Back to Models

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.

Context Length
8K
Max Output
--
Input Price
$0.120/ 1M tokens

Modalities

textimageembedding

Pricing Breakdown

TypeRate
Input$0.120 / 1M tokens

Supported Parameters

input_typedimensionstruncate

API Usage Examples

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."}
    ]
  }'