OpenAI: gpt-5-mini API
A high-efficiency variant of GPT-5 released in August 2025. It inherits GPT-5's native reasoning architecture but is optimized for speed and cost. Excelling in coding, logical classification, and structured data extraction, it is the most cost-effective "reasoning" small model, succeeding the previous o4-mini.
- Context window: 400,000 tokens
- Max output: 128,000 tokens
- Input: text, image
- Output: text
- Reasoning: Supported
- Tool calling: Supported
- File input: Supported
- Released: 2025-08-07
- Knowledge cutoff: 2024-05-30
Frequently Asked Questions
What is the context window of gpt-5-mini?
gpt-5-mini supports a context window of up to 400,000 tokens.
Does gpt-5-mini support function calling?
Yes. gpt-5-mini supports tool / function calling.
Does gpt-5-mini support reasoning?
Yes. gpt-5-mini is a reasoning-capable model.
What is the knowledge cutoff of gpt-5-mini?
The knowledge cutoff of gpt-5-mini is 2024-05-30.