficient small language models (SLMs). They contain significantly fewer parameters than large language models, which makes them cost-effective and fast. But because they're purpose-built for specific tasks, data, and requirements, they perform remarkably well.
Explore Arcee Conductor
Our most affordable SLM, this 24B is designed to be fast and efficient, with exceptional world knowledge for its size. A practical workhorse model that can tackle a range of tasks without the overhead of larger architectures.
A versatile and powerful 32B SLM, capable of handling varied tasks with precision and adaptability across multiple domains. Ideal for dynamic use cases that require significant computational power.
Our most powerful and versatile general-purpose SLM, this 72B is designed to excel at handling complex tasks across domains. Its scalability and depth make it ideal for enterprises seeking comprehensive AI solutions.
Our most advanced reasoning model, this 32B SLM tackles the most complex problem-solving scenarios with precision and depth. It excels at handling multifactorial decision-making, abstract reasoning, and scenario modeling.
A 32B SLM optimized for managing complex tool-based interactions and API function calls. Its strength lies in precise execution, intelligent orchestration, and effective communication between systems – making it ideal for automation pipelines.
With "Auto" mode, Conductor chooses the best model to use, within a defined list of available models. Model selection is based on task and domain complexity.
For complex prompts, select "Auto Reasoning" and Conductor will choose the best reasoning model to return your carefully curated output.
To initiate a function call, select "Auto Tools", which uses Caller-Large, a 32B model specially trained to use external tools such as APIs and functions.
To unlock additional options – like volume discounts, custom model configuration, and dedicated SLAs – contact Sales to learn about our Enterprise Tier.
Currently, companies face significant challenges:
While selecting the best model for your task improves response quality, that isn't enough – on its own – to solve these challenges completely. This is why intelligent model routing is essential. It automatically selects the optimal model for each prompt, helping you to reclaim your profit margins without sacrificing quality.
Arcee Conductor is an intelligent model routing platform that directs each input to its ideal AI model based on complexity, domain, cost, and other requirements. By dynamically routing between large language models (LLMs) and small language models (SLMs), Conductor maximizes cost efficiency without compromising performance. You get the right model for each prompt, every time.
In Arcee Conductor, your prompt is automatically routed to the most suitable model through an advanced routing mechanism.
Available models include:
Arcee AI SLMs: Virtuoso-Large, Virtuoso-Medium, Arcee-Blitz, Maestro-32b and Caller-Large
LLMs: Claude-Sonnet-3.7, GPT-4.1, Claude-Sonnet-3.7-Thinking, o3-mini, DeepSeek-R1
A mode on Arcee Conductor is a selection of specialized AI models grouped by functionality. Each mode serves a different purpose, giving you the flexibility to use the most suitable approach for your task, whether for general inquiries, complex reasoning, or function-calling.
Each mode serves a specific purpose to deliver the most effective results for your particular needs.
You can sign up here to begin using Arcee Conductor today. First-time users receive $20 in credits (equivalent to approximately 400 million tokens) towards your Conductor usage.
Arcee Conductor is based on a usage-based pricing model. When you sign up for Conductor for the first time, you'll receive $20 in credits automatically. This allows you to immediately start using the platform.
After you've used your $20 in credits, charges will be applied to your payment method based on your usage. The specific rates vary depending on specific rates per token of models.
Arcee-Blitz
(General Purpose)
$0.45
$0.75
Virtuoso-Medium
(General Purpose)
$0.50
$0.80
Virtuoso-Large
(General Purpose)
$0.75
$1.20
Maestro
(Reasoning)
$0.90
$3.30
Caller-Large
(Function Calling)
$0.55
$0.85
Claude 3.7 Sonnet
$3.00
$15.00
GPT-4.1
$2.00
$8.00
DeepSeek-R1
$3.00
$7.00
OpenAI o3-mini
$1.10
$4.40
First-time users of Arcee Conductor can get started with a one-time $20 credit. Optimize output across models, reduce usage costs, and maximize performance with intelligent routing.
Subscribe to our newsletter
.svg)
