The 2024-08-06 version of GPT-4o offers improved performance in structured outputs, with the ability to supply a JSON schema in the respone_format. Read more [here](https://openai.com/index/introducing-structured-outputs-in-the-api/). GPT-4…
Model details →OpenAI: GPT-4o (2024-08-06) vs Qwen: Qwen2.5 VL 72B Instruct
Qwen: Qwen2.5 VL 72B Instruct wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
Model details →Side-by-side comparison
| Capability | OpenAI: GPT-4o (2024-08-06) | Qwen: Qwen2.5 VL 72B Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 128K | 128K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $2.50 | $0.80 | 🏆 Qwen: Qwen2.5 VL 72B Instruct |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $10.00 | $1.00 | 🏆 Qwen: Qwen2.5 VL 72B Instruct |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | — | 🏆 OpenAI: GPT-4o (2024-08-06) |
| Vision input Accepts image inputs alongside text. | Yes | Yes | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is OpenAI: GPT-4o (2024-08-06) better than Qwen: Qwen2.5 VL 72B Instruct?
Qwen: Qwen2.5 VL 72B Instruct wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between OpenAI: GPT-4o (2024-08-06) and Qwen: Qwen2.5 VL 72B Instruct?
Input: $2.50 vs $0.80 per 1M tokens. Output: $10.00 vs $1.00 per 1M tokens.
What context windows do OpenAI: GPT-4o (2024-08-06) and Qwen: Qwen2.5 VL 72B Instruct support?
OpenAI: GPT-4o (2024-08-06) supports up to 128K tokens. Qwen: Qwen2.5 VL 72B Instruct supports up to 128K tokens.
Do both OpenAI: GPT-4o (2024-08-06) and Qwen: Qwen2.5 VL 72B Instruct support tool calling?
OpenAI: GPT-4o (2024-08-06): yes. Qwen: Qwen2.5 VL 72B Instruct: not advertised.