Cohere makes Embed Multilingual Light v3.0 Image, a proprietary embedding model. It takes text as input and produces vector embeddings as output.
Input
Output
Context
512
Max Output
n/a
Parameters
-
Input Modalities
Output Modalities
Some values come from web research and may be incorrect. Report incorrect data
None the catalog can show from stated facts or measured scores.
None the catalog can show from stated facts or measured scores.
Specification sources
As of Nov 11, 2026.
Answered from the facts on this page, with their sources.
Embed Multilingual Light v3.0 Image has a context window of 512 tokens (source: Web research). A provider may serve less; Inferbase routes on what each provider serves.
No. Embed Multilingual Light v3.0 Image is not released under an open license. Use it through Cohere's API or a provider that serves it.
Cohere has not published a parameter count for Embed Multilingual Light v3.0 Image. The catalog does not estimate undisclosed sizes.
Embed Multilingual Light v3.0 Image accepts Text and produces Embedding. The Capabilities card lists the API features it supports, such as function calling and structured output.
No benchmark source has published a result for Embed Multilingual Light v3.0 Image yet, so it is shown as unmeasured, not estimated.
Not on Inferbase Managed today. Add your own provider key or endpoint that serves Embed Multilingual Light v3.0 Image, and Inferbase runs it on your account with the same routing and logs.
Cohere does not publish open weights for Embed Multilingual Light v3.0 Image, so it runs through an API: Cohere's own, or Inferbase where it is served.
Start on the free plan with 5,000 requests a month, no card required.