mistral-embed
Embedding
Mistral's text embedding model. Default for Mistral-aligned RAG pipelines on La Plateforme.
mistral-embed is a embedding AI model from Mistral. It costs $0.1000 per million input tokens, with a 8,000-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
8,000
tokens
Hand-maintained from Mistral'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 Mistral
See all 15 →Mistral Large 3
Frontier · 256,000 ctx
in $0.5000/Mout $1.50/M
Mistral Medium 3.5
Balanced · 256,000 ctx
in $1.50/Mout $7.50/M
Mistral Small 4
Efficient · 128,000 ctx
in $0.1500/Mout $0.6000/M
Mistral Large 2
Frontier · 128,000 ctx
in $2.00/Mout $6.00/M
Pixtral Large
Vision · 128,000 ctx
in $2.00/Mout $6.00/M
Pixtral 12B
Compact Vision · 128,000 ctx
in $0.1500/Mout $0.1500/M
Frequently asked questions
How much does mistral-embed cost?
mistral-embed costs $0.1000 per million input tokens.
What is mistral-embed's context window?
mistral-embed supports up to 8,000 tokens of context in a single request.
What is mistral-embed best for?
Mistral's text embedding model. Default for Mistral-aligned RAG pipelines on La Plateforme.
Who makes mistral-embed?
mistral-embed is developed and served by Mistral.
