# OpenAI Search Preview

Access the most up to date information on the web using openai search preview; get verifiable, cited, and instant answers powered by an AI search engine.

## API Information

- **Model Slug:** openai-search-preview
- **Branded URL:** https://www.eachlabs.ai/openai/gpt/openai-search-preview
- **Provider:** OpenAI
- **Category:** Text to Text
- **Output Type:** code
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Input at $2.50 per 1M tokens, output at $10 per 1M tokens
- **Estimated Processing Time:** 1 seconds
- **Last Updated:** 2026-06-08
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/openai-search-preview

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Input at $2.50 per 1M tokens, output at $10 per 1M tokens

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Input at $2.50 per 1M tokens, output at $10 per 1M tokens |

## Input Schema

| Parameter | Type | Required | Default | Constraints | Description |
|-----------|------|----------|---------|-------------|-------------|
| region | string | No | - | - | - |
| city | string | No | - | - | - |
| country_iso_code | string | No | - | - | - |
| search_context_size | string | No | - | low,medium,high | - |
| prompt | string | Yes | What was a positive news story from today? | - | - |

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "openai-search-preview",
  "input": {
    "prompt": "What was a positive news story from today?"
  }
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "code",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**openai-search-preview — Text-to-Text AI Model**

Developed by OpenAI as part of the gpt family, **openai-search-preview** is a text-to-text AI model that delivers verifiable, cited answers by integrating real-time web search into its responses, solving the problem of outdated or hallucinated information in standard language models. This **OpenAI text-to-text** capability, known as GPT-4o Search Preview, empowers developers and creators seeking instant, up-to-date insights without manual research. Users searching for "**openai-search-preview API**" or "OpenAI search preview" will find it excels at grounding responses in current web data, providing links to sources for transparency and reliability.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.