GPT-5.4 Image 2
OpenAI · released Apr 21, 2026
- Type
- Proprietary
- Input
- $8.00
- Output
- $15.00
- Cached
- $2.00
List price · per 1M tokens · OpenAI at 272K context · source ↗
Our take
Written Aug 3, 2026GPT-5.4 Image 2 is OpenAI's hosted-only image-generation model that reads text, images and files and writes back both text and images. Its request limit of 272,000 tokens is unusually large for generation tasks, though no independent quality benchmarks are available in our data.
Use this for image generation and editing workflows that need long, detailed instructions, or for multimodal pipelines where the same model must read files and produce images. Pick it when you want OpenAI's direct platform with a known throughput of 38 tokens per second. Skip it if you need measured quality scores, want to self-host, or prefer a provider where throughput is verified.
The case for it
- 272,000-token request limit — unusually large for an image-generation model.
- Reads text, images and files and writes back both text and images.
- Identical pricing across both tracked providers.
The case against it
- No benchmark scores in our data, so quality is unverified.
- Throughput is only measured on OpenAI's platform; unverified on the alternative provider.
- Hosted only with no licence listed; cannot be run on your own hardware.
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-5.4 Image 2 — 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
- $8.00 in / $15.00 out
- Context served
- 272K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $8.00 / $15.00 | 272K | not measured | Unknown | Unknown | Unknown |
| OpenAI | $8.00 / $15.00 | 272K | 44 tok/s | 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 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
Models people weigh against GPT-5.4 Image 2
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.
- 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.
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+image+file->text+image
- Catalogue slug
- openai-gpt-5-4-image-2