Muse Code
Terminal-based AI coding agent that plans, writes, debugs, and validates code across large repos using persistent sub-agents.
Updated 2026-08-18
Yes, within limits. Muse Code runs a free tier with paid plans above it.
Listed pricing: Freemium + $1.25/M input tokens standard.
Overview
Muse Code is a terminal-based AI coding agent from Meta that plans, writes, debugs, and validates code across large repositories using persistent sub-agents. Launched in beta on August 5, 2026 alongside the co-trained Muse Spark 1.2 model, it targets developers who work on complex, multi-file codebases rather than simple scripts.
The agent operates directly in the terminal and maintains state across subtasks, allowing it to coordinate changes that span multiple files or modules. It is positioned against other autonomous coding tools from Anthropic, OpenAI, and independent startups, with Meta emphasizing its focus on large-scale codebases and the option for lower-cost usage through a contributor tier that shares usage data.
Is Muse Code free?
Yes, within limits. Muse Code runs a free tier with paid plans above it.
What the free tier covers: Limited usage with standard rate limits.
Listed pricing: Freemium + $1.25/M input tokens standard.
Pricing on this page has not been re-verified. The entry was last edited on , and no separate pricing check has been run since. Treat the figures as a record of what was published then and confirm on the official site.
What the free tier leaves out
Read straight off the plan list below. Vendors move features between tiers, so check the current split before you pay.
- Standard $1.25/M input tokens Full access without data sharing
- Contributor $0.10/M input tokens Reduced rate with usage data opt-in
Muse Code pricing
| Plan | Price | What's included |
|---|---|---|
| Free tier | Free | Limited usage with standard rate limits |
| Standard | $1.25/M input tokens | Full access without data sharing |
| Contributor | $0.10/M input tokens | Reduced rate with usage data opt-in |
Limited usage with standard rate limits
Full access without data sharing
Reduced rate with usage data opt-in
Pricing on this page has not been re-verified. The entry was last edited on , and no separate pricing check has been run since. Treat the figures as a record of what was published then and confirm on the official site.
Is Muse Code worth it?
You can test that on the free tier before paying anything. The recorded trade-offs are listed below, and any one of them can settle the question on its own.
The 8.2/10 AI Score is an editorial read of published capability, price and shipping pace. Nobody here has hands-on hours with Muse Code. How we verify.
Worth it if
The strengths recorded against this entry.
- Handles multi-file changes in large repositories
- Persistent sub-agents maintain task context
- Contributor tier offers significantly lower token costs
- Backed by Meta's Muse Spark 1.2 model
Not worth it if
Any one of these blocks your use case.
- Still in beta with limited public benchmarks
- Terminal-only interface may limit adoption
- Data-sharing requirement for lowest pricing tier
- No public information on output token pricing
Key features
Persistent sub-agents
Breaks complex tasks into coordinated sub-agents that retain context across steps, reducing drift on large changes.
Large repo navigation
Designed to traverse and modify multi-file repositories instead of operating on isolated files or snippets.
Token-based pricing tiers
Standard rate of $1.25 per million input tokens with a $0.10/M contributor tier available when opting into data sharing.
How it compares
| Tool | Best for | Pricing | Score |
|---|---|---|---|
| Muse Code | — | Freemium + $1.25/M input tokens standard | 8.2/10 |
| Cursor vs Cursor → | Professional developers handling complex, multi-file refactors who want AI built into a familiar VS Code-based editor. | Freemium | 9.5/10 |
| GPT-5.5 vs GPT-5.5 → | Developers and teams needing a frontier reasoning model for agentic coding workflows and large-codebase context handling. | API: $5/$30 per 1M tokens (in/out). ChatGPT Plus $20/mo, Pro $200/mo | 9.4/10 |
| Claude Code vs Claude Code → | Developers who want an agent that works inside an existing repo and toolchain rather than in a hosted editor, and who already pay for a Claude plan. | Included with Claude Free, Pro, Max, Team and Enterprise plans | 9.3/10 |
Compare head-to-head
Comparison explorer Put Muse Code up against any three tools Opens with Muse Code already loaded. Add up to three more from the full index and read pricing, features, pros and cons in one table. →Related reading
How to Install and Use Meta's Muse Code Agent
Meta's Muse Code installs with one curl line and bills $0.10 per million input tokens on the contributor tier. The steps, failure modes, and when to skip it.
Muse Code Ships With Spark 1.2 and a $0.10 Tier
Meta's Muse Code and Muse Spark 1.2 landed August 5 at $1.25/$4.25 per million tokens, or $0.10/$0.20 if Meta can train on your code.
DeepSeek Harness: Open Agent Runtime, How to Run It
DeepSeek open-sourced an MIT-licensed agent runtime on August 13. Plugin architecture, Trajectory replay, and the npx command to run it locally.
Ready to try Muse Code?
Head to the official site to start with Muse Code — pricing and plans are listed above.
Visit Muse Code