Cohere
Embedding

Embed v3 Multilingual

Embedding

Multilingual embedding from Cohere, covers 100+ languages. Default for cross-lingual RAG.

Embed v3 Multilingual is a embedding AI model from Cohere. It costs $0.1000 per million input tokens, with a 500-token context window.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.1000/M
per million input tokens
OUTPUT
—
per million output tokens
BLENDED 70/30
—
unchanged since 3 May
CONTEXT
500
tokens

Hand-maintained from Cohere's published pricing; no check date on record.

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from Cohere

See all 12 →

Frequently asked questions

How much does Embed v3 Multilingual cost?

Embed v3 Multilingual costs $0.1000 per million input tokens.

What is Embed v3 Multilingual's context window?

Embed v3 Multilingual supports up to 500 tokens of context in a single request.

What is Embed v3 Multilingual best for?

Multilingual embedding from Cohere, covers 100+ languages. Default for cross-lingual RAG.

Who makes Embed v3 Multilingual?

Embed v3 Multilingual is developed and served by Cohere.

Terms used on this page