OpenAI: GPT-4o-mini (2024-07-18)
GPT-4o-mini is a multimodal model from OpenAI that accepts text, images, and files as input. It supports a 128,000-token context window and can return up to 16,384 tokens per response. Tool use is supported, which makes it suitable for agentic workflows, but it does not include a dedicated reasoning mode and structured output support is unconfirmed. At $0.15 per million input tokens and $0.60 per million output tokens, it sits at the budget end of the OpenAI lineup, making it a reasonable candidate for high-volume or cost-sensitive applications. However, its benchmark standing is currently unproven, with only a single aider_polyglot score of 3.6 on record and no broader independent coverage. Buyers who need a cost-efficient multimodal model with tool support may find it worth testing, but should run their own evals before committing to it for production use.
- Model ID
- openai/gpt-4o-mini-2024-07-18
- Vendor
- openai
- Tokenizer
- GPT
- Input Modalities
- text, image, file
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- yes