Embed v3 English
Embedding
Cohere's English embedding model. Strong retrieval quality for English-only RAG pipelines.
Embed v3 English 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
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 →Command A+
Frontier · 256,000 ctx
in $0.3000/Mout $1.50/M
Command A
Previous · 256,000 ctx
in $2.50/Mout $10.00/M
Command R+
Previous · 128,000 ctx
in $2.50/Mout $10.00/M
Command R
Balanced · 128,000 ctx
in $0.1500/Mout $0.6000/M
Command R7B
Compact · 128,000 ctx
in $0.0375/Mout $0.1500/M
Aya Expanse 32B
Multilingual · 128,000 ctx
in $0.5000/Mout $1.50/M
Frequently asked questions
How much does Embed v3 English cost?
Embed v3 English costs $0.1000 per million input tokens.
What is Embed v3 English's context window?
Embed v3 English supports up to 500 tokens of context in a single request.
What is Embed v3 English best for?
Cohere's English embedding model. Strong retrieval quality for English-only RAG pipelines.
Who makes Embed v3 English?
Embed v3 English is developed and served by Cohere.
