# Price an unsaved evaluation

Source: https://docs.vlayers.ai/reference/agents/quote-evaluation-draft

`GET /v1/evaluations/scoring/quote` · scope `workspace:read`

The same price for an evaluation you have not saved yet. Send the sizes of what the form holds, never the text: `criteriaBytes`, `optionsBytes` and `labelsBytes` (UTF-8 bytes; an option counts its value, its description and 8 bytes of punctuation, a rating label its text and 40 bytes), the `model`, and `agentId` for that agent's judgement limit. The ceiling counts them, so a longer text or more options raise `quote.maxUsd`.

Requires an API key with the `workspace:read` scope.

| Name | In | Type | Required | Description |
|---|---|---|---|---|
| `model` | query | string | no | The judge model. Default: gpt-4o-mini. Example: `"gpt-4o-mini"` |
| `agentId` | query | string | no | The agent the evaluation applies to; its judgement limit is used. Example: `"0192f5c2-6f7a-7b9c-8d1e-2f3a4b5c6d78"` |
| `criteriaBytes` | query | integer | no | The UTF-8 byte size of what the judge looks for (at most 4000 characters, so 16000 bytes). Example: `120` |
| `optionsBytes` | query | integer | no | The size of the options as the judge prompt writes them, at most 12 options. Example: `40` |
| `labelsBytes` | query | integer | no | The size of the two rating labels as the judge prompt writes them. Example: `0` |
| `sampleRate` | query | number | no | The share of subjects to judge, above 0 up to 1. Default: 1. Example: `1` |

## Request

cURL:

```bash
curl "https://api.vlayers.ai/v1/evaluations/scoring/quote?model=gpt-4o-mini&criteriaBytes=120&agentId=$AGENT_ID" \
  -H "Authorization: Bearer $VOICELAYER_API_KEY"
```

TypeScript:

```ts
import { VoiceLayer } from '@voicelayer/api';

const voicelayer = new VoiceLayer();

const { quote } = await voicelayer.agents.quoteEvaluationDraft({
  model: 'gpt-4o-mini',
  criteriaBytes: 120,
  agentId: '<agent-id>'
});
console.log(quote.maxUsd);
```

Python:

```python
from voicelayer import VoiceLayer

vl = VoiceLayer()

result = vl.agents.quote_evaluation_draft(
    model="gpt-4o-mini",
    criteria_bytes=120,
    agent_id="<agent-id>",
)
print(result.quote.max_usd)
```

## Response `200`

```json
{
  "quote": {
    "maxUsd": 0.0123,
    "typicalUsd": 0.0031,
    "maxScoresPerConversation": 3,
    "sampleRate": 1,
    "outcomeIsFree": true
  }
}
```
