GPT-5.4 Nano
GPT-5.4 Nano is a large language model made by OpenAI, added to the catalog on 17 Mar 2026. It has a context window of 400,000 tokens and costs $0.20 per 1M input tokens and $1.25 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: summarising long documents, answering questions about image inputs and reviewing files and related materials.
Price checked · source: OpenRouter
What GPT-5.4 Nano is
OpenAI GPT-5.4 Nano is a lightweight member of the GPT-5.4 family, described for speed-critical and high-volume tasks. It accepts text, image, and file inputs and produces text. The model’s catalog description notes a low-latency design, which suits workflows built around frequent requests or responses where waiting time matters. It also supports reasoning and tool use, along with structured outputs and response-format controls.
The model has a context length of 400,000 tokens and a maximum output of 128,000 tokens. That context capacity can accommodate substantial source material alongside a request, making the model relevant to work with long documents or several related inputs. Its text output can be used for summaries, answers, explanations, or content formatted to a specified structure. Image and file acceptance provides additional input options beyond plain text, while tool support allows it to participate in tool-enabled workflows. These capabilities suit document review, image-based question answering, long-context analysis, and generating structured responses. The catalog does not specify particular file formats or image tasks, so applications depend on the inputs and surrounding system. The large maximum output also leaves room for extended responses when a task calls for them. This makes it a candidate for tasks that combine extensive context with detailed text output.
Key features
- Accepts text, image, and file inputs
- Produces text with a maximum output of 128,000 tokens
- 400,000-token context length
- Supports tools, reasoning, structured outputs, and response formats
Typical uses
- Summarising long documents
- Answering questions about image inputs
- Reviewing files and related materials
- Generating structured text responses
- Tool-enabled workflows
GPT-5.4 Nano pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.20 | $0.10 |
| Output, per 1M tokens | $1.25 | $0.625 |
| Cached input read, per 1M tokens | $0.02 | $0.01 |
| Web search, per search | $0.01 | $0.01 |
| Variant | Model id |
|---|---|
| Batch | openai/gpt-5.4-nano:batch |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 17 Mar 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0005 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0060 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0085 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.032 |
GPT-5.4 Nano specifications
| Model id | openai/gpt-5.4-nano |
|---|---|
| Version | gpt-5.4-nano-20260317 |
| Context window | 400,000 tokensAbout 300,000 English words |
| Max output | 128,000 tokens |
| Knowledge cutoff | 2025-08-31 |
| Added to catalog | 17 Mar 2026 |
| Input types | file, image, text |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | Yes |
| Content moderation | Applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for GPT-5.4 Nano yet.
Compare GPT-5.4 Nano
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.