> ## Documentation Index
> Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Phaseo Gateway base URL: https://api.phaseo.app/v1. Send `Authorization: Bearer $PHASEO_API_KEY` with every request.
> Model IDs look like `provider/model`, for example `openai/gpt-6-astra`. Do not guess IDs: list them with `GET /v1/models` or check https://phaseo.app/models. `phaseo/free` routes to an available free model and needs no wallet balance.
> For new text integrations prefer `POST /v1/responses`. `POST /v1/chat/completions` (OpenAI format) and `POST /v1/messages` (Anthropic format) suit existing code.
> The full API contract is https://phaseo.app/docs/openapi/v1/openapi.yaml. Official SDKs: `@phaseo/sdk` (TypeScript) and `phaseo` (Python), plus Go, C#, PHP, Ruby and Rust.
> Search these docs over MCP at https://phaseo.app/docs/mcp, and install Phaseo skills with `npx skills add https://phaseo.app/docs`. If a page is wrong or out of date, report it with the MCP `submit_feedback` tool.
> Manage Phaseo accounts with the `phaseo` CLI (`npm install -g @phaseo/cli`, then `phaseo login` or `phaseo login --device-code`), the `/v1` Management API or the MCP server at `https://mcp.phaseo.app/mcp?access=manage`. Do not send users to the dashboard for account tasks. A person is still needed for sign-up, approving a sign-in, paying the first top-up on the checkout link that `phaseo credits add` returns when no card is saved, confirming each saved-card top-up from the emailed link, and account security (password, MFA, passkeys). Create API keys with `phaseo keys create --name <name> --json`; never guess one. Credit top-ups need `phaseo login --scopes billing:write` first. Task map: https://phaseo.app/docs/v1/developers/manage-from-an-agent.md.

# Moderation

> Klassifiziere Text und Bilder mit POST /v1/moderations aus jedem Phaseo-SDK auf ihre Sicherheit.

Sende Text oder Bilder an `POST /v1/moderations`, um zu erfahren, ob sie markiert werden und in welchen Kategorien. Die Beispiele verwenden einen `client`, der wie unter [Installation](https://phaseo.app/docs/de/v1/sdk-reference/client/installation.md) erstellt wurde.

```typescript TypeScript theme={null}
const moderation = await client.generateModeration({
  model: "openai/omni-moderation",
  input: "Text to classify",
});

console.log(moderation.results[0].flagged);
```

```python Python theme={null}
moderation = client.generate_moderation({
    "model": "openai/omni-moderation",
    "input": "Text to classify",
})

print(moderation["results"][0]["flagged"])
```

```go Go theme={null}
resp, err := client.GenerateModeration(context.Background(), map[string]interface{}{
  "model": "openai/omni-moderation",
  "input": "Text to classify",
})
if err != nil {
  panic(err)
}
fmt.Println(resp["results"])
```

```csharp C# theme={null}
var response = await client.GenerateModeration(new Dictionary<string, object>
{
    ["model"] = "openai/omni-moderation",
    ["input"] = "Text to classify",
});
```

```php PHP theme={null}
$response = $client->generateModeration([
    'model' => 'openai/omni-moderation',
    'input' => 'Text to classify',
]);
```

```ruby Ruby theme={null}
response = client.generate_moderation(
  model: 'openai/omni-moderation',
  input: 'Text to classify'
)
```

```java Java theme={null}
String body = """
{
  "model": "openai/omni-moderation",
  "input": "Text to classify"
}
""";

Object response = client.createModeration(new com.fasterxml.jackson.databind.ObjectMapper().readTree(body));
System.out.println(String.valueOf(response));
```

```rust Rust theme={null}
// Noch keine Moderations-Methode: post() sendet JSON an jeden Phaseo-Pfad.
let response = client.post("/moderations", &json!({
    "model": "openai/omni-moderation",
    "input": "Text to classify"
}))?;

println!("{}", response.body["results"][0]["flagged"]);
```

| Sprache | Methode | Rückgabe |
| - | - | - |
| TypeScript | `client.generateModeration(request)` | `ModerationsResponse` |
| Python | `client.generate_moderation(request)` oder `client.moderations.create(request)` | Ein Dict |
| Go | `client.GenerateModeration(ctx, req)`, Alias `CreateModeration` | `map[string]interface{}` |
| C# | `client.GenerateModeration(request)`, Alias `CreateModeration` | `Dictionary<string, object>?` |
| PHP | `$client->generateModeration($request)`, Alias `createModeration()` | Ein Array |
| Ruby | `client.generate_moderation(...)`, Alias `create_moderation` | Ein Hash |
| Java | `client.createModeration(jsonNode)` | `Object` |
| Rust | `client.post("/moderations", &request)` | `PhaseoResponse`, mit dem JSON in `body` |

## Parameter

Die Feldnamen sind in jedem SDK die Felder des JSON-Bodys.

| Feld | Hinweise |
| - | - |
| `input` | Erforderlich. Ein String, ein Array von Strings oder ein Array aus `text`- und `image_url`-Parts. |
| `model` | Eine Moderationsmodell-ID. Standard ist `openai/omni-moderation`. |
| `metadata` | Deine eigenen Schlüssel-Wert-Daten. |
| `provider` | Routing-Präferenzen für Anbieter. |
| `meta` | Setze den Wert auf `true`, um den `meta`-Block des Gateways einzuschließen. |

Das vollständige Schema steht in der [Moderations-API-Referenz](https://phaseo.app/docs/de/v1/api-reference/endpoint/moderations.md).

## Antwort

`ModerationsResponse`. Jedes Ergebnis enthält `flagged`, eine `categories`-Map mit booleschen Werten und eine `category_scores`-Map mit Scores:

```json theme={null}
{
  "results": [
    {
      "flagged": false,
      "categories": {
        "hate": false,
        "hate/threatening": false,
        "harassment": false,
        "harassment/threatening": false,
        "self-harm": false,
        "self-harm/intent": false,
        "self-harm/instructions": false,
        "sexual": false,
        "sexual/minors": false,
        "violence": false,
        "violence/graphic": false
      },
      "category_scores": {
        "hate": 0.01,
        "hate/threatening": 0.0,
        "harassment": 0.02,
        "harassment/threatening": 0.0,
        "self-harm": 0.0,
        "self-harm/intent": 0.0,
        "self-harm/instructions": 0.0,
        "sexual": 0.05,
        "sexual/minors": 0.0,
        "violence": 0.01,
        "violence/graphic": 0.0
      }
    }
  ]
}
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.