Data points: 80
The readout for GPT-5.4 and GPT-5 Nano, before the detailed comparison sheet.
Decision read
GPT-5.4
GPT-5.4 currently has the stronger profile, with verified wins split 4 to 2.
Evidence depth
80 data points
Includes 8 benchmark rows, 0 audit samples, and 7 provider examples.
Selection signal
Start with GPT-5.4
The charts below split 15 high-signal samples across speed, scores, and audit health.
Model compare GPT-5.4 vs GPT-5 Nanogpt-5-4-vs-gpt-5-nano | Model A GPT-5.4 | Model B GPT-5 Nano |
|---|---|---|
| Overall leader | Leading | Contender |
| Verified metric wins | 4 wins | 2 wins |
| Where it leads | First-token latency, Free providers, Provider coverage, Recent tests | Cheapest input price, Average speed |
| Model metadata | GPT-5.4 exposes 1.1M tokens; notable signals: Text input, Image input, File input, Text output. | GPT-5 Nano exposes 400K tokens; notable signals: Text input, Image input, File input, Text output. |
| Developer | OpenAI | OpenAI |
| Context window | 1.1M tokens | 400K tokens |
| Max output | 128K tokens | No data |
| Released | Mar 2026 | Aug 2025 |
| Modalities | Input TextImageFile Output Text | Input TextImageFile Output Text |
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
| Parameters | No data | No data |
| Tokenizer | GPT | GPT |
| Knowledge cutoff | No data | 2024-05-31 |
| OpenRouter ID | openai/gpt-5.4 | openai/gpt-5-nano |
| References | No data | No data |
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
| Metric | GPT-5.4 | GPT-5 Nano |
|---|---|---|
| GPQA | 92.0%#3 | 67.6%#86 |
| Input price | $2.50/M#37 | $0.050/M#3 |
| SciCode | 56.6%#3 | 36.6%#69 |
| HLE | 41.6%#4 | 8.2%#71 |
| Output price | $15.00/M#44 | $0.400/M#6 |
| Blended price | $5.63/M#63 | $0.138/M#7 |
| Output speed | 92.4 tok/s#56 | 142.3 tok/s#33 |
| Time to first answer token | 134.24 s#111 | 81.19 s#104 |
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-5.4 | GPT-5 Nano |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | GPT-5.4 | GPT-5 Nano |
|---|---|---|
Sub2API20 tests | GPT-5.4 speed / latency 51 tok/s / 4032ms input / output No data | GPT-5 Nano speed / latency N/A / N/A input / output No data |
Fengsili API10 tests | GPT-5.4 speed / latency 88 tok/s / 6075ms input / output No data | GPT-5 Nano speed / latency N/A / N/A input / output No data |
Omini Api10 tests | GPT-5.4 speed / latency 51 tok/s / 1443ms input / output No data | GPT-5 Nano speed / latency N/A / N/A input / output No data |
Sub2API10 tests | GPT-5.4 speed / latency 54 tok/s / 1369ms input / output No data | GPT-5 Nano speed / latency N/A / N/A input / output No data |
Sub2API10 tests | GPT-5.4 speed / latency 51 tok/s / 1093ms input / output No data | GPT-5 Nano speed / latency N/A / N/A input / output No data |
GPT-5.4 gpt-5.4-free speed / latency No data input / output $0/M / $0/M | GPT-5 Nano gpt-5-nano-minimal speed / latency No data input / output $0.100/M / $0.800/M | |
GPT-5.4 gpt-5.4-low speed / latency No data input / output $0.103/M / $0.616/M | GPT-5 Nano gpt-5-nano-2025-08-07 speed / latency No data input / output $0.0021/M / $0.016/M |
This report only uses LMSpeed data for GPT-5.4 and GPT-5 Nano: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | GPT-5.4 | GPT-5 Nano |
|---|---|---|
| When to choose each model | GPT-5.4 GPT-5.4 is stronger when you prioritize First-token latency, Free providers, Provider coverage, Recent tests. | GPT-5 Nano GPT-5 Nano is stronger when you prioritize Cheapest input price, Average speed. |
TL;DR: GPT-5.4 leads across 80 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from GPT-5.4 vs GPT-5 Nano into nearby model comparisons with enough verified LMSpeed data.
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
