Tycho 1.0
Radium's model for high-volume work: classifying, extracting, summarizing and routing text at the lowest price per token.
Tycho is the model Radium puts on high-volume text: sorting requests into labels, pulling fields out of documents, summarizing calls and tickets, and deciding where each request goes next.
Radium selects open-weight models, tunes them and serves them behind one API, where a router and a reinforcement learning engine choose the model for each request.
High-volume text goes to Tycho.
Starts answering 40% sooner than Claude Haiku.
Tycho and Claude Haiku ran the same 80 structured tasks with fixed answers, then 40 tasks at four concurrent requests for speed. Tycho starts answering sooner and finishes sooner at the median, while Haiku scored higher on accuracy, writes slightly faster and finishes its slowest requests a little sooner. GPT-5.4 mini results on the same tasks are pending.
GPT-5.4 mini pending
GPT-5.4 mini pending
GPT-5.4 mini pending
GPT-5.4 mini pending
The infrastructure, measured by others.
One model ID, and the whole stack under it.
- PlatformThe Radium API, its router and RL engine, and a pool of tuned open-weight models.OpenAI- and Anthropic-compatible, so your SDK and prompts stay where they are.The router and RL engine choose the model for each request.Radium's model curation team selects and tunes the models.
- InfraDistributed computing across data center sites, on modified server firmware and Radium's own switch software.
- HardwareRacks of GPU servers in data centers across several sites.
Switching takes three values.
Point the SDK you already use at Radium with a new base URL, a Radium key and the model name. Switching back is the same change in reverse.
- Endpoints
- OpenAI- and Anthropic-compatible
- Context window
- 128,000 tokens
- Input
- Text only
- Structured output
- JSON mode and JSON schema
- Tool calling
- Parallel calls with strict schemas
- Streaming
- OpenAI and Anthropic formats, with tool call deltas
- Rate limits
- 1,000 requests a minute, burst of 33, no tokens-per-minute limit
- Coming later
- Responses API, embeddings and batch
Start on Clarke and send the hard requests to Hal.
Hal
Reasoning across sources, code and long agent loops.
Clarke
RAG, copilots, tool calling and most production traffic.
Tycho
Classification, extraction and routing at volume, on text.
Questions about Tycho.
How is Tycho built?
Radium builds Tycho from open-weight models that its model curation team selects and tunes, and serves them behind one API with a router and a reinforcement learning engine that choose the model for each request.
How do I move a workload to Tycho?
Set the base URL to https://api.radium.cloud/v1, use a Radium API key and set the model to tycho-1.0. Your SDK, prompts and tool schemas stay the same.
What does Tycho cost?
$0.10 per million input tokens and $1.50 per million output tokens, and cached input is $0.02. New accounts get $25 of credit with no card needed.
Does Radium train on my data?
Your prompts and outputs are never used to train a model.
How was Tycho benchmarked?
On Radium's own suite of 80 structured tasks with fixed answers and 40 tasks for speed, against Claude Haiku, with GPT-5.4 mini results on the same suite pending. The full method, confidence intervals and limits are on the benchmark results page.
Does Tycho read images?
Move your highest-volume calls to Tycho.
One line of code to switch.
A different class of performance.
Every new account gets $25 in credit. No card required.
