模型详情
gpt-4-turbo
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to December 2023.
模型规格
- 上下文长度
- 128K
- 最大输出
- 4.096K
- 输入/输出模态
- 文本 / 图像
- 发布日期
- 2024-04
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
$10.0000 /1M Tokens
补全
$30.0000 /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?
Vision-capable GPT-4 with JSON mode and function calling
Use GPT-4 Turbo for tasks requiring vision capabilities, JSON mode, and function calling. It is the next generation of GPT-4 with training data up to December 2023.
What should you check before using it?
Consider GPT-4o for better speed and cost
GPT-4o offers better performance at lower cost. Test your vision and function calling tasks to determine if GPT-4 Turbo is still the right choice.
Why use it through MixRoute?
Use the OpenAI-compatible endpoint with stable model ID
Use the confirmed compatible endpoint with model ID gpt-4-turbo through MixRoute.
08
Token 成本估算
基于本页价格的实时估算，非实际账单
此模型没有缓存读取价格，不计算缓存费用
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。