🧮 Embeddings API

Convert text into high-dimensional vectors for semantic search, similarity comparison, clustering, and RAG applications.

What Are Embeddings?

Embeddings are numerical representations of text that capture semantic meaning. Similar texts have similar embeddings, enabling powerful search and comparison features.

"The quick brown fox"
[0.012, -0.034, 0.891, ..., 0.023]
(1536 dimensions)

Embedding Models

mythic-embed-3-mini
1536
Dimensions
8192
Max Tokens
62.1%
MTEB Score
$0.02
Per 1M Tokens

Common Use Cases

🔍
Semantic Search
Find content by meaning, not just keywords
📚
RAG Systems
Retrieve relevant context for AI responses
🎯
Recommendations
Suggest similar items based on content
📊
Clustering
Group similar documents automatically
🔗
Deduplication
Detect near-duplicate content
🏷️
Classification
Categorize text into predefined groups

Code Example

Python - Generate Embeddings
from mythicdot import MythicDot import numpy as np client = MythicDot() # Generate embeddings for texts texts = [ "How do I reset my password?", "I forgot my login credentials", "What are your business hours?" ] response = client.embeddings.create( model="mythic-embed-3", input=texts ) # Extract embeddings embeddings = [item.embedding for item in response.data] # Calculate similarity (cosine) def cosine_similarity(a, b): return np.dot(a, b) / (np.linalg.norm(a) * np.linalg.norm(b)) # Compare first two (similar meaning) sim_1_2 = cosine_similarity(embeddings[0], embeddings[1]) print(f"Similarity 1-2: {sim_1_2:.3f}") # ~0.85 (similar) # Compare first and third (different topics) sim_1_3 = cosine_similarity(embeddings[0], embeddings[2]) print(f"Similarity 1-3: {sim_1_3:.3f}") # ~0.32 (different)

Pricing

Model Dimensions Price per 1M Tokens
mythic-embed-3 3072 $0.13
mythic-embed-3-mini 1536 $0.02

Start Embedding

Build powerful search and similarity features with our embeddings.

API Reference → Vector Stores