Mistral AI - API - verified
Mistral Embed embeddings
Mistral Embed is a current embedding model from Mistral AI, called by API as mistral-embed. It returns 1,024-dimension vectors by default and accepts up to 8,000 input tokens, for text input. The first-party list price is $0.10 per 1M input tokens.
CurrentModel id: mistral-embed
- Default dims
- 1,024
- Max input
- 8,000 tok
- Price / 1M
- $0.10
- Inputs
- Text
Dimensions
- 1,024default
Default output: 1,024 dimensions.
Pricing
- Per 1M input tokens
- $0.10
- Batch, per 1M
- Not stated
Model page lists $0.1 per 1M tokens; versioned id mistral-embed-2312; batch rate not shown in the captured pricing view.
Usage
Copied verbatim from the page linked below. Placeholders such as project ids and API keys are the source's own.
import os
from mistralai.client import Mistral
api_key = os.environ["MISTRAL_API_KEY"]
model = "mistral-embed"
client = Mistral(api_key=api_key)
embeddings_batch_response = client.embeddings.create(
model=model,
inputs=["Embed this sentence.", "As well as this one."],
)Source: docs.mistral.ai/studio/knowledge-rag/embeddings/text_embeddings
Worth knowing
Context is listed as 8k on the model page and outputs are norm 1, so cosine similarity, dot product and Euclidean distance are equivalent for retrieval and clustering.
Released . Multilingual: not stated.
FAQ
How many dimensions does Mistral Embed output?
Default output: 1,024 dimensions.
What is the max input length of Mistral Embed?
8,000 tokens per input, per Mistral AI's documentation. Longer text has to be chunked before you embed it.
How much does Mistral Embed cost?
The first-party list price is $0.10 per 1M input tokens. Model page lists $0.1 per 1M tokens; versioned id mistral-embed-2312; batch rate not shown in the captured pricing view. Source: https://docs.mistral.ai/models/mistral-embed-23-12.
What can Mistral Embed embed?
Text input, per the provider.
Sources
Last verified from the pages below.
- Mistral Embed model page - docs.mistral.ai
- Mistral text embeddings docs - docs.mistral.ai
- Mistral models overview - docs.mistral.ai
More Mistral AI embedding models
Default dimensions, max input tokens and list price per 1M tokens.
Newsletter
New models, every week
One email per week. New model releases, embedding and retrieval updates and what they mean for what you build.
Keep exploring
Model API pricing and specs
First-party prices per 1M tokens for chat and reasoning models.
Local models
Open-weight LLMs you can download and run, with sizes and licenses.
What is RAG?
Where embeddings fit in a retrieval pipeline, end to end.
Vector databases compared
Where the vectors go once you have picked a model.