GPT-5 Mini (batch)
by OpenAI · openai/gpt-5-mini:batch · #121 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:21 PM UTC · refreshed hourly
GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but with reduced latency and cost....
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$0.125
per 1M tokens
Output
$1.00
per 1M tokens
Blended (3:1)
$0.344
3 input : 1 output
Cache read
$0.012
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GPT-5 Mini (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.344 | $0.0138 | — |
| 50% | $0.302 | $0.008125 | −41% |
| 90% | $0.268 | $0.003625 | −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 | $0.000362 | $0.3625 |
| Document summary | 8,000 | 1,000 | $0.002 | $2.00 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00575 | $5.75 |
| Long-context analysis | 150,000 | 5,000 | $0.0238 | $23.75 |
Performance
Intelligence Index
17.4
AA composite quality
Coding Index
15.6
Math Index
90.7
Agentic Index
8.9
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 | 83.7% |
| GPQA Diamond | 82.8% |
| Humanity's Last Exam | 21.5% |
| LiveCodeBench | 83.8% |
| SciCode | 39.0% |
| AIME 2025 | 90.7% |
| IFBench | 75.4% |
| AA-LCR (Long Context Reasoning) | 72.3% |
| Terminal-Bench Hard | 33.3% |
| Terminal-Bench 2.1 | 3.7% |
| τ²-Bench (Telecom) | 68.4% |
| τ³-Bench Banking | 15.5% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,137 |
| UI components | 1,121 |
| Data viz | 1,145 |
| SVG | 1,115 |
| 3D | 1,066 |
| Game dev | 1,153 |
| Code categories | 1,130 |
| ASCII art | 1,141 |
Specs
Context window
400K
tokens
Max output
128K
tokens
Input modalities
text, image, file
Tokenizer
GPT