OpenAI: GPT-5.4 Nano
OpenAI's GPT-5.4 Nano is a versatile AI model capable of handling text, file, and image inputs within a context length of 400,000 tokens. It supports reasoning and tools, enabling complex problem-solving tasks; however, it does not provide structured output. With pricing at $0.2 per million input tokens and $1.25 per million output tokens, this model is suitable for those willing to pay for its advanced capabilities. Its blended benchmark score of 67.5 across three independent benchmarks positions it as a reliable choice, though the scores in specific areas like agentic AI remain lower. For tasks requiring robust reasoning and diverse input types, GPT-5.4 Nano could be a valuable addition to your toolkit.
Benchmark results
Independent, published benchmarks. Blended score 67.5 across 3 benchmarks, last refreshed 2026-08-02. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 63.1 |
| AI Index Coding | software engineering tasks | 92.5 |
| AI Index Agentic | multi-step tool-using tasks | 45.4 |
- Model ID
- openai/gpt-5.4-nano
- Vendor
- openai
- Released
- March 2026
- Tokenizer
- GPT
- Input Modalities
- file, image, text
- Output Modalities
- text
- Max Output
- 128,000 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- yes
What it costs in practice
Computed from the current $0.20/M input and $1.25/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.16 |
| A month of a busy support chatbot | 5M in / 2M out | $3.50 |
Strong choice for
Category rankings
Where OpenAI: GPT-5.4 Nano places across the 27 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #3 | Bulk Data LabelingData · of 25 ranked | 134 |
| #7 | Customer SupportBusiness · of 25 ranked | 133 |
| #8 | JSON ExtractionData · of 25 ranked | 146 |
| #8 | Dataset AnnotationResearch · of 25 ranked | 143 |
| #9 | Image CaptioningVision · of 25 ranked | 120 |
| #10 | Code CompletionCode · of 25 ranked | 133 |
| #10 | Short-Form SummarizationWriting · of 25 ranked | 130 |
| #10 | Email DraftingWriting · of 25 ranked | 126 |
| #10 | Language LearningEducation · of 25 ranked | 126 |
| #10 | Chat CompanionPersonal · of 25 ranked | 130 |
| #11 | Trivia & General KnowledgePersonal · of 25 ranked | 120 |
| #15 | Meeting NotesBusiness · of 25 ranked | 149 |
| #18 | OCR / Document ParsingData · of 25 ranked | 144 |
| #18 | Table Extraction from PDFsData · of 25 ranked | 144 |
| #18 | Sales / Cold EmailBusiness · of 25 ranked | 122 |
| #18 | Job Application DraftingBusiness · of 25 ranked | 122 |
| #18 | Journaling HelperPersonal · of 25 ranked | 122 |
| #18 | Recipe GenerationPersonal · of 25 ranked | 122 |
| #19 | SOP / Process DocsBusiness · of 25 ranked | 134 |
| #20 | CSV / Spreadsheet CleanupData · of 25 ranked | 151 |
| #21 | Diagram ExtractionVision · of 25 ranked | 145 |
| #21 | Real-Time ChatLatency · of 25 ranked | 117 |
| #23 | Transcript CleanupWriting · of 25 ranked | 139 |
| #23 | Resume WritingBusiness · of 25 ranked | 116 |
| #24 | Code DocumentationCode · of 25 ranked | 140 |
| #25 | Chart & Graph ReadingVision · of 25 ranked | 146 |
| #25 | Function / Tool CallingAgents · of 25 ranked | 146 |
Similar models
OpenAI: GPT-5.6 Luna Pro
OpenAI: GPT-5.6 Luna
OpenAI: GPT-5.6 Terra Pro
OpenAI: GPT-5.6 Terra
OpenAI: GPT-5.4 Mini
OpenAI: GPT-5.4
Quick answers
- How much does OpenAI: GPT-5.4 Nano cost?
- $0.20 per million input tokens and $1.25 per million output tokens.
- What is OpenAI: GPT-5.4 Nano's context window?
- 400,000 tokens, roughly 600 pages of text in a single request.
- Does OpenAI: GPT-5.4 Nano support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can OpenAI: GPT-5.4 Nano process images?
- Yes, it accepts image input.