Text Embedding 3 Small
text-embedding-3-smallCompare text-embedding-3-small API pricing, supported endpoints, capabilities and access options on Modelsell.
- Starting price
- View full pricing
- Context
- 8.2K
- Maximum input window
- Modalities
- →
Pricing by Supplier
| Input/ 1M tokens |
|---|
$0.012 |
| Input/ 1M tokens |
|---|
$0.012 |
Capabilities / Supported modalities
Provider & data privacy
BPE (vendor-specific)Performance
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·Text Embedding 3 Small
This model is not included in the current benchmark snapshot.
Missing models or measurements are not zero scores.
Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.
About Text Embedding 3 Small
text-embedding-3-small 适合把大量文本变成可按含义检索的索引。文章标题、商品说明、客服问题和知识库段落都可以生成向量，再通过相似度找到相关内容。它侧重轻量和成本效率，适合经常新增资料或需要大量查询的应用。
例如用户输入“怎么让账号更安全”，系统可以召回介绍双重验证和登录保护的内容，而不必要求查询与文档使用完全相同的词。也可以用向量寻找相似工单、推荐相关文章，或对大量反馈做聚类，再由人工为类别命名。
默认输出为 1,536 维，可以用 dimensions 调整为更短的向量。索引库和查询端必须采用相同的模型、维度与预处理规则；改变设置后，旧向量不能直接混用。选择配置时，应使用真实问题检查召回质量，同时比较存储与检索开销。
长文本宜按主题分块，保留标题、原文和业务标识。检索时还需结合租户、权限、时间等过滤条件；向量相似并不代表内容有权访问，也不保证就是最终答案。这个模型返回数值向量，问答应用需要在召回资料后继续组织文字回答。
Use cases and prompting
文章推荐可以这样接入：为文章标题与摘要生成向量，保存文章 ID；用户阅读一篇文章后，用其向量检索相关内容，再按时间、类别或业务规则过滤排序。
示例输入文本：“为账号开启双重验证，并管理可信设备。”查询文本：“怎样防止别人登录我的账号？”直接提交文本，无需写聊天提示词。
检索效果怎样评估？准备真实查询和应召回的文档，比较分块、维度和过滤设置。更换模型或 dimensions 后重建索引，查询与文档保持一致。
API access
API documentation
text-embedding-3-smallUse the linked documentation for model-specific request parameters and examples.
Authentication
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
Rate limits
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| Azure | Unlimited | Unlimited | Unlimited |
| OpenAI | Unlimited | Unlimited | Unlimited |
No restriction
Frequently asked questions about text-embedding-3-small
What is text-embedding-3-small?
Compare text-embedding-3-small API pricing, supported endpoints, capabilities and access options on Modelsell.
How do I call text-embedding-3-small?
Create an API key with access to text-embedding-3-small, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
How is text-embedding-3-small priced?
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
What is the context window of text-embedding-3-small?
The model catalog lists a context window of 8192 tokens. Check the selected endpoint for request limits.
How should I evaluate text-embedding-3-small for my project?
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.