GPT-5 Mini

GPT-5 Mini is a small model from OpenAI for responsive agents, coding help, and everyday automation. It is the first version of the gpt-mini line in the registry. It has a context window of 400000 tokens and a max output of 128000 tokens. Price starts at $0.04 per million input tokens and $0.29 per million output tokens, with cached input at $0.022 per million tokens. Weights are not open. It accepts image and text inputs, returns text, and supports reasoning mode and tool calling. Knowledge cutoff is 2024-05-30. It is served by 31 hosts.

First version of its line in the registry.

Range across the hosts that serve it: up to $0.45 per 1M input tokens.

• ·400k token context window
• ·128k max output tokens
• ·Supports reasoning mode and tool calling
• ·Accepts image and text inputs
• ·Low price from $0.04 per million input tokens

• Reach for it for building responsive agents
• Reach for it for coding help and automation
• Reach for it for tasks needing long context

31 hosts serve this model at the price above · the maker's documentation

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window size?

The context window is 400000 tokens.

Does it support image inputs?

Yes, it accepts image and text inputs, and returns text.

Are the weights open?

No, the weights are not open.