Skip to main content
Exerati Platform

Ship smarter. Scale faster.

OpenAI-compatible API, chat, CLI access, and vision model testing for teams building on Exerati.

terminal

$ curl https://api.exerati.com/v1/chat/completions \

-H "Authorization: Bearer sk-..." \

-H "Content-Type: application/json" \

-d '{"model": "exerati-x1.0", "messages": [...]}'

Terminal CLI

AI from your terminal

Install the Exerati CLI and start making AI requests directly from your terminal. Pipe data, chain commands, and integrate into your existing workflows.

Cross-platform: macOS, Windows, Linux
Streaming responses with markdown rendering
Pipe stdin/stdout for automation
OpenVSX IDE extension for Cursor & Antigravity
View installation guide
Terminal — exerati-cli

# Install the CLI (Linux / macOS)

$ curl -fsSL https://exerati.com/install.sh | bash

# Install the CLI (Windows PowerShell)

$ irm https://exerati.com/install.ps1 | iex

# Download desktop app (macOS ARM)

$ curl -fsSL https://exerati.com/releases/exerati-desktop/

Exerati-Code-Desktop-arm64.dmg -o Exerati.dmg

# Download desktop app (Windows)

$ curl -fsSL https://exerati.com/releases/exerati-desktop/

Exerati-Code-Desktop-x64.exe -o Exerati.exe

# Download desktop app (Linux)

$ curl -fsSL https://exerati.com/releases/exerati-desktop/

Exerati-Code-Desktop-x64.AppImage -o Exerati.AppImage

# Authenticate & send a request

$ exerati auth login --key "sk-exr-..."

Authenticated as [email protected]

$ exerati chat "Explain async/await"

Async/await is syntactic sugar over

Promises, making asynchronous code

easier to read and write...

Capabilities

Exerati capabilities, ready for builders.

The core surfaces teams need to test prompts, ship API integrations, and monitor usage from one platform.

Strong

Unified API

OpenAI-compatible requests with Exerati billing and controls

Good

Model Runtime

Low-latency access to the exerati-x1.0 runtime

Developing

Developer Tools

CLI and documentation improving rapidly

Experimental

Vision Capabilities

Image understanding in beta testing

Benchmarks

Model Performance & Pricing

Compare each model by speed, latency, and context window. All models use the same points-based billing formula.

Text / Exerati

Exerati X1.0

Available

Speed

1,231.6 T/S

Latency

13,503.7 ms

Tokens / second 1,231.6 T/S
Latency 13,503.7 ms
Context window 256,000 tokens

Points-Based Pricing

All models use the same points formula. Cached input tokens are 10x cheaper. Subscription plans start at 50 pts/mo free.

Models

AI Models

Explore Exerati model access with clear context windows, capabilities, and points-based pricing.

View All Models

Exerati X1.0

Exerati

Available

General-purpose text model for chat and completion tasks.

Context Window 256,000
Type Text
chat completion

Features

Built for practical AI operations.

A compact control surface for API keys, chat testing, CLI workflows, model selection, and usage visibility.

OpenAI-Compatible API

Drop-in replacement for OpenAI endpoints. Same request format, same response structure. Start building immediately.

AI Chat

Test prompts, compare model behavior, and inspect responses before shipping them into your application.

CLI Access

Connect to AI models directly from your terminal. Pipe data, chain commands, and integrate into your existing workflows.

Vision Models Beta

Test and build with vision-capable models. Upload images, analyze visual content, and create multimodal applications.

Pricing

Simple, transparent pricing

Start free, add wallet balance when you need it, and keep spend visible as usage grows.

Free Default

Free

Free tier with 50 monthly points. Perfect for trying out the platform.

$0.00 / month

or $0.00 / year

  • Requests / Minute: 5
  • Concurrent Requests: 1
  • Points / Month: 50
Get started
Solo

Solo

Solo tier with 2,500 monthly points. Ideal for individual developers.

$6.00 / month

or $60.00 / year

  • Requests / Minute: 10
  • Concurrent Requests: 3
  • Points / Month: 2500
Get started
Prime

Prime

Prime tier with 7,500 monthly points and hourly throttling. Built for power users.

$15.00 / month

or $150.00 / year

  • Requests / Minute: 30
  • Concurrent Requests: 10
  • Points / Month: 7500
  • Points / Hour: 7500
Get started
Apex

Apex

Apex tier with 20,000 monthly points. Maximum throughput for teams.

$30.00 / month

or $300.00 / year

  • Requests / Minute: 300
  • Concurrent Requests: 300
  • Points / Month: 20000
Get started

Ready to start building?

Join developers using Exerati to power their AI applications. Free to start, pay as you grow.