All models
Mistral AI
Mistral Embed
Mistral's straightforward hosted text embedding model for semantic search, clustering, classification, and RAG.
Plain-English overview
What Mistral Embed actually is
Mistral Embed converts single or batched text inputs into 1,024-dimensional vectors through Mistral's Embeddings API. Its simple fixed-size output and published token price make it an approachable option for conventional text retrieval.
The model is narrower than newer multimodal or document-aware alternatives: applications handle parsing, chunking, query-versus-document strategy, and storage. That simplicity can be useful when the ingestion pipeline already owns those decisions.
Good fit for
- Text-only semantic search
- Mistral-centered RAG applications
- Teams that want a simple fixed-dimension endpoint
Category comparison
The facts that matter for embeddings models
These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.
- Embedding price
- $0.10 / 1M tokensCurrent provider price per million input tokens or the closest published billing unit.
- Input capacity
- 8K tokensMaximum content accepted in one embedding input, using the provider's documented token basis.
- Vector dimensions
- 1,024Supported output sizes; smaller vectors reduce storage while larger vectors may preserve more information.
- Accepted inputs
- TextText, code, image, audio, video, PDF, or document-aware input supported by the endpoint.
- Retrieval controls
- Single or batched inputs; application handles chunkingQuery/document modes, task types, truncation, chunking, or other controls that shape vectors for retrieval.
- Where it runs
- Mistral hosted API and StudioDirect API, cloud marketplace, private deployment, or self-hosted route documented by the provider.
Pricing & comparisons
Estimate your cost
Set your usage. Your estimate updates as you type.
Assumes 600 tokens per page, processed separately. Actual token counts vary. This covers embedding only, not storage, search, or generated answers.
Mistral Embed
Mistral AI
Estimated total (USD)
For the usage above · USD · API pricing, not a subscription
- Input tokens
- $0.10 per 1M tokens
How this estimate works
Estimates exclude taxes, tools, cache storage/writes, free allowances and custom discounts. Image estimates cover output only, not prompt or reference-image charges. Quality modes differ by model. Unlisted settings are not treated as free.
API and provider access
Where to get Mistral Embed
Availability
Regions and access stage
Generally available through Mistral's hosted Embeddings API and Studio.
Mistral's standard and optional regional-inference routes have model-specific coverage; verify Embed support for an EU- or US-pinned endpoint.
Check live availabilityData and training
The route matters.
Mistral says API data is not used for training by default. Standard API inputs and outputs are generally retained for 30 rolling days for abuse monitoring unless approved zero-data-retention controls apply.
This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.
Read the provider policyFrequently asked questions
Mistral Embed FAQ
What is Mistral Embed?
Mistral's straightforward hosted text embedding model for semantic search, clustering, classification, and RAG. Mistral Embed converts single or batched text inputs into 1,024-dimensional vectors through Mistral's Embeddings API. Its simple fixed-size output and published token price make it an approachable option for conventional text retrieval.
When was Mistral Embed released?
Mistral Embed was released on December 11, 2023 according to the cited provider materials.
Where can I access Mistral Embed?
Generally available through Mistral's hosted Embeddings API and Studio. The access routes listed in this guide are Mistral AI.
How much does Mistral Embed cost?
$0.10 / 1M tokens. Mistral's standard hosted API list price. Batch and dedicated-deployment economics can differ from the synchronous shared endpoint.
Where is Mistral Embed available?
Generally available through Mistral's hosted Embeddings API and Studio. Mistral's standard and optional regional-inference routes have model-specific coverage; verify Embed support for an EU- or US-pinned endpoint.
Is my Mistral Embed API data used for training?
Mistral says API data is not used for training by default. Standard API inputs and outputs are generally retained for 30 rolling days for abuse monitoring unless approved zero-data-retention controls apply. The policy belongs to the provider route and account terms, so verify it again before production use.
Price comparison
USD per million tokens for the shown API routes at standard context length. Cache and long-context rates may differ. Models without matching reviewed prices are omitted; lower cost does not mean better quality.
- Mistral Embed$0.10
Mistral AI
This model
- Voyage 4 Large$0.12
Voyage AI
- Voyage Context 4$0.12
Voyage AI
- Voyage Code 4$0.12
Voyage AI
- text-embedding-3-large$0.13
OpenAI
- Gemini Embedding 2$0.20
Google
Related comparisons
Head-to-head comparisons
Mistral Embed vs Gemini Embedding 2
Google's multimodal embedding model for placing text, images, video, audio, and PDFs in one searchable vector space.
Open full comparisonMistral Embed vs text-embedding-3-large
OpenAI's highest-capability text embedding model for semantic search, recommendations, clustering, and retrieval pipelines.
Open full comparisonMistral Embed vs Cohere Embed 4
Cohere's enterprise embedding model for multilingual text, images, and visually rich documents with a 128K context window.
Open full comparisonMistral Embed vs Voyage 4 Large
Voyage AI's quality-first general embedding model for text and code retrieval, with adjustable dimensions and a shared family vector space.
Open full comparisonMistral Embed vs Voyage Context 4
Voyage AI's document-aware embedding model that automatically creates vectors for chunks while preserving information from the surrounding document.
Open full comparisonMistral Embed vs Voyage Code 4
Voyage AI's specialist embedding model for finding relevant code from natural-language questions or other source-code context.
Open full comparison
