GPT-5.2 (batch)
by OpenAI · openai/gpt-5.2:batch · #314 cheapest of 422 paid models
Prices updated Sep 20, 2026, 12:34 AM UTC · refreshed hourly
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate computation dynamically, responding quickly...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$0.875
per 1M tokens
Output
$7.00
per 1M tokens
Blended (3:1)
$2.41
3 input : 1 output
Cache read
$0.087
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GPT-5.2 (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $2.41 | $0.0963 | — |
| 50% | $2.11 | $0.0569 | −41% |
| 90% | $1.87 | $0.0254 | −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 | $0.002537 | $2.54 |
| Document summary | 8,000 | 1,000 | $0.014 | $14.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0403 | $40.25 |
| Long-context analysis | 150,000 | 5,000 | $0.1663 | $166.25 |
Performance
Intelligence Index
30.4
AA composite quality
Coding Index
—
Math Index
99
Agentic Index
—
Output speed
0 tok/s
median
Time to first token
0s
median
Time to first answer
0s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 87.4% |
| GPQA Diamond | 90.3% |
| Humanity's Last Exam | 37.7% |
| LiveCodeBench | 88.9% |
| AIME 2025 | 99.0% |
| IFBench | 75.4% |
| AA-LCR (Long Context Reasoning) | 82.7% |
| Terminal-Bench Hard | 47.0% |
| τ²-Bench (Telecom) | 84.8% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,207 |
| Web apps | 1,101 |
| Full-stack | 1,052 |
| Mobile apps | 1,123 |
| Android native | 1,073 |
| UI components | 1,205 |
| Data viz | 1,216 |
| SVG | 1,162 |
| 3D | 1,108 |
| Game dev | 1,219 |
| Godot game dev | 1,142 |
| Code categories | 1,185 |
| ASCII art | 1,171 |
Specs
Context window
400K
tokens
Max output
128K
tokens
Input modalities
file, image, text
Tokenizer
GPT