Run the EveryAPI gateway inside OpenClaw
OpenClaw is a self-hosted assistant that can connect messaging channels and model providers. Because its configuration schema is evolving, follow the documentation for your installed release when adding EveryAPI as an OpenAI-compatible provider.
One base URL line points OpenClaw at EveryAPI
Default global Base URL / China-first Base URL: https://api.everyapi.ai/v1 / https://api-cn.everyapi.ai/v1
From zero to your first call
- Install OpenClaw
Install OpenClaw from its current official instructions and record the release or package version you use.
docs.openclaw.ai/start/onboarding
- Open the provider configuration
Find the model-provider settings documented for your installed OpenClaw release. Do not assume that older config paths or camelCase field names still apply.
- Choose the supported OpenAI protocol
Set the EveryAPI base URL and key, then select the OpenAI-compatible protocol supported by both the OpenClaw workflow and the model you intend to use.
- Use the full provider/model name for agent.model
Assign an EveryAPI model ID using the provider/model syntax required by your OpenClaw release. Test it before enabling messaging channels or skills that can act on external systems.
