HiNow LogoHiNow

Mistral Embed

Model Information

Display Name: Mistral Embed

API Model ID: mistralai/mistral-embed

Category: Text To Embedding

Description: Mistral Embed is the most cost-effective commercial embedding model available, ideal for semantic search, RAG applications, and clustering tasks. **Key Features:** - 8K token context window - 1024 dimension embeddings - Lowest cost commercial embedding - Multilingual support - Semantic similarity optimized - Batch processing support **Capabilities:** - Semantic search - Document retrieval (RAG) - Text clustering - Similarity matching - Classification tasks - Recommendation systems **Best For:** - Cost-sensitive RAG applications - Large-scale document search - High-volume embedding tasks - Multilingual retrieval **Technical Specs:** - Embedding Dimensions: 1024 - Context: 8K tokens - Batch API: 50% discount available - License: Commercial

Context Window: 8,192 tokens

How to Use This Model

To use Mistral Embed via the HInow.ai API, use the model ID: mistralai/mistral-embed

API Request Example (Chat/Text)


POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

{
  "model": "mistralai/mistral-embed",
  "messages": [
    {"role": "user", "content": "Your message here"}
  ]
}

Pricing

  • input: $0.014

Quick Reference

To use this model, set: "model": "mistralai/mistral-embed"

Featured: Yes

Documentation: https://hinow.ai/models/mistralai/mistral-embed

API Endpoint: https://api.hinow.ai/v1

Back to Models
Mistral Embed

Mistral Embed

Featured

mistralai/mistral-embed

$0.014
input

About

Mistral Embed is the most cost-effective commercial embedding model available, ideal for semantic search, RAG applications, and clustering tasks.

Key Features:

  • 8K token context window
  • 1024 dimension embeddings
  • Lowest cost commercial embedding
  • Multilingual support
  • Semantic similarity optimized
  • Batch processing support

Capabilities:

  • Semantic search
  • Document retrieval (RAG)
  • Text clustering
  • Similarity matching
  • Classification tasks
  • Recommendation systems

Best For:

  • Cost-sensitive RAG applications
  • Large-scale document search
  • High-volume embedding tasks
  • Multilingual retrieval

Technical Specs:

  • Embedding Dimensions: 1024
  • Context: 8K tokens
  • Batch API: 50% discount available
  • License: Commercial

Capabilities

Text To Embedding
Context8K tokens

Code Examples

curl -X POST https://api.hinow.ai/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $HINOW_API_KEY" \
  -d '{
    "model": "mistralai/mistral-embed",
    "input": "Your input here"
  }'