模型详情
text-embedding-3-small
text-embedding-3-small is OpenAI's improved, more performant version of the ada embedding model. Embeddings are a numerical representation of text that can be used to measure the relatedness between two pieces of text. Embeddings are useful for search, clustering, recommendations, anomaly detection, and classification tasks.
模型规格
- 上下文长度
- 8.191K
- 最大输出
- –
- 输入/输出模态
- 文本
- 发布日期
- 2025-10
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
$0.0200 /1M Tokens
补全
$0.0200 /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?
Efficient embedding model for cost-sensitive workloads
Use text-embedding-3-small for embedding tasks where cost and speed are more important than maximum accuracy. It is an improved version of the ada embedding model.
What should you check before using it?
Compare accuracy vs text-embedding-3-large
text-embedding-3-small trades some accuracy for lower cost and faster performance. Test your specific use case to confirm the accuracy meets your requirements.
Why use it through MixRoute?
Use the compatible endpoint with stable model ID
Use the confirmed compatible endpoint with model ID text-embedding-3-small 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。