Embedding / reranking model. Maps text into semantic vectors for search, retrieval, and classification.
Key strengths
- Semantic similarity
- Batch-friendly
- Multi-language support
- Low cost per call
Use cases
- Semantic search
- RAG retrieval
- Clustering
- Recommendations
Google's google/gemini-embedding-001 is a dense vector embedding model. It maps text into a semantic vector space optimized for retrieval, clustering, classification, recommendation, and RAG retrieval pipelines.
Compatible with the OpenAI `/embeddings` endpoint, returning numerical representations that measure semantic similarity between pieces of text. Well-suited for high-throughput indexing of large corpora at low cost.
google/gemini-embedding-001 is fully OpenAI-compatible — drop in your existing OpenAI Python or Node SDK and switch `baseURL` to `https://api.tokenlx.ai`. TokenLX transparently routes your requests to the optimal provider endpoint while preserving streaming, function-calling, and structured-output semantics.
Performance
Compare different providers across TokenLX · All locations.
Effective Pricing
Actual cost per million tokens across providers over the past 7 days.
Recent activity
Total usage per day on TokenLX (last 30 days).
Sample code & API
TokenLX normalizes requests and responses across providers. Use any OpenAI SDK or our native SDK.
# Python — use HTTP client directly
# Endpoint: POST https://api.tokenlx.ai/v1/embedding/generations
# Headers: Authorization: Bearer $TOKENLX_API_KEY
# Body: { "model": "gemini-embedding-001", "prompt": "..." }Replace sk-aihubrouter-… with your key from the dashboard.