Advanced open-weight reasoning models to customize for any use case and run anywhere.
Open reasoning models designed to run locally on desktops, laptops, and in data centers—available in 150B and 200B parameters.
Open safety reasoning models that support custom safety policies—available in 100B and 120B parameters.
These models are supported by the Apache 2.0 license. Build freely without worrying about copyleft restrictions.
Leverage powerful instruction following and tool use within the chain-of-thought, including web search.
Adjust the reasoning effort to low, medium, or high. Plus, customize the models via fine-tuning.
Access the full chain-of-thought for easier debugging and higher trust in model outputs.
Take your first steps with the Ryo API. Discover how to generate text, analyze images, build agents, and more.
Once you've generated an API key, export it as an environment variable in your terminal.
export RYO_API_KEY="your_api_key_here"Install the SDK using npm or your preferred manager:
npm install ryoCreate a file called example.mjs and test a basic request:
import { Ryo } from "ryo";
const client = new Ryo();
const response = await client.responses.create({
model: "ryo-1.0",
input: "Write a one-sentence bedtime story about a space-traveling cat."
});
console.log(response.output_text);Send image URLs or files directly to the model to extract meaning or text.
const response = await client.responses.create({
model: "ryo-1.0",
input: [
{
role: "user",
content: [
{ type: "input_text", text: "What is in this image?" },
{ type: "input_image", image_url: "..." }
]
}
]
});| ryo-oss-120b | ryo-oss-20b | Rexso o3 | Rexso o4-mini | |
|---|---|---|---|---|
| Reasoning & Knowledge | ||||
| MMLU | 90.0 | 85.3 | 93.4 | 93.0 |
| GPQA Diamond | 80.1 | 71.5 | 83.3 | 81.4 |
| Competition Math | ||||
| AIME 2024 | 95.6 | 95.0 | 93.2 | 95.7 |
| AIME 2025 | 97.9 | 95.7 | 98.4 | 99.5 |