Skip to content
AI Model Radar

GPT-4.1-mini

gpt-4.1-mini
OpenAI · chat · api · seen 11m ago
GA Alert me on changes
Context
1M
Max output
33K
Input $/1M
$0.75
Output $/1M
$4.50
Modalities
text
Released
10 Apr 2025
AI summary
● machine-written

OpenAI releases GPT-4.1-mini for coding and subagent tasks

GPT-4.1-mini is a compact language model from OpenAI optimized for coding, computer use, and subagents. It supports a 1M-token context window with up to 33K tokens of output, accessible via API. The model emphasizes cost efficiency relative to larger variants.

What's new
  • Supports vision, function calling, prompt caching, and structured output
  • 1M-token context window with 33K max output tokens
  • Available via OpenAI API with standard and cached input pricing
Best for
Coding and code generation tasksComputer use automationSubagent deploymentCost-sensitive applications requiring competitive performance
Sources

Source: https://platform.openai.com/docs/models