Build leading AI products
on Rexso's platform.

Open models by Rexso Intelligence

Advanced open-weight reasoning models designed for deep research. Customize for any use case and deploy across any architecture.

Hugging Face GitHub Source Model Specs
SALESFORCE WIX Intercom invideo MERCARI

Powered by our frontier models

Our industry-leading models are designed for real-world utility, delivering advanced intelligence and multimodal capabilities.

Rex-5.4

Input: $2.50 per 1M tokens

Output: $10.00 per 1M tokens

128K context length

Knowledge cutoff: Aug 2025

Rex-5.4 mini

Input: $0.15 per 1M tokens

Output: $0.60 per 1M tokens

128K context length

Knowledge cutoff: Aug 2025

Rex-5.4 nano

Input: $0.10 per 1M tokens

Output: $0.30 per 1M tokens

128K context length

Knowledge cutoff: Aug 2025

ryo-R7

Open reasoning models designed to run locally on desktops, laptops, and in data centers—available in 150B and 200B parameters.

ryo-R1-safeguard

Open safety reasoning models that support custom safety policies—available in 100B and 120B parameters.

Permissive license

These models are supported by the Apache 2.0 license. Build freely without worrying about copyleft restrictions.

Designed for agentic tasks

Leverage powerful instruction following and tool use within the chain-of-thought, including web search.

Deeply customizable

Adjust the reasoning effort to low, medium, or high. Plus, customize the models via fine-tuning.

Full chain-of-thought

Access the full chain-of-thought for easier debugging and higher trust in model outputs.

Start working with Rex-5.4

Prompting guidance

Learn how to prompt Rex-5.4 for highest performance.

View prompting guidance

Front-end coding examples

Explore front-end applications built with Rex-5.4.

View front-end examples

Migration support

Learn how to migrate from other models to Rex-5.4.

View migration guide

The all-in-one platform for agents

Build, deploy, and optimize production-ready agents faster with pre-built components or from scratch.

Build

Build agents on a visual-first canvas with Agent Builder or in a code-first environment with the Agents SDK.

Deploy

Create customizable, front-end agentic experiences with ChatKit.

Optimize

Run evals to measure agentic performance, and improve results with prompt optimization and fine-tuning.

Enterprise-grade features
for operating at scale

Security and data privacy

  • No training on your data
  • Zero data retention policy by request
  • HIPAA compliance available
  • SOC 2 Type 2 compliance

Administrative controls

  • Role-based access controls
  • Set billing and usage alerts
  • Granular usage and cost visibility

Access to Rexso expertise

  • Dedicated account teams
  • Priority deployment guidance
  • Solution architects collaboration

Developer quickstart

Take your first steps with the Ryo API. Discover how to generate text, analyze images, build agents, and more.

Create and export an API key

Once you've generated an API key, export it as an environment variable in your terminal.

export an environment variable on macOS or Linux systems
export RYO_API_KEY="your_api_key_here"

Install the Ryo SDK and Run an API Call

Install the SDK using npm or your preferred manager:

install the Ryo SDK with npm
npm install ryo

Create a file called example.mjs and test a basic request:

Test a basic API request
javascript
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);

Analyze images and files

Send image URLs or files directly to the model to extract meaning or text.

Analyze the content of an image
javascript
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: "..." }
      ]
    }
  ]
});

Model performance

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

Our partners

AWS CLOUDFLARE DATABRICKS AZURE TOGETHER.AI
Research
  • Research Index
  • Research Overview
  • Ryo for Science
Products
  • ChatRyo
  • Ryo for Business
  • API Platform
Developers
  • Documentation
  • API Reference
  • GitHub
Company
  • About Us
  • Careers
  • Safety Approach