OpenAI

gpt-4.1-mini

openai/gpt-4.1-mini
Context

262144

Input

text, image

Output

text

Tool calling

Supported

About this model

GPT-4.1 Mini is a distilled 400B-parameter version of GPT-4.1 optimized for cost-efficient deployment. Features the same 256-expert MoE architecture with selective expert activation, delivering 80% of GPT-4.1's capability at 30% of the inference cost.

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

$0.400 / 1M tokens

Output tokens

$1.600 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.400 / 1M tokens
Output tokens$1.600 / 1M tokens
Cached input tokens$0.100 / 1M tokens

Performance

Published evaluation results associated with this model.

Enterprise Applications

Business Analyst Sim88.2
Financial Report Accuracy90.7
Legal Contract Review83.9

Efficiency Metrics

Tokens/$ (input)38.4
Tokens/$ (output)25.2
Latency (complex query)0.6
VRAM Utilization142.5

Core Capabilities

MMLU82.4
TruthfulQA84.1
GSM8K92.7

Tool Integration

API Call Success92.3
Data Extraction Accuracy89.6
Spreadsheet Automation86.4

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-mini",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'