GPT-5 Nano
by OpenAI · openai/gpt-5-nano · #42 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:41 AM UTC · refreshed hourly
GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$0.05
per 1M tokens
Output
$0.40
per 1M tokens
Blended (3:1)
$0.137
3 input : 1 output
Cache read
$0.0050
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for GPT-5 Nano with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.137 | $0.0055 | — |
| 50% | $0.121 | $0.00325 | −41% |
| 90% | $0.107 | $0.00145 | −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 | $0.000145 | $0.145 |
| Document summary | 8,000 | 1,000 | $0.0008 | $0.8 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0023 | $2.30 |
| Long-context analysis | 150,000 | 5,000 | $0.0095 | $9.50 |
Performance
Intelligence Index
19.9
AA composite quality
Coding Index
—
Math Index
83.7
Agentic Index
—
Output speed
177 tok/s
median
Time to first token
87.29s
median
Time to first answer
87.29s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 78.0% |
| GPQA Diamond | 67.6% |
| Humanity's Last Exam | 8.2% |
| LiveCodeBench | 78.9% |
| SciCode | 36.6% |
| AIME 2025 | 83.7% |
| IFBench | 67.6% |
| AA-LCR (Long Context Reasoning) | 41.7% |
| Terminal-Bench Hard | 12.1% |
| τ²-Bench (Telecom) | 36.5% |
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,129 |
| UI components | 1,109 |
| Data viz | 1,096 |
| 3D | 1,023 |
| Game dev | 1,104 |
| Code categories | 1,118 |
Specs
Context window
400K
tokens
Max output
128K
tokens
Input modalities
text, image, file
Tokenizer
GPT