# OpenAI: GPT-4.1 Nano

openai/gpt-4.1-nano

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 token context window, and scores 80.1% on MMLU, 50.3% on GPQA, and 9.8% on Aider polyglot coding – even higher than GPT‑4o mini. It’s ideal for tasks like classification or autocompletion.

by [OpenAI](/content/openai/index.html)

**Input type**
**Output type**
**Publish time**
2025-04-14

## Recent activity on GPT-4.1 Nano

**Tokens processed per day**

## Throughput

| Providers | Min (tokens/s) | Max (tokens/s) | Avg (tokens/s) |
| --- | --- | --- | --- |
| Azure | 5.9 | 61.59 | 25.16 |
| OpenAI | 1.85 | 1.85 | 1.85 |

## First Token Latency

**(ms)**

| Providers | Min (ms) | Max (ms) | Avg (ms) |
| --- | --- | --- | --- |
| Azure | 643 | 1692 | 999.45 |
| OpenAI | 599 | 599 | 599.00 |

## Uptime stats for GPT-4.1 Nano

Uptime stats for GPT-4.1 Nano across all providers

**Uptime**

| Providers | Uptime | Recent uptime |
| --- | --- | --- |
| Azure | 100.00% | Apr 30, 2026 6:00 PM |
| OpenAI | 100.00% | Apr 30, 2026 6:00 PM |

**Price**

**Input**  
$ 0.1/ M tokens  
**Output**  
$ 0.4/ M tokens  
**Cache read**  
$ 0.025/ M tokens

**Model limitation**  
**Context**  
1.05M  
**Max output**  
32.77K

**Supported Parameters**  
- max_completion_tokens  
- temperature  
- top_p  
- frequency_penalty  
- presence_penalty  
- seed  
- logit_bias  
- logprobs  
- top_logprobs  
- response_format  
- stop  
- tools  
- tool_choice  
- parallel_tool_calls

## Sample code and API for GPT-4.1 Nano

ZenMux normalizes requests and responses across providers for you.

**OpenAI: Python-SDK**  
```python
from openai import OpenAI

client = OpenAI(
  base_url="https://zenmux.ai/api/v1",
  api_key="<ZENMUX_API_KEY>",
)

# Chat Completion
completion = client.chat.completions.create(
  model="openai/gpt-4.1-nano",
  messages=[\
    {\
      "role": "user",\
      "content": "What is the meaning of life?"\
    }\
  ]
)
print(completion.choices[0].message.content)
```