Use hundreds of models via OpenRouter with FastClaw
Connect FastClaw to OpenRouter and give every agent access to models from many vendors with a single API key.
One key, many vendors
The openrouter preset targets https://openrouter.ai/api/v1 with OPENROUTER_API_KEY — then choose any model OpenRouter lists.
Model per agent
Try a new model on one agent without touching the rest of your deployment.
Switch on the fly
Change the model from the console or with /model in fastclaw chat — sessions and memory carry over.
What you can do
- Let agency clients pick their model without you managing a dozen vendor keys — see FastClaw for agencies.
- Benchmark agents across vendors by giving each one a different model.
- Fall back to a direct Anthropic or OpenAI provider whenever you need vendor-specific features.
Set it up
- In Console → Models, click Add provider, choose OpenRouter and paste your key.
- Add the model IDs you want to use and pick a default, or set one on an agent's Models tab.
- From the CLI, the preset fills in the API base:
fastclaw agents config alpha set provider.openrouter.apiKeyEnv OPENROUTER_API_KEY
fastclaw agents config alpha set provider.openrouter.apiBase https://openrouter.ai/api/v1
Notes
Learn how providers, defaults and per-agent overrides fit together on the models feature page.
Frequently asked questions
More Integrations
All IntegrationsOpenAI
Run FastClaw agents on OpenAI models — set a deployment-wide default, override per agent, and expose your agents through an OpenAI-compatible API.
Anthropic
Run FastClaw agents on Claude through Anthropic's native Messages API — with prompt caching, extended thinking and image input preserved.
DeepSeek
Run FastClaw agents on DeepSeek — a built-in preset, thinking-mode support and per-agent model overrides for low-cost, capable agents.
Ollama
Point FastClaw at Ollama to run AI agents on local, open-weight models — no API key, no data leaving your machine.
Try it on your own agents
Start free in FastClaw Cloud, or self-host the single binary in a minute.