模型详情
gpt-4o-mini-2024-07-18
GPT-4o mini is OpenAI's newest model after [GPT-4 Omni](/models/openai/gpt-4o), supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable than other recent frontier models, and more than 60% cheaper than [GPT-3.5 Turbo](/models/openai/gpt-3.5-turbo). It maintains SOTA intelligence, while being significantly more cost-effective. GPT-4o mini achieves an 82% score on MMLU and presently ranks higher than GPT-4 on chat preferences [common leaderboards](https://arena.lmsys.org/). Check out the [launch announcement](https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/) to learn more. #multimodal
模型规格
- 上下文长度
- 128K
- 最大输出
- 16.384K
- 输入/输出模态
- 文本 / 图像
- 发布日期
- 2024-07
02
API 端点
单一 MixRoute 网关，OpenAI 兼容
-
OpenAI-compatible
/v1/chat/completionsPOST
03
价格
固定费率，单位：/1M Tokens
输入
$0.1500 /1M Tokens
补全
$0.6000 /1M Tokens
缓存读取
$0.0750 /1M Tokens
05
选型摘要
快速判断是否适合你的工作负载
What is this model good for?
Cost-effective multimodal tasks at scale
Use GPT-4o mini for high-volume multimodal tasks where cost efficiency is critical. It supports text and image inputs, achieving strong benchmark scores while being over 60% cheaper than GPT-3.5 Turbo.
What should you check before using it?
Confirm performance on your specific task class
GPT-4o mini is a small model optimized for cost. Test your specific multimodal tasks to confirm the accuracy meets your requirements compared to larger models like GPT-4o.
Why use it through MixRoute?
Use the OpenAI-compatible endpoint with stable model ID
Use the confirmed compatible endpoint with model ID gpt-4o-mini through MixRoute, then run the same integration tests used for the current client.
08
Token 成本估算
基于本页价格的实时估算，非实际账单
同一前缀被重复读取的输入占比，最高 100%
单一端点，可验证的决策
使用相同的请求格式测试此模型和备用路由
从真实工作负载开始，再由质量、总成本和故障条件决定是否接入生产流量。