GPT-4o-mini vs GPT-5 Nano
API pricing, context window and capabilities for GPT-4o-mini and GPT-5 Nano, side by side. Prices are the cheapest listed serving route per 1M tokens, from LiteLLM and OpenRouter.
Verdict
computed from the published numbersGPT-5 Nano wins on price, on intelligence and on context window. Benchmark data is unavailable for one or both models.
Price
GPT-5 Nano
Terminal-Bench
Not called
Intelligence
GPT-5 Nano
Context window
GPT-5 Nano
Key takeaways
who wins on what, from the published numbersGPT-4o-mini wins
No clear edge on the tracked metrics.
GPT-5 Nano wins
- Cheaper input ($0.15 vs $0.05 /1M)
- Cheaper output ($0.60 vs $0.40 /1M)
- Larger context window (131K vs 5M)
- Higher max output (16K vs 128K)
- More serving providers (6 vs 8)
- Has reasoning mode
- Has web search
Cheaper overall
GPT-5 Nano
$0.05 + $0.40 /1M
Larger context
GPT-5 Nano
5M
More providers
GPT-5 Nano
8 providers
Pricing & specs
cheapest listed route · per 1M tokensOn-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments can be materially lower.
| GPT-4o-mini | GPT-5 Nano | |
|---|---|---|
| Input $/1M | $0.15via OpenAI | $0.05via Databricks best |
| Output $/1M | $0.60via OpenAI | $0.40via Databricks best |
| Context window | 131K | 5M best |
| Max output | 16K | 128K best |
| Serving providers | 6 | 8 best |
| Date | Released Jul 18, 2024 | Released Aug 7, 2025 |
Benchmarks
Benchmark scores, side by side| GPT-4o-mini | GPT-5 Nano | |
|---|---|---|
| Intelligence | 6.7 | 13.0 best |
| Terminal-Bench | 6% | Not available |
| GPQA Diamond | 43% | 68% best |
| Output speed | 120 t/s | 196 t/s best |
| Latency (TTFT) | 0.84s best | 66.02s |
Cost calculator
choose a serving route for each sideInput tokens / month
Output tokens / month
GPT-4o-mini
via Gmi
$1.35
GPT-5 Nano
via Databricks
$0.65
Capabilities
feature support, side by side| Feature | GPT-4o-mini | GPT-5 Nano |
|---|---|---|
| Vision | ✓ | ✓ |
| Tool use | ✓ | ✓ |
| Reasoning | — | ✓ |
| Audio | — | — |
| Prompt caching | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Web search | — | ✓ |
Related comparisons
Frequently asked questions
Which is cheaper, GPT-4o-mini or GPT-5 Nano?
GPT-5 Nano is cheaper for input ($0.15 vs $0.05 per 1M tokens) from Databricks. GPT-5 Nano is cheaper for output ($0.60 vs $0.40 per 1M tokens) from Databricks.
What is the context window difference between GPT-4o-mini and GPT-5 Nano?
GPT-4o-mini has a 131K-token context window and GPT-5 Nano has 5M tokens, so GPT-5 Nano can take a larger prompt.
How do GPT-4o-mini and GPT-5 Nano compare on benchmarks?
On the tracked benchmarks, GPT-5 Nano leads on intelligence.
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI