Text-Embedding-V4

Model IntroductionText

Text-Embedding-V4 is a text embedding model designed to convert text into high-dimensional vector representations. It captures semantic meaning for downstream tasks such as retrieval, clustering, and classification.

Key Features

  • High semantic fidelity: Produces embeddings that preserve nuanced meaning across sentences and paragraphs.
  • Multilingual support: Handles multiple languages within a shared vector space.
  • Scalable dimension: Offers configurable output dimensions to balance accuracy and storage.
  • Efficient inference: Optimized for low-latency batch processing.
  • Robust to domain shift: Maintains performance on specialized or technical text.

Use Cases

  • Semantic search and retrieval-augmented generation (RAG)
  • Document clustering and topic discovery
  • Duplicate detection and deduplication
  • Recommendation systems based on text similarity
  • Zero-shot classification via embedding comparison

API request example

Endpoint /v1/chat/completions. Replace <API_KEY> with a key from the console.

Standard OpenAI Chat Completions. Swap `model` for the target slug.

curl https://api.ravenrouter.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer <API_KEY>" \
  -d '{
  "model": "Text-Embedding-V4",
  "messages": [
    {
      "role": "user",
      "content": "Hello! Introduce yourself in one sentence."
    }
  ],
  "max_tokens": 64
}'

More models: API Reference → Examples by model

Text-Embedding-V4 API — $0.08/1M input | RavenRouter AI