Does OpenLLM store my prompts?

No. Requests stream through to the provider and back; we record metadata like token counts, model and latency for your usage dashboard.

Is there a free plan?

Yes. You can sign up and route requests on the free tier, then upgrade from Settings when you need more.

OpenCode vs Claude Code: which terminal agent to use

Guides

OpenCode vs Claude Code

Claude Code is Anthropic's own agent, tuned for Claude models. OpenCode is open source and provider-agnostic. You don't have to pick one model setup per agent.

$curl -fsSL https://www.openllm.sh/install | bash

$openllm claude

$openllm opencode

Start free See pricing

Pick Claude Code when

Claude models are your main driver
You want Anthropic's first-party features as they ship

Pick OpenCode when

You switch between many providers and models
You want an open-source agent you can read and change

Or run both on one setup

Launch either through OpenLLM and they share the same model aliases, fallback chains, MCP code search, memory and usage dashboard. Neither client's own config is modified.

Fallback chains when a model is rate-limited

Define an ordered chain per model alias. When a hop returns a rate limit, an overload or a provider error, the request moves to the next hop instead of failing your session.

Chains are configured once and shared by every client and device
Each hop resolves its own model settings, so a fallback never inherits the wrong parameters
Every hop that ran is visible in your request history

Questions

Something else? Contact us