返回模型列表

Cohere Embed V4

coherecohere/embed-v4

Multilingual multimodal embedding model capable of transforming images, texts, and interleaved content into vector representations. State-of-the-art performance with byte/binary quantization and matryoshka embeddings for compression.

上下文长度
8K
最大输出
--
输入价格
$0.120每百万 Tokens

模态能力

文本图像embedding

价格明细

类型费率
输入$0.120 每百万 Tokens

支持参数

input_typedimensionstruncate

API 使用示例

cURL
curl https://api.therouter.ai/v1/chat/completions   -H "Content-Type: application/json"   -H "Authorization: Bearer $THE_ROUTER_API_KEY"   -d '{
    "model": "cohere/embed-v4",
    "messages": [
      {"role": "user", "content": "Summarize the key points from this input."}
    ]
  }'