GPT-5.2-Codex
by OpenAI · openai/gpt-5.2-codex · #281 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$1.75
per 1M tokens
Output
$14.00
per 1M tokens
Blended (3:1)
$4.81
3 input : 1 output
Cache read
$0.175
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GPT-5.2-Codex with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $4.81 | $0.1925 | — |
| 50% | $4.22 | $0.1138 | −41% |
| 90% | $3.75 | $0.0508 | −74% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.005075 | $5.07 |
| Document summary | 8,000 | 1,000 | $0.028 | $28.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0805 | $80.50 |
| Long-context analysis | 150,000 | 5,000 | $0.3325 | $332.50 |
Performance
Intelligence Index
40.1
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
162 tok/s
median
Time to first token
1.41s
median
Time to first answer
1.41s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| GPQA Diamond | 89.9% |
| Humanity's Last Exam | 33.5% |
| SciCode | 54.6% |
| IFBench | 77.6% |
| AA-LCR (Long Context Reasoning) | 75.7% |
| Terminal-Bench Hard | 37.1% |
| τ²-Bench (Telecom) | 92.1% |
Design Arena Elo
| Category | Elo |
|---|---|
| Web apps | 1,110 |
| Full-stack | 1,050 |
| Mobile apps | 1,165 |
| Android native | 1,176 |
| Godot game dev | 1,142 |
Specs
Context window
400K
tokens
Max output
128K
tokens
Input modalities
text, image
Tokenizer
GPT