# Command Code Review

> Command Code review: Coding agent for open models (DeepSeek, Kimi, GLM, Qwen, MiniMax) with taste learning; CLI + desktop + ACP for Zed; cheap $1-$20 plans.

![Command Code logo](https://www.versusref.com/logos/command-code.png)

Coding agent for open models (DeepSeek, Kimi, GLM, Qwen, MiniMax) with taste learning; CLI + desktop + ACP for Zed; cheap $1-$20 plans with published $ rolling windows.

See pricing · facts verified Oct 2, 2026

## What we know about Command Code

Command Code sits in the ai coding agents category, where it is coding agent for open models (DeepSeek, Kimi, GLM, Qwen, MiniMax) with taste learning; CLI + desktop + ACP for Zed; cheap $1-$20 plans with published $ rolling windows. We keep this Command Code profile grounded in primary sources, each fact dated to when we last confirmed it.

Command Code does not publish a public per-minute rate we have been able to verify, so the price figure here stays blank until we can confirm one. We would rather show nothing than a guessed number; if you have a current Command Code quote, it is the fastest way for us to close that gap.

On capabilities, Command Code covers enterprise plan (contact sales), pick the model per task, runs local models, zero data retention option, autonomous multi-file edits, and runs terminal commands. Each of those is verified against Command Code's own docs or dashboard, not marketing copy.

In total we track 25 verified facts for Command Code today, each linking the primary source it came from so you can check our work - and vendor claims we have not measured ourselves are labeled as such on the Command Code fact sheet below.

## Fact sheet

### Pricing

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| How usage is metered | $ usage pool + time windows | Oct 2 | [source](https://commandcode.ai/docs/resources/pricing-limits) |
| Cheapest paid plan (monthly) | $1 | Oct 2 | [source](https://commandcode.ai/pricing) |
| Top individual plan | $200 | Oct 2 | [source](https://commandcode.ai/pricing) |
| Usage included at entry tier | $10 in credits included (~9K requests) | Oct 2 | [source](https://commandcode.ai/pricing) |
| Rate-limit window | rolling 5-hour + weekly $ windows: Go $2/$5 | Oct 2 | [source](https://commandcode.ai/docs/resources/pricing-limits) |
| Price beyond the plan | Top-up credits 'at model cost, zero markup' | Oct 2 | [source](https://commandcode.ai/pricing) |
| Bring your own API key | Yes | Oct 2 | [source](https://commandcode.ai/docs/byok) |
| Team plan price | 40 USD/mo | Oct 2 | [source](https://commandcode.ai/pricing) |
| Enterprise plan (contact sales) | ✓  Yes | Oct 2 | [source](https://commandcode.ai/pricing) |

### Capabilities

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Models available | GPT-5.6 Sol, Gemini 3.7 Flash +9 more | Oct 2 | [source](https://commandcode.ai/) |
| Pick the model per task | ✓  Switch via /model. | Oct 2 | [source](https://commandcode.ai/docs/byok) |
| Runs local models | ✓  Yes | Oct 2 | [source](https://commandcode.ai/docs/byok) |

### Compliance & trust

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Trains on your code? | 'The Company does not train AI models on your source code | Oct 2 | [source](https://commandcode.ai/privacy) |
| Zero data retention option | ✓  Yes | Oct 2 | [source](https://commandcode.ai/privacy) |

### Build experience

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| Where it runs | CLI, desktop, ACP (Zed and other ACP clients) | Oct 2 | [source](https://commandcode.ai/) |
| Autonomous multi-file edits | ✓  Yes | Oct 2 | [source](https://commandcode.ai/docs) |
| Runs terminal commands | ✓  Yes | Oct 2 | [source](https://commandcode.ai/docs/permissions) |
| Background / cloud agents | ✓  Yes | Oct 2 | [source](https://commandcode.ai/docs) |
| Parallel agents | ✓  Git worktrees support. | Oct 2 | [source](https://commandcode.ai/docs) |
| MCP support | ✓  Yes | Oct 2 | [source](https://commandcode.ai/docs) |
| Project rules files | Taste profile in .commandcode/ (auto-learned) +2 more | Oct 2 | [source](https://commandcode.ai/privacy) |
| Checkpoints / rollback | ✓  Yes | Oct 2 | [source](https://commandcode.ai/docs) |

### Commercial

| Fact | Value | Verified | Source |
| --- | --- | --- | --- |
| License | Proprietary (npm package 'command-code' declares UNLICENSED) | Oct 2 | [source](https://registry.npmjs.org/command-code) |
| GitHub stars | 4,100 | Oct 2 | [source](https://github.com/CommandCodeAI/command-code) |
| Last release | v1.74.0 (CLI), 2026-10-02 | Oct 2 | [source](https://commandcode.ai/changelog) |

## Command Code head-to-head

| Comparison | Record | Per use case |
| --- | --- | --- |
| [Command Code vs Claude Code](https://www.versusref.com/coding-agents/claude-code-vs-command-code/) | won 4 · lost 3 · tied 0 | Beginners: won; Enterprise: lost; Free Plans: won; Local Models: won; Open Source: won; Terminal Workflows: lost; VS Code: lost |

Source: https://www.versusref.com/coding-agents/tools/command-code/