GoogleFastHigh

Gemini Embedding 001

Google's text embedding model for generating vector representations. Optimized for semantic search, clustering, and similarity tasks.

279credits

per 1M input tokens · no output-token charge

High-quality text embeddings

2,048 token max input per request

Output dimensions: 128–3,072 (default 3,072; recommended 768 / 1,536 / 3,072)

Matryoshka Representation Learning (MRL) for flexible dimensionality

8 task types: SEMANTIC_SIMILARITY, CLASSIFICATION, CLUSTERING, RETRIEVAL_DOCUMENT, RETRIEVAL_QUERY, CODE_RETRIEVAL_QUERY, QUESTION_ANSWERING, FACT_VERIFICATION

Optimized for semantic search, clustering, classification, and RAG

Run it right now

Test this model instantly in the Console Playground — no code required

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

llms.txtllms.txt ↗

Model Specifications

Context Window

tokens

Training Cutoff

August 2024

Compatible SDK

Google AI

Capabilities

Vision

Function Calling

Streaming

JSON Mode

System Prompt

Token Pricing (per 1M tokens)

Token Type	Credits	USD Equivalent
Input Tokens	279	$0.19
Output Tokens	No charge — billed on input tokens only

* 1,500 credits ≈ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/gemini/v1beta/openai/embeddings" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gemini-embedding-001",
  "input": "What is the meaning of life?"
}'

Parameters

Parameter	Type	Required	Default	Description
`input`	string \| array	Yes	-	Text or array of texts to embed. Max 2,048 input tokens per item.
`model`	string	Yes	gemini-embedding-001	Model identifier.
`dimensions`	integer	No	3072	Output embedding dimensionality. Range: 128–3,072. Recommended: 768, 1,536, 3,072. Manual L2 normalization required for non-3,072 dimensions.
`task_type`	string	No	-	Optimize embedding for a downstream task. One of: SEMANTIC_SIMILARITY, CLASSIFICATION, CLUSTERING, RETRIEVAL_DOCUMENT, RETRIEVAL_QUERY, CODE_RETRIEVAL_QUERY, QUESTION_ANSWERING, FACT_VERIFICATION. SEMANTIC_SIMILARITYCLASSIFICATIONCLUSTERINGRETRIEVAL_DOCUMENTRETRIEVAL_QUERYCODE_RETRIEVAL_QUERYQUESTION_ANSWERINGFACT_VERIFICATION

Examples

Text Embedding

Generate embeddings for semantic search

curl -X POST "https://api.core.today/llm/gemini/v1beta/openai/embeddings" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "gemini-embedding-001",
  "input": "What is the meaning of life?"
}'

Tips & Best Practices

1Max input: 2,048 tokens per item — split long documents into chunks first

2Default output: 3,072 dimensions; use 768 or 1,536 to reduce storage/cost via MRL

3Set `task_type` to match your use case (e.g., RETRIEVAL_DOCUMENT for indexing, RETRIEVAL_QUERY for queries)

4Manually L2-normalize embeddings if you request a non-3,072 dimensionality

5Combine with vector databases for RAG pipelines

6Batch multiple texts in a single request for efficiency

7Google retires this model on 2028-05-14 - new projects should start on gemini-embedding-2 (vectors are not interchangeable; re-embed your corpus when switching)