Model positioning
GPT-4.1 mini is a smaller, faster model in the GPT-4.1 family, intended for low-latency general-purpose API applications. It focuses on instruction following, tool calling, coding, and long-context understanding, without using a separate reasoning step. (developers.openai.com)
Capabilities and uses
- Supports text input and output, as well as image input; supports function calling, structured outputs, and streaming. (developers.openai.com)
- The context window is 1,047,576 tokens, and the maximum output is 32,768 tokens; the knowledge cutoff date is June 1, 2024. (developers.openai.com)
- Can be used for coding assistance, information extraction from long documents, image understanding, customer service, and agent applications that require tool calling. (openai.com)
Limitations and status
- Does not support native audio or video input or output; images are supported as input only. The model may still produce errors, and important results should be verified. (developers.openai.com)
- As of November 18, 2026, the snapshot
gpt-4.1-mini-2025-04-14has been officially marked as deprecated and is scheduled to shut down on January 14, 2027; the replacement model listed in the official deprecation announcement isgpt-6-luna. (developers.openai.com)
API pricing
As of November 18, 2026, OpenAI's official standard base text token prices are in US dollars (USD), per million tokens: input $0.40, cache-eligible input $0.10, and output $1.60. Tool calling and other services may incur additional charges; terms or prices for other platforms, fine-tuning, and batch processing may differ. Official model pricing; official API pricing. (developers.openai.com)
Release and official sources
- Release date: April 14, 2025.
- API model ID:
gpt-4.1-mini; the dated snapshot isgpt-4.1-mini-2025-04-14. - Official OpenAI release announcement; model documentation; deprecation announcement. (openai.com)