gemini-embedding-001
Provides text embedding models for generating embeddings for words, phrases, sentences, and code. These foundational embeddings support advanced NLP tasks such as semantic search, classification, and clustering, offering more accurate and context-aware search results compared to keyword-based approaches. Building Retrieval Augmented Generation (RAG) systems is a common use case for embeddings. Embeddings play a crucial role in significantly enhancing model outputs, improving factual accuracy, coherence, and contextual richness. They enable efficient retrieval of relevant information from knowledge bases (represented as embeddings), which is then passed as additional background information in the input prompt to the language model, guiding it to generate more informed and accurate responses.
Performance
Pricing
| Input price | $0.00 · 1M tokens |
| Output price | $0.00 · 1M tokens |
| Context window | 2K tokens |
| Compatible endpoints | embedding |
| Vendor |
Call gemini-embedding-001 from your code
Point any OpenAI-compatible SDK at UnoRouter and request the model by name. Replace YOUR_API_KEY with a real key from your dashboard.
curl https://api.unorouter.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gemini-embedding-001",
"messages": [{"role": "user", "content": "Hello!"}]
}'Frequently asked questions
How much does gemini-embedding-001 cost per 1M tokens?
Input is priced at $0.00 per 1M tokens, output at $0.00 per 1M tokens. Billing is per token, no rounding to batch sizes.
How do I access gemini-embedding-001 via API?
Send requests to the UnoRouter /v1/chat/completions endpoint with model=gemini-embedding-001. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.
What is the context window of gemini-embedding-001?
gemini-embedding-001 supports a context window of 2K tokens, shared between your prompt and the model's response.
Similar models
Try gemini-embedding-001 now
Create an API key and start making requests in under a minute.