Embed 4
Cohere
📐 Embedding
Cohere's most performant multimodal embedding model. Generates 1536-dimensional vectors from text or images. Supports Matryoshka embeddings (256/512/1024/1536 dimensions), 128K context, and 100+ languages.
Specifications
Context Window128,000 tokens
ModalitiesInput: text, image · Output: embedding
FeaturesTools: No Streaming: No
Pricing
Included with plan
More from Cohere
Command A Reasoning
Cohere’s first reasoning model, able to ‘think’ before generating an output in a way that allows it to perform well in certain kinds of nuanced problem-solving
Command A Vision
Cohere’s first multimodal model capable of understanding and interpreting visual data alongside text.
Command A
Cohere's most performant model, excelling at tool use, agents, RAG, and multilingual tasks. Command A offers a 256K context window, high throughput, and efficie
Command R+
Command R+ is an instruction-following conversational model that performs language tasks at a higher quality, more reliably, and with a longer context than prev