Amazon Nova Multimodal Embeddings
Amazon 的向量模型，可将文本、图像和视频转换为向量表示，用于搜索和检索场景。
规格
- 上下文
- —
- 最大输出
- —
- 输入价
- $0.135/ 百万 Token
- 输出价
- —
- 发布日期
- 2025-10-28
上下文
- 官方未公布
价格 · USD / 百万 Token
- 输入
- $0.135
- 输出
- —
- 缓存读取
- —
- 缓存写入
- —
输入输出
- 输入
- 文本图像音频视频文档
- 输出
- 向量
API
- 接口类型
思考
- 支持思考
- 不支持
源信息
- 状态
- 可用
- 发布日期
- 2025-10-28
- 知识截止
- —
能力
- 官方未公布
调用方式
1 个 Provider
amazon-bedrockmodel = amazon.nova-2-multimodal-embeddings-v1:0
embeddings
POSThttps://bedrock-runtime.us-east-1.amazonaws.com/model/{modelId}/invoke
JSON
标准格式
{
"id": "nova-multimodal-embeddings",
"object": "model",
"created": 1761609600,
"owned_by": "amazon",
"name": "Amazon Nova Multimodal Embeddings",
"api": {
"types": [
"embeddings"
]
},
"limits": {
"context": null,
"input": null,
"output": null
},
"modalities": {
"input": [
"text",
"image",
"audio",
"video",
"document"
],
"output": [
"embedding"
]
},
"reasoning": {
"supported": false,
"efforts": []
},
"pricing": {
"currency": "USD",
"unit": "1M_tokens",
"input": 0.135,
"output": null,
"cache_read": null,
"cache_write": null
},
"features": [],
"info": {
"status": "active",
"release_date": "2025-10-28",
"knowledge_cutoff": null,
"description": "Amazon's embedding model that converts text, images, and video into vector representations for search and retrieval use cases.",
"docs": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-amazon-amazon-nova-multimodal-embeddings.html",
"verified_at": "2026-10-10"
}
}官方来源
3