Skip to main content

Models overview

Radium serves three tuned model tiers through OpenAI- and Anthropic-compatible endpoints. The tiers map directly to the frontier model families you already know.

Comparison

Hal 1.0 is for reasoning: agents that decompose problems, generate structured plans, or write long programs. Use it when the task pays for quality. Clarke 1.0 is the default for most workloads: RAG, copilots, tool calls and any system where latency and cost matter. Tycho 1.0 is for high-volume automation: classification, entity extraction, summarization, routing. Send a request to Tycho when you would have used a classifier model or a rules engine.

Frontier model mapping

Use this table to choose the Radium tier that replaces the frontier model you are switching from.

Capabilities matrix