GPT-5.4 Mini
GPT-5.4 Mini 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 $0.75 per 1M input tokens and $4.50 per 1M output tokens. It accepts text, images and files and produces text. Typical uses: working with long documents, answering questions about images and generating and reviewing code.
Price checked ยท source: OpenRouter
What GPT-5.4 Mini is
OpenAI GPT-5.4 Mini is a text-generating model that accepts text, images and files. Its listed capabilities include reasoning and coding, and it supports tools, structured outputs and response formats. The model produces text; the catalog does not list image generation or audio input or output. GPT-5.4 Mini is described as a faster, more efficient model for high-throughput workloads, bringing the core capabilities of GPT-5.4 to that setting.
The model has a context length of 400,000 tokens and a maximum output of 128,000 tokens. This gives it room to process lengthy text or file-based material, or to work with text alongside image inputs within a single context. Its text output can be used for responses and generated content, while structured outputs and response-format support allow the output to follow a specified format. Tool support is available for workflows that use tools, though the catalog does not specify particular tools or how they are used. The listed reasoning and coding capabilities make it suitable for tasks that involve working through questions or producing code. Its combination of text, image and file inputs, long context, and text output supports document work, image-related prompts, and other text-centered tasks. The catalog does not specify particular supported file types or image formats.
Key features
- Accepts text, image and file inputs and produces text
- Has a 400,000-token context length
- Supports reasoning and tool use
- Supports structured outputs and response formats
- Allows up to 128,000 output tokens
Typical uses
- Working with long documents
- Answering questions about images
- Generating and reviewing code
- Producing structured text
- Reasoning through text-based tasks
GPT-5.4 Mini pricing
US dollars, list price through OpenRouter.
| Item | Standard | Batch |
|---|---|---|
| Input, per 1M tokens | $0.75 | $0.375 |
| Output, per 1M tokens | $4.50 | $2.25 |
| Cached input read, per 1M tokens | $0.075 | $0.0375 |
| Web search, per search | $0.01 | $0.01 |
| Variant | Model id |
|---|---|
| Batch | openai/gpt-5.4-mini: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 | $0.0017 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.022 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.032 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.119 |
GPT-5.4 Mini specifications
| Model id | openai/gpt-5.4-mini |
|---|---|
| Version | gpt-5.4-mini-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 Mini yet.
Compare GPT-5.4 Mini
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.