Inferrs

inferrs can serve local models behind an OpenAI-compatible

API. OpenClaw works with through the generic path.

is currently best treated as a custom self-hosted OpenAI-compatible backend, not a dedicated OpenClaw provider plugin.

Getting started

Full config example

This example uses Gemma 4 on a local

server.

json5
Copy
{
  agents: {
    defaults: {
      model: { primary: "inferrs/google/gemma-4-E2B-it" },
      models: {
        "inferrs/google/gemma-4-E2B-it": {
          alias: "Gemma 4 (inferrs)",
        },
      },
    },
  },
  models: {
    mode: "merge",
    providers: {
      inferrs: {
        baseUrl: "http://127.0.0.1:8080/v1",
        apiKey: "inferrs-local",
        api: "openai-completions",
        models: [
          {
            id: "google/gemma-4-E2B-it",
            name: "Gemma 4 E2B (inferrs)",
            reasoning: false,
            input: ["text"],
            cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
            contextWindow: 131072,
            maxTokens: 4096,
            compat: {
              requiresStringContent: true,
            },
          },
        ],
      },
    },
  },
}

Advanced configuration

Why requiresStringContent matters

Gemma and tool-schema caveat

Manual smoke test

Proxy-style behavior

Troubleshooting

curl /v1/models fails

messages[].content expected a string

Direct /v1/chat/completions calls pass but openclaw infer model run fails

inferrs still crashes on larger agent turns

Related