GPT-4o Search Preview
OpenAI · released Mar 12, 2025
- Type
- Proprietary
- Input
- $2.50
- Output
- $10.00
- Cached
- Not published
List price · per 1M tokens · OpenAI at 128K context · source ↗
Our take
Written Aug 2, 2026GPT-4o Search Preview is a hosted-only text model from OpenAI that augments its responses with search. It handles up to 128,000 tokens in a single request and is available through two channels at the same price point, though no benchmark scores are available to verify its quality.
Choose this when you need search-augmented generation specifically from an OpenAI model, or for long-context text tasks up to 128,000 tokens. Skip it if you want measured quality scores, need throughput guarantees for latency-sensitive work, or are looking for a cheaper option in the same class.
The case for it
- Identical pricing across both tracked providers — no markup or arbitrage opportunity between them.
- Search augmentation built into a model from the most widely recognised AI lab.
The case against it
- Premium pricing with no measured quality evidence in our data: the output cost is high and benchmark scores are absent.
- No throughput data for latency-sensitive use; speed is unverified in our data.
- Text-only; no image, audio or video input or output.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up GPT-4o Search Preview — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Why this differs from the header. The strip above quotes OpenAI's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $2.50 in / $10.00 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $2.50 / $10.00 | 128K | not measured | Unknown | Unknown | Unknown |
| OpenAI | $2.50 / $10.00 | 128K16K out | not measured | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | |||
| OpenAI |
Tool calling: 0 of 2 listings say yes, 2 publish no parameter list. JSON output: 0 of 2 listings say yes, 2 publish no parameter list. Strict schema: 0 of 2 listings say yes, 2 publish no parameter list.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, so we hold no quality figures at all.
- 2 of 2 listings publish no parameter list, so what their API accepts is unknown to us.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- openai-gpt-4o-search-preview