AutoMode / Compare routers
Claude Code model routers compared
A Claude Code model router picks a model for each prompt, so you stop switching by hand. The main options differ in how they run, what they route and what they can prove. We make AutoMode, so read this as a maker's view. Each row comes from the project's own README.
These projects change quickly. We read the four main READMEs on 2026-10-30 and the others on 2026-10-31. If a cell is wrong, open an issue.
Four routers side by side
| Feature | AutoMode | effortless | jev-router | claude-router |
|---|---|---|---|---|
| Effort per prompt | Yes | Yes | Not described | Yes |
| Model per prompt | Yes, on by default | Off by default, experimental | Yes | Yes |
| Extra credential | None | None. A Jev key is optional | Jev key | Depends on the classifier. Ollama needs none |
| How it runs | Claude Code mod | Claude Code mod | Local proxy around the CLI | Claude Code mod |
| CLIs | Claude Code | Claude Code | Claude Code and Codex | Claude Code |
| Multi-stage workflow | Plan, build, verify, review | Not described | Not described | Not described |
| Mandatory review for risky work | Yes, Opus | Not described | Not described | Not described |
| Prompt cache | Countdown on the bar, cost check before a switch | Countdown on the bar, compact and handoff offers | Refuses a downgrade that wastes more cache than it saves | Cache-cost rules in its policy |
| Published cost result | No | Yes. 21% less than Opus medium, on mostly easy tasks. Its README gives the limits | None found | "Savings are not measured" |
"Not described" means the README does not mention it. It does not prove the feature is absent.
Where the others are ahead
- effortless has a cost result. AutoMode does not. We will not quote a saving until a public run produces one.
- effortless is simpler. It does one job.
- jev-router also runs on Codex. AutoMode runs only in Claude Code.
- claude-router lets you choose the classifier, including a local Ollama model. AutoMode's judge always runs on Haiku, through your Claude login.
AutoMode is not independent of these projects. Its effort rules and bar techniques are ported from effortless. Its classifier contract and switch payback are adapted from claude-router and jev-router.
Other tools with similar names
- ClaudeRouter classifies each prompt and delegates to Haiku, Sonnet or Opus. It installs from npm, and its README lists a Pro or Max plan as a requirement for delegation.
- claude-model-router tracks token use and routes sub-tasks to subagents, rather than the main prompt. Its 35 to 50% figure is its own claim.
- Claude Code Router does a different job. It is a local app that connects coding agents to the providers you choose, then routes and fails over between them. Pick it to reach other providers.
Which one should you pick?
- You want effort routing and nothing more: effortless.
- You also use Codex: jev-router.
- You want to run the classifier locally: claude-router.
- You want to reach non-Anthropic models: Claude Code Router.
- You want model and effort routing, risk floors and a review workflow with no key: AutoMode.
Does a router save money?
It can, but a router can also cost more. A model switch in a warm chat rewrites the prompt cache. Treat any saving as a claim until you can repeat the benchmark.
Install AutoMode
Paste these into Claude Code, one at a time, then run /reload-plugins.
/plugin marketplace add mralexivy/AutoMode
/plugin install automode@automodeIt is free. It needs no key and no server, and it starts on its own.