Radium Hal 1.0
Designed for complex reasoning, agent
workflows, and software tasks.
Radium models run on optimized infrastructure designed for high throughput, reliable performance, and lower cost per token in production environments.
Maximum Capability
Radium's most powerful model for complex reasoning, multi-step agents, and deep code analysis.
Complex reasoning and analysis
Agentic workflows
Deep code generation
Highest-capability model for complex reasoning, coding, and enterprise workloads.
Radium's most powerful model for tasks that demand deeper reasoning, multi-step planning, and precise execution across complex enterprise workflows.
Hal 1.0
Capability
Designed for complex reasoning, agent workflows, and software tasks.
Significant savings with prompt caching (up to 90%) on repeated prompts.
Hal is best suited for:
- Complex reasoning and analysis
- Advanced coding and software engineering
- Multi-step AI agents
- Enterprise document and research workflows
- High-stakes production workloads
Comparable to Opus 4.7
and GPT-5.5
Where delivery
efficiency becomes
pricing power.
Switch in one line of code and run your existing AI workloads more efficiently without rebuilding your application.
Improve unit economics
at production scale
Radium is used by teams shipping
AI into real-world systems
Square’s R&D team used Radium to prototype early (pre-Gen AI) text-to-video and text-to-speech applications.
EQTY Lab used Radium to train a state-of-the-art climate model that was presented at COP28, the United Nations climate change conference.
Realbotix uses Radium to power low-latency, real-time AI interactions on its humanoid robotics platform. Radium enables responsive inference at the speed required for live human–AI interaction.
A leader in generative AI for law, Alexi used Radium to train domain-specific retrieval models. Alexi’s advanced AI platform generates legal memos, arguments, and answers to general litigation queries.
One line of code to switch.
A different class of performance.
Swap OpenAI for Radium in your API call. That's it.