everyapi
Integration · Cross-platform AI assistant (the lobster way 🦞)OpenAI-compatible · one key · live model catalog
OpenClaw

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.

01Setup code

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

02Steps

From zero to your first call

  1. Install OpenClaw

    Install OpenClaw from its current official instructions and record the release or package version you use.

    docs.openclaw.ai/start/onboarding

  2. 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.

  3. 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.

  4. 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.