GPT-5.4 Nano (batch)
OpenAI · released Mar 17, 2026
GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is designed for low-latency...
Specification
- Context window
- 400K
- Max output
- 128K
- Knowledge cutoff
- Aug 31, 2025
- Parameters
- Undisclosed
- Licence
- Proprietary
- Serving providers
- 1
- Moderated
- Yes
Intelligence
39.7
87th percentile
Coding
56.1
Coding Index
Agentic
29.7
Agentic Index
Output speed
—
Median across providers
Latency
—
Time to first token
Cost per task
$0.06
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- GPQA Diamond81.7%
- τ²-bench (Telecom)76.0%
- IFBench75.9%
- AA-LCR (long context)72.0%
- SciCode46.9%
- Terminal-Bench Hard42.4%
- Humanity's Last Exam28.3%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| GPQA Diamond | 81.7% |
| τ²-bench (Telecom) | 76.0% |
| IFBench | 75.9% |
| AA-LCR (long context) | 72.0% |
| SciCode | 46.9% |
| Terminal-Bench Hard | 42.4% |
| Humanity's Last Exam | 28.3% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GLM 5Z.ai40.6
- Qwen3.6 PlusQwen40.5
- GPT-5.4 Nano (batch)OpenAI39.7
- GPT-5.4 NanoOpenAI39.7
- Qwen3.7 PlusQwen39.4
- GLM 5 TurboZ.ai39.1
- M2.7MiniMax38.9
- Claude Opus 4.6Anthropic38.8
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GLM 5 | 40.6 |
| Qwen3.6 Plus | 40.5 |
| GPT-5.4 Nano (batch) | 39.7 |
| GPT-5.4 Nano | 39.7 |
| Qwen3.7 Plus | 39.4 |
| GLM 5 Turbo | 39.1 |
| M2.7 | 38.9 |
| Claude Opus 4.6 | 38.8 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.1
- Output / 1M tokens
- $0.625
- Cached input / 1M
- $0.01
- Blended 3:1
- $0.231
One task, estimated
$0.06
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.