AI model comparison
GPT-5.4 Mini vs GPT-5.2-Codex
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
OpenAI
GPT-5.4 Mini
GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads.
- Input / 1M
- $0.75
- Output / 1M
- $4.50
- Context
- 400K
OpenAI
GPT-5.2-Codex
GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows.
- Input / 1M
- $1.75
- Output / 1M
- $14
- Context
- 400K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
GPT-5.4 Mini
2.8x cheaper for a typical chat
Higher intelligence score
GPT-5.2-Codex
28.5 vs 24.1 on Artificial Analysis
Larger context window
Tie
400K vs 400K tokens
Newer release
GPT-5.4 Mini
Released March 17, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
GPT-5.4 Mini24.1GPT-5.2-Codex28.5Coding index
GPT-5.4 Mini56.1GPT-5.2-CodexNot availableAgentic index
GPT-5.4 Mini17.9GPT-5.2-CodexNot availablePricing
GPT-5.4 Mini vs GPT-5.2-Codex API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | GPT-5.4 Mini | GPT-5.2-Codex |
|---|---|---|
| Input tokensPer 1M tokens | $0.75 | $1.75 |
| Output tokensPer 1M tokens | $4.50 | $14 |
| Cached input (read)Per 1M tokens | $0.08 | $0.18 |
| Cache writePer 1M tokens | Not available | Not available |
| Web searchPer request | $0.01 | $0.01 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
GPT-5.4 Mini$3.75GPT-5.2-Codex$10.50Coding task
30K in, 4K out
GPT-5.4 Mini$40.50$20.25 cachedGPT-5.2-Codex$108.50$61.25 cachedLong document summary
150K in, 2K out
GPT-5.4 Mini$121.50$20.25 cachedGPT-5.2-Codex$290.50$54.25 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | GPT-5.4 Mini | GPT-5.2-Codex |
|---|---|---|
| Context window | 400K tokens | 400K tokens |
| Max output | 128K tokens | 128K tokens |
| Input types | File, Image, Text | Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | Extra high, High, Medium, Low, None | Extra high, High, Medium, Low |
| Default reasoning effort | Medium | Medium |
| Release date | March 17, 2026 | January 14, 2026 |
Features
Supported features
API features available for each model.
| Metric | GPT-5.4 Mini | GPT-5.2-Codex |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Not supported | Not supported |
| Stop sequences | Not supported | Not supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Supported | Supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
GPT-5.4 MiniView full model details- GPT-5.4 Mini vs DeepSeek V4 Flash 0423
- GPT-5.4 Mini vs Gemini 3 Flash Preview
- GPT-5.4 Mini vs GLM 5 Turbo
- GPT-5.4 Mini vs Gemini 3.5 Flash Lite
- GPT-5.4 Mini vs Kimi K2.7 Code
- GPT-5.4 Mini vs Inkling
- GPT-5.4 Mini vs Grok 4.3
- GPT-5.4 Mini vs GPT-5.1
- GPT-5.4 Mini vs GPT-5.1-Codex
- GPT-5.4 Mini vs GPT-5 Mini
- GPT-5.4 Mini vs GLM 5V Turbo
- GPT-5.4 Mini vs GPT-5
- GPT-5.4 Mini vs Nemotron 3 Ultra
- GPT-5.4 Mini vs Claude Opus 4.1
- GPT-5.4 Mini vs o3 Pro
- GPT-5.4 Mini vs Qwen3.5 397B A17B
- GPT-5.4 Mini vs GPT-5.1-Codex-Mini
- GPT-5.4 Mini vs o3
- GPT-5.4 Mini vs o4 Mini
Our take
GPT-5.4 Mini is 2.8x cheaper for a typical chat. GPT-5.2-Codex scores higher on the Artificial Analysis Intelligence Index (28.5 vs 24.1). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is GPT-5.4 Mini or GPT-5.2-Codex cheaper?
GPT-5.4 Mini is cheaper for a typical chat (2K input tokens and 500 output tokens). GPT-5.4 Mini costs $0.75 per 1M input tokens and $4.50 per 1M output tokens, while GPT-5.2-Codex costs $1.75 per 1M input tokens and $14 per 1M output tokens.
Which has a bigger context window, GPT-5.4 Mini or GPT-5.2-Codex?
GPT-5.4 Mini supports up to 400K tokens of context, compared with 400K for GPT-5.2-Codex.
Is GPT-5.4 Mini smarter than GPT-5.2-Codex?
On the Artificial Analysis Intelligence Index, GPT-5.4 Mini scores 24.1 and GPT-5.2-Codex scores 28.5, putting GPT-5.2-Codex ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use GPT-5.4 Mini and GPT-5.2-Codex at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see GPT-5.4 Mini and GPT-5.2-Codex answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to GPT-5.4 Mini and GPT-5.2-Codex at the same time. Compare the answers side by side and keep the best one.