Advanced AI coding access for Software
Engineers.

Sanad 0.1, GLM 5.2, GLM 4.7 Flash, GPT OSS 120B, Sanad CLI, and the Sanad VS Code Extension bring account-based AI coding to Software Engineers. Sign in with Google or Microsoft, add USD balance, and start coding without provider API keys.

Start with Sanad Read about Sanad 0.1

Self-serve access 2 hours/day Pay as you go

Use Sanad where software engineers already work.

Claude Code terminal

Use a Sanad API key with a Claude Code-compatible endpoint for terminal-first coding sessions.

Sanad VS Code Extension

Install from Visual Studio Marketplace, sign in with your Sanad account, and code without provider API keys.

Sanad CLI

Install from npm, run sanad login, and open the interactive coding agent in any repository.

Sanad Business for engineering teams.

Company workspaces, member invitations, model controls, billing readiness, and usage analytics for teams adopting Sanad.

Workspace control

Invite members, assign admins, separate company access from personal access, and keep policy managed in one console.

Usage visibility

Review requests, active users, model mix, client mix, and spend signals without exposing prompt bodies on the public site.

Team guardrails

Set allowed models, daily usage limits, compatibility-token access, and billing readiness for business adoption.

Available Sanad models.

Choose Sanad 0.1 for the default coding workflow, GLM 5.2 for long-context work, GLM 4.7 Flash for fast iterations, or GPT OSS 120B for reasoning-heavy coding tasks.

Sanad 0.1

Default

Sanad's default coding model profile for CLI and VS Code users. It is tuned for practical implementation, debugging, reviews, and project-aware work.

GLM 5.2

Coding benchmark

GLM's official report presents strong coding, agentic, and long-context performance for software engineering workflows.

GLM 4.7 Flash

Fast iteration

GLM 4.7 Flash provides a lower-latency option for short coding turns, explanations, and focused implementation help.

GPT OSS 120B

Reasoning

OpenAI's open-weight reasoning model gives Sanad users another option for complex debugging and agentic coding work.

GLM 5.2 official benchmark evidence

Sanad links directly to the official GLM 5.2 report so engineers can inspect the published coding and agentic benchmark data.

GLM 5.2 benchmark comparison from the official Z.ai GLM 5.2 launch report.

GLM 5.2 coding benchmark comparison from the official Z.ai GLM 5.2 launch report.

Transparent pay-as-you-go access.

Users and businesses top up USD balance, start the daily timer, and pay only for model tokens used through Sanad.

Sanad account balance

$1+USD top-ups

Self-serve access to Sanad 0.1, GLM 5.2, GLM 4.7 Flash, and GPT OSS 120B, with 2 hours per day for coding workflows.

Add USD balance

Self-serve access for users and businesses
2 hours of use per day, reset by the timezone from the user's registered city
Sanad VS Code Extension, Sanad CLI, and Claude Code support
Final model prices are visible in your Sanad account before usage