Added on Oct 28,2026

OpenLLM is an AI routing layer that sends requests from coding agents such as Claude Code, Codex and OpenCode through one local layer that connects your subscriptions, local models and API keys.
It lets you use the models you already pay for or run yourself inside any supported tool. If one model hits a rate limit mid-task, the next model in your fallback chain answers so the agent keeps working.
Every account includes some inference, so the first request works with nothing connected and no keys or card. It routes to providers including OpenAI, Anthropic and Google, as well as local servers such as Ollama and LM Studio, with a catalogue of over 200 models across 13 providers.
Key features include shared memory across your agents, web data through Context.dev, an integrations marketplace that adds a tool once for every client, an OpenAI- and Anthropic-compatible API, scoped API keys, usage and cost analytics and a subscription daemon for Claude, Codex and Kimi.
Provider keys are encrypted with AES-256-GCM in the browser under a recovery phrase only the user holds, so the server stores ciphertext only and cannot decrypt the vault.
It works with Claude Code, Codex, OpenCode, Grok Build, Raycast, Hermes and ChatGPT, and installs as a Mac app or with a one-line terminal command. Your existing Claude config is not modified.
Pricing: the Free plan costs nothing and includes 50 million non-cached tokens a month and two connected devices. Pro costs 30 US dollars a month with unlimited tokens, five devices and a 3-day free trial.
It is suited to developers who use several coding agents and model providers and want one place to manage keys, fallbacks and usage.
Similar tools to compare with OpenLLM:
| Tool | Pricing | Best for |
|---|---|---|
| Pollinations | Freemium | Developers and hobby builders who want a single API for adding AI images, audio and text to their websites, bots and app... |
| NemoClaw | Free | Developers and platform teams who want to run always-on AI agents on NVIDIA hardware under policy-based security control... |
| Agnes AI | Freemium | Developers building AI-powered apps who want access to several models through one API. |
| DiagramGPT | Free | Developers and students who need to sketch system designs and workflows quickly by describing them in words. |
| OrcaRouter | Freemium | Developers and teams who want to balance AI quality and cost across many models. |
Leave a review for the community
No Review Found