OpenAI: GPT-5.4 Nano
GPT-5.4 Nano is a model from OpenAI that accepts text, image, and file inputs and returns text. It offers a 400,000-token context window with up to 128,000 tokens of output, which leaves room for long documents or large batches of material in a single request. It supports tool calling and reasoning; the available data does not confirm structured output support, so teams that depend on strict schemas should verify that before committing. At $0.20 per million input tokens and $1.25 per million output tokens, it suits cost-sensitive workloads that still need tools and long context. Its blended score of 68.1 rests on only three benchmarks, so treat its standing as provisional. Within that set the profile is uneven: 92.5 on the coding index, 63.1 on the general index, and 45.4 on the agentic index. Shortlist it for budget coding tasks, but test it carefully before using it for multi-step agent work.
Benchmark results
Independent, published benchmarks. Blended score 68.1 across 3 benchmarks, last refreshed 2026-11-08. 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 |
Category rankings
Where OpenAI: GPT-5.4 Nano places across the 11 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #7 | Bulk Data LabelingData · of 25 ranked | 134 |
| #10 | Customer SupportBusiness · of 25 ranked | 133 |
| #12 | JSON ExtractionData · of 25 ranked | 146 |
| #12 | Short-Form SummarizationWriting · of 25 ranked | 130 |
| #12 | Email DraftingWriting · of 25 ranked | 126 |
| #12 | Language LearningEducation · of 25 ranked | 126 |
| #12 | Chat CompanionPersonal · of 25 ranked | 130 |
| #12 | Dataset AnnotationResearch · of 25 ranked | 143 |
| #14 | Image CaptioningVision · of 25 ranked | 120 |
| #15 | Code CompletionCode · of 25 ranked | 133 |
| #16 | Trivia & General KnowledgePersonal · of 25 ranked | 120 |
Similar models
OpenAI: GPT-6.1 Terra Pro
OpenAI: GPT-6.1 Terra Pro (batch)
OpenAI: GPT-6.1 Terra
OpenAI: GPT-6.1 Terra (batch)
OpenAI: GPT-6.1 Sol Pro
OpenAI: GPT-6.1 Sol Pro (batch)
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.