Claude Code
A terminal-native coding agent that reads, edits and runs code across a whole repository.
Full Claude Code record →Head to head
Claude Code vs Replit Agent
Claude Code (Anthropic) and Replit Agent (Replit) both sit in Coding. Claude Code shipped more tracked changes in the last 30 days (10 vs 5). Every value below comes from the latest crawl of the vendors' own pages.
| Attribute | Claude Code Anthropic | Replit Agent Replit |
|---|---|---|
| Segment | Coding | Coding |
| Version | latest | Replit Agent |
| Entry cost | from $20/mo | Free tier · from $20/mo |
| Pricing tiers | Pro $20 · Team (Standard seat) $25 · Team (Premium seat) $125 · Enterprise $20 | Free Mode (Core/Pro allowance) free |
| Model stack | Claude 3.5 Sonnet · Fable 5 · Fable 5.1 · Haiku · Haiku 4.5 · Haiku 5.5 · Opus · Opus 5 · Opus 5.5 · Sonnet · Sonnet 3.5 · Sonnet 5 · Sonnet 5.5 | Agent Max Models · Agent Power Models · Claude · Free Mode · Free Mode Model · frontier models · GPT-5 class · Max Mode · Max Mode Model · Max mode models · Power Mode · Power Mode Model · Power mode models · unspecified frontier model |
| Context window | Up to 1M varies by model | Model-dependent |
| Public API | ||
| Routes models | ||
| Changes / 30d | 10 | 5 |
| Origin | Global | Global |
| Capabilities | Terminal agent, Repo-wide edits, Subagents, MCP servers, Hooks, Background tasks, Agentic coding CLI, VS Code extension | Prompt to deployed app, Autonomous testing loop, Database and auth provisioning, Mobile app, Checkpoint billing, Plan mode, Lite mode, Economy mode |
Replit Agent
Replit Agent scaffolds, edits and deploys full applications from natural language, billed by effort-based agent checkpoints.
Full Replit Agent record →