# Judge Copy
> Score a draft email for inbox placement. Free.
**Beta.** This endpoint is not in production yet and may change before it ships.
Runs the same Copy check as the editor panel: a 0-100 score, the likely placement, flagged sentences and flagged words. Nothing is saved and no AI credit is charged.
## Body Parameters
Subject line, up to 500 characters.
Email body, plain text or HTML. At least one of `subject` or `body` is required.
Set to `true` when the body is HTML.
Sequence step the copy belongs to (1-50). Step 1 is judged as a first-touch email.
## Response
Inbox score, 0-100.
`inbox`, `promotions` or `spam`.
Confidence in the placement, 0-1.
One-line summary of the read.
Overall problems judged present.
Flagged sentences, with offsets into `subjectText` or `bodyText`, a category and a suggested action.
Flagged words, with a replacement when one is unambiguous.
Model that produced the verdict.
The subject as checked. Flag offsets refer to this text.
The body as checked, as plain text. Flag offsets refer to this text.
Whether the body was cut to `maxBodyChars` before checking.
Longest body that is checked.
```bash cURL
curl -X POST "https://api.foxreach.io/api/v1/copy/judge" \
-H "X-API-Key: otr_your_key" \
-H "Content-Type: application/json" \
-d '{"subject": "Quick question", "body": "Hi {{firstName}}, are you the right person to talk to about outbound?"}'
```
```python Python (beta)
from foxreach import FoxReach
client = FoxReach(api_key="otr_your_key")
result = client.copy.judge("Quick question", "Hi {{firstName}}, are you the right person to talk to about outbound?")
print(result["verdict"]["score"])
```
```typescript TypeScript (beta)
import { FoxReach } from "foxreach";
const client = new FoxReach({ apiKey: "otr_your_key" });
const result = await client.copy.judge({
subject: "Quick question",
body: "Hi {{firstName}}, are you the right person to talk to about outbound?",
});
console.log(result.verdict.score);
```
```json
{
"data": {
"verdict": {
"score": 91,
"placement": "inbox",
"placementConfidence": 0.9,
"placementProbabilities": {"inbox": 0.9, "promotions": 0.08, "spam": 0.02},
"summary": "Reads like a personal note.",
"signals": [],
"flags": [],
"words": []
},
"model": "typesafe/jev-latest",
"subjectText": "Quick question",
"bodyText": "Hi {{firstName}}, are you the right person to talk to about outbound?",
"truncated": false,
"maxBodyChars": 12000
}
}
```
## Errors
| Status | Description |
|--------|-------------|
| `400` | Neither subject nor body was provided |
| `401` | Missing or invalid API key |
| `502` | The model could not be reached or returned something unusable. Retry shortly |
| `503` | Copy check is unavailable on this server |
## Rate Limit
- **100 requests per minute, shared by every `expensive` call in your workspace.** Fixed 60-second window.
- Every response includes `X-RateLimit-Limit`, `X-RateLimit-Remaining`, `X-RateLimit-Reset` (unix epoch seconds) and `X-RateLimit-Bucket` (`expensive`).
- A `429` response includes a `Retry-After` header (seconds until the bucket resets).
For client-side patterns (`Retry-After`, exponential backoff, monitoring `X-RateLimit-Remaining`), see [Rate Limiting](/rate-limiting).