GPT-4.1 Nano pricing & benchmarks
Released Apr 14, 2025 · served by 2 providers
What GPT-4.1 Nano is
For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...
- Model ID:
openai/gpt-4.1-nano - Modality: text+image+file->text
- Knowledge cutoff: 2024-06-30
- Tool calling: supported · Structured output: supported
Providers and prices for GPT-4.1 Nano
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| OpenAIcheapest | $0.100 | $0.400 | 1.0M | — | 99.2% | — |
| Azure | $0.110 | $0.440 | 1.0M | — | 100.0% | — |
GPT-4.1 Nano benchmark results
Design Arena head-to-head results, as reported through the OpenRouter model API.
| Category | Arena | Rank | Elo | Win rate |
|---|---|---|---|---|
| 3d | models | #97 | 982 | 46% |
| gamedev | models | #97 | 1027 | 49.6% |
| uicomponent | models | #100 | 953 | 43.9% |
| codecategories | models | #105 | 993 | 47.3% |
| website | models | #106 | 998 | 48.1% |
| dataviz | models | #107 | 921 | 41.1% |
Cheaper models in the same class
Models scoring within 4 points of GPT-4.1 Nano on the Intelligence Index, but with a lower output price.
FAQ
How much does the GPT-4.1 Nano API cost?
$0.100 per 1M input tokens and $0.400 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.22.
Is GPT-4.1 Nano free?
No. It is a paid model starting at $0.100 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for GPT-4.1 Nano?
OpenAI at $0.100 input / $0.400 output per 1M tokens.
Can I self-host GPT-4.1 Nano?
No. GPT-4.1 Nano is closed-weight and only available through hosted APIs.