> ## Documentation Index
> Fetch the complete documentation index at: https://gomodel-feature-failover-management.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# GoModel & OpenClaw

> Use GoModel as an OpenAI-compatible AI gateway for OpenClaw, with recommended OpenAI models and a production-ready setup.

## Overview

GoModel is an OpenAI-compatible **AI gateway** for OpenClaw. It gives you one
stable API endpoint while routing requests to OpenAI and other providers. This
keeps OpenClaw configuration simple and makes model switching easier.

Flow:

`OpenClaw -> GoModel -> OpenAI/Anthropic/Gemini/...`

## Recommended OpenAI Models (As of February 28, 2026)

These OpenAI model IDs are currently good defaults for OpenClaw:

| Model ID              | Best for                                                                      |
| --------------------- | ----------------------------------------------------------------------------- |
| `gpt-5-mini`          | Default choice for cost/performance balance                                   |
| `gpt-5.2`             | Higher quality for complex coding and agentic tasks                           |
| `gpt-5.2-chat-latest` | Chat-tuned behavior aligned with ChatGPT                                      |
| `gpt-5.2-codex`       | Advanced coding workflows in Codex-like environments (Responses API oriented) |

<Note>
  Verify availability in your GoModel instance first: `GET /v1/models`. Model
  availability depends on your OpenAI account tier and API surface.
</Note>

Reference:

* OpenAI GPT-5.2 release: [OpenAI Changelog](https://platform.openai.com/docs/changelog)
* OpenAI model docs: [Models Overview](https://platform.openai.com/docs/models)

## 1. Run GoModel

Start GoModel with at least one provider and a master key:

```bash theme={null}
docker run --rm -p 8080:8080 \
  -e GOMODEL_MASTER_KEY="change-me" \
  -e OPENAI_API_KEY="sk-..." \
  enterpilot/gomodel
```

Confirm your model list:

```bash theme={null}
curl -s http://localhost:8080/v1/models \
  -H "Authorization: Bearer change-me"
```

## 2. Add a GoModel provider in OpenClaw

In your OpenClaw config, add a custom provider that uses OpenAI-compatible requests:

```json theme={null}
{
  "env": {
    "GOMODEL_MASTER_KEY": "change-me"
  },
  "models": {
    "mode": "merge",
    "providers": {
      "gomodel": {
        "baseUrl": "http://localhost:8080/v1",
        "apiKey": "${GOMODEL_MASTER_KEY}",
        "api": "openai-completions",
        "models": [
          {
            "id": "gpt-5-mini",
            "name": "GoModel gpt-5-mini",
            "reasoning": false,
            "input": ["text"],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 8192
          },
          {
            "id": "gpt-5.2",
            "name": "GoModel gpt-5.2",
            "reasoning": true,
            "input": ["text"],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 128000,
            "maxTokens": 8192
          }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "gomodel/gpt-5-mini"
      }
    }
  }
}
```

Replace model IDs with values returned by GoModel at `/v1/models`.

<Tip>
  `gpt-5.2-codex` is highly relevant for coding agents, but OpenAI currently
  positions it as Responses API oriented. If your OpenClaw setup uses
  `openai-completions`, prefer `gpt-5-mini` or `gpt-5.2`.
</Tip>

## 3. Validate from OpenClaw

After reloading OpenClaw, send a test prompt with your configured default model.

If you get `401 Unauthorized`, verify OpenClaw is sending the same value as `GOMODEL_MASTER_KEY`.

## Notes

* If GoModel is running in Docker and OpenClaw is not, `http://localhost:8080` is usually correct.
* If both run in different containers, use a shared Docker network and container hostname instead of `localhost`.
* You can expose multiple GoModel-backed models by adding more entries under `models.providers.gomodel.models`.
* GoModel as an AI gateway also gives you centralized auth, audit logs, usage analytics, and provider abstraction with one OpenAI-compatible endpoint.