Data points: 86
The readout for GPT-5.4 and GPT-5 Codex, 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
86 data points
Includes 8 benchmark rows, 1 audit samples, and 9 provider examples.
Selection signal
Start with GPT-5.4
The charts below split 18 high-signal samples across speed, scores, and audit health.
Model compare GPT-5.4 vs GPT-5 Codexgpt-5-4-vs-gpt-5-codex | Model A GPT-5.4 | Model B GPT-5 Codex |
|---|---|---|
| Overall leader | Leading | Contender |
| Verified metric wins | 4 wins | 2 wins |
| Where it leads | Cheapest input price, Free providers, Provider coverage, Recent tests | Average speed, First-token latency |
| Model metadata | GPT-5.4 exposes 1.1M tokens; notable signals: Text input, Image input, File input, Text output. | GPT-5 Codex exposes 400K tokens; notable signals: Text input, Image input, Text output, Tool calling. |
| Developer | OpenAI | OpenAI |
| Context window | 1.1M tokens | 400K tokens |
| Max output | 128K tokens | 128K tokens |
| Released | Mar 2026 | Sep 2025 |
| Modalities | Input TextImageFile Output Text | Input TextImage Output Text |
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputText outputTool callingStructured outputsJSON modeReasoning |
| Parameters | No data | No data |
| Tokenizer | GPT | GPT |
| Knowledge cutoff | No data | 2024-09-30 |
| OpenRouter ID | openai/gpt-5.4 | openai/gpt-5-codex |
| 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 Codex |
|---|---|---|
| GPQA | 92.0%#3 | 83.7%#40 |
| SciCode | 56.6%#3 | 40.9%#41 |
| HLE | 41.6%#4 | 25.6%#27 |
| Output speed | 92.4 tok/s#56 | 170.0 tok/s#19 |
| Input price | $2.50/M#37 | $1.25/M#30 |
| Output price | $15.00/M#44 | $10.00/M#41 |
| Blended price | $5.63/M#63 | $3.44/M#58 |
| Time to first answer token | 134.24 s#111 | 11.29 s#62 |
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | GPT-5.4 | GPT-5 Codex |
|---|---|---|
钠 APIWinner: GPT-5.4 | GPT-5.4 gpt-5.4 Audit score 90 1008476100 | GPT-5 Codex gpt-5-codex No audit 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 Codex |
|---|---|---|
天宫造物50 tests | GPT-5.4 speed / latency 50 tok/s / 7305ms input / output No data | GPT-5 Codex speed / latency N/A / N/A input / output No data |
Sub2API20 tests | GPT-5.4 speed / latency 51 tok/s / 4032ms input / output No data | GPT-5 Codex speed / latency N/A / N/A input / output No data |
星见雅 API20 tests | GPT-5.4 speed / latency 49 tok/s / 5435ms input / output No data | GPT-5 Codex speed / latency N/A / N/A input / output No data |
6345ywz API15 tests | GPT-5.4 speed / latency 41 tok/s / 6581ms input / output No data | GPT-5 Codex speed / latency N/A / N/A input / output No data |
Zeabur15 tests | GPT-5.4 speed / latency 41 tok/s / 2439ms input / output No data | GPT-5 Codex speed / latency 204 tok/s / 2223ms input / output No data |
GPT-5.4 gpt-5.4 speed / latency No data input / output $0/M / $0/M | GPT-5 Codex gpt-5-codex-openai-compact speed / latency No data input / output $75.00/M / $600.00/M | |
GPT-5.4 gpt-5.4-free speed / latency No data input / output $0/M / $0/M | GPT-5 Codex gpt-5-codex speed / latency No data input / output $2.50/M / $20.00/M | |
GPT-5.4 gpt-5.4 speed / latency No data input / output $0.027/M / $0.027/M | GPT-5 Codex gpt-5-codex-openai-compact speed / latency No data input / output $10.27/M / $10.27/M | |
GPT-5.4 gpt-5.4-high speed / latency No data input / output $0.034/M / $0.205/M | GPT-5 Codex gpt-5-codex-low speed / latency No data input / output $0.034/M / $0.274/M |
This report only uses LMSpeed data for GPT-5.4 and GPT-5 Codex: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | GPT-5.4 | GPT-5 Codex |
|---|---|---|
| When to choose each model | GPT-5.4 GPT-5.4 is stronger when you prioritize Cheapest input price, Free providers, Provider coverage, Recent tests. | GPT-5 Codex GPT-5 Codex is stronger when you prioritize Average speed, First-token latency. |
TL;DR: GPT-5.4 leads across 86 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from GPT-5.4 vs GPT-5 Codex 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.
