> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://respan.ai/docs/integrations/gateway/omp/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://respan.ai/_mcp/server.

# omp (gateway)

> Set up omp (oh-my-pi) with the Respan gateway.

Route [omp](https://omp.sh)'s LLM calls through the Respan gateway for automatic logging, caching, and model switching. omp loads custom providers from `~/.oh-omp/agent/models.yml`, so only your `RESPAN_API_KEY` is needed.

## Setup

#### Install omp

```bash
curl -fsSL https://omp.sh/install | sh
```

Or install from npm, which exposes the binary as `oh-omp`:

```bash
npm install -g @oh-labs/oh-omp
```

#### Add Respan as a provider

Create or edit `~/.oh-omp/agent/models.yml`:

```yaml
providers:
  respan:
    baseUrl: https://api.respan.ai/api
    apiKey: RESPAN_API_KEY
    api: openai-completions
    models:
      - id: gpt-4o
        name: GPT-4o
      - id: claude-sonnet-4-5-20250929
        name: Claude Sonnet 4.5
```

`apiKey` is the **name** of the environment variable that holds your key. Export it in your shell profile:

```bash
export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
```

No separate provider key needed. The Respan gateway handles provider authentication.

#### Run omp

```bash
omp --model respan/gpt-4o
```

For a one-shot, non-interactive run:

```bash
omp -p --model respan/gpt-4o "your prompt"
```

All LLM calls now route through Respan.

## Switch models

Add more entries under `models` and pick any of them with `--model respan/<id>`. Any of the 1000+ models available through the gateway work, for example:

```text
gpt-4o
claude-sonnet-4-5-20250929
gemini/gemini-3.5-flash
```

See the [full model list](https://platform.respan.ai/platform/models).

> Set up omp (oh-my-pi) with the Respan gateway.