| Pricing | Startup: Free for up to 3 users and 3 projects. Cloud Starter: $9 per user/month with unlimited users and projects. Cloud Pro: $19 per user/month with unlimited users, projects, 1,000 included AI credits per licensed user per month, and priority support. Self-hosted: Starting at $3,000 per instance/
| Lite: $20/month (limited use, weekly allowance); Pro: $69/month (10 million free tokens); Max: $129/month (10 million free tokens); Ultra: $269/month (10 million free tokens); Enterprise: custom pricing with dedicated GPU cluster; Usage-based API: from $0.12 per 1M tokens prepaid balance with no mon
|
|---|
| Key features | - Specification Management: Manage connected requirements, data entities, APIs, interfaces, wireframes, and test cases in a versioned product model with traceable relations and branch-aware revisions
- Change Management: Define each product change through a Change Request that connects goal, affected specifications, project branch, implementation impact, and linked issue
- Architecture & Software Units Blueprints: Define subsystem architecture and software unit blueprints with implementation rules, responsibilities, dependencies, and file boundaries linked to product sp
- AI Assistants: AI Analyst, AI Test Designer, AI Architect, and AI Product Expert for refining specifications, designing tests, developing architecture, and reviewing implementation
- MCP for AI Coding Agents: Give coding agents branch-aware specifications, architecture guidance, software units, file traces, and Change Request context through MCP
- Specification and Code Alignment Verification: Check that code matches specifications and follows architecture rules as the system evolves
- Test Management: Organize test cases, test runs, execution, and result history
- MCP for QA Agents: Give QA agents prepared test runs, cases, steps, and expected outcomes through MCP to record execution results
| - Works with Cursor, VS Code, JetBrains, OpenCode, Hermes, Pi and other OpenAI-compatible clients
- Nine AI models available including DeepSeek V4 Pro, GLM 5.3, Qwen, and others
- Switch between models mid-conversation without losing context
- Unlimited tokens on Pro, Max, Ultra plans with transparent rate limits
- Code never trained on or shared with third-party providers
- 10 million free tokens with all paid plans for trial
- Referral program with credits and Pix payouts
- Community of 200+ active developers on WhatsApp and Discord
- Context windows up to 1 million tokens on most models
- Data export available during subscription and up to 30 days after termination
|
|---|
| What makes it different | - Preserves product context across tasks, agents, and code changes through a structured, verified product model
- Reduces handoffs and coordination by delegating whole features with connected specifications and implementation scope
- Prevents architecture drift by connecting implementation with subsystem architecture rules, unit guidelines, and component responsibilities
- Built for complex products where a single feature touches connected data, APIs, interfaces, and business rules across multiple repositories and systems
- Keeps product model current as specifications and implementation change using AI assistance and team review
| - Dedicated GPU allocation per plan with no resource sharing
- Fixed flat monthly pricing with no surprise token overages
- Brazilian infrastructure with code isolation from US-based AI providers
- Transparent usage limits and model pricing shown before subscription
|
|---|
Reqode
Verboo Code