OpenAI

gpt-4.1-nano

openai/gpt-4.1-nano
Context

64K

Input

text, image

Output

text

Tool calling

Supported

About this model

GPT-4.1 Nano is a highly efficient 100B-parameter variant optimized for edge deployment and mobile devices. Features 128 experts with aggressive pruning and INT8 quantization, delivering 60% of GPT-4.1's capability while consuming 75% less power.

Compare Text Models

Input modalities

text

Accepted as model input

image

Accepted as model input

Providers

Available routing options for this model through OneInfer.

OpenAI
Available

Input tokens

$0.100 / 1M tokens

Output tokens

$0.400 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.100 / 1M tokens
Output tokens$0.400 / 1M tokens
Cached input tokens$0.025 / 1M tokens

Performance

Published evaluation results associated with this model.

Edge Performance

Tokens/Watt1420
Latency (mobile)0.8
Cold Start Time1.2
Memory Bandwidth68.4

Core Capabilities

MMLU76.8
TruthfulQA79.3
GSM8K88.5

Efficiency Metrics

Tokens/$ (input)112.6
Tokens/$ (output)84.3
VRAM Utilization36.8
Power Consumption (W)18.4

Mobile Optimization

Android Compatibility99.2
iOS On-Device97.8
Model Shrink Factor4.2
Background Operation92.1

API example

Refer Documentation
curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4.1-nano",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'