OpenAI: GPT-4o (2024-08-06)
GPT-4o (2024-08-06) is a multimodal model from OpenAI that accepts text, images, and files as input, with a 128,000-token context window and a 16,384-token output ceiling. It supports tool use, making it suitable for agentic workflows, though it does not include a dedicated reasoning mode. At $2.50 per million input tokens and $10.00 per million output tokens, it sits at a mid-tier price point among capable frontier models. Its blended benchmark score of 22.3 across four benchmarks is modest, and the limited coverage means that score should be treated as indicative rather than definitive. Teams that need reliable multimodal input handling and tool integration without paying top-tier prices may find it a reasonable shortlist candidate, though buyers prioritizing coding or agentic tasks should compare its specific scores in those categories against newer or cheaper alternatives before committing.
- Model ID
- openai/gpt-4o-2024-08-06
- 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
- no