Gemini Embedding Pricing
Gemini Embedding is an embedding model from Google, last listed at Free per 1M tokens. It produces 768-dimensional vectors and accepts inputs up to 2,048 tokens. Free tier
Status checked against official pricing pages. Sources: Google
No longer on the official price list. Prices shown are the last ones published. Google’s pricing page now lists Gemini Embedding 2 instead: free on the free tier, $0.20 per 1M text tokens on the paid tier. Newer option: Gemini Embedding 2 at $0.20 per 1M tokens.
What does it cost to embed a corpus with Gemini Embedding?
Embedding cost is a one-time charge per document — unlike LLM inference, you only pay to embed each chunk once at ingest time. Re-embedding only happens when you re-chunk or swap models.
| Corpus size | Tokens | One-time embed cost |
|---|---|---|
| Small docs corpus (~1M tokens) | 1,000,000 | Free |
| Mid-size corpus (~50M tokens) | 50,000,000 | Free |
| Enterprise corpus (~500M tokens) | 500,000,000 | Free |
Want to model your RAG stack end-to-end? RAG cost calculator →
Vector database sizing — what 768-dim vectors cost to store
Each Gemini Embedding embedding is a 768-dimensional float32 vector, ~ 3.00 KB per vector. At 1M vectors that's ~ 2929.7 MB of raw vector data (before index overhead). Compare against alternates with different dimension counts:
- OpenAI text-embedding-3-small: 1536 dims → 5859.4 MB per 1M vectors
- OpenAI text-embedding-3-large: 3072 dims → 11718.8 MB per 1M vectors
- Voyage 3 Large: 2048 dims → 7812.5 MB per 1M vectors
- Voyage 3 Lite: 512 dims → 1953.1 MB per 1M vectors
- Cohere Embed v4: 1024 dims → 3906.3 MB per 1M vectors
- Gemini Embedding: 768 dims → 2929.7 MB per 1M vectors
Alternatives to Gemini Embedding
Higher-priced embedding models
FAQ
How much does Gemini Embedding cost?
Google no longer publishes a price for Gemini Embedding. No longer on the official price list. Prices shown are the last ones published. Google’s pricing page now lists Gemini Embedding 2 instead: free on the free tier, $0.20 per 1M text tokens on the paid tier. Newer option: Gemini Embedding 2 at $0.20 per 1M tokens.
What are Gemini Embedding's embedding dimensions?
Gemini Embedding outputs 768-dimensional vectors. This affects both storage size and similarity computation speed in your vector database.
What is the max input length?
Gemini Embedding accepts inputs up to 2,048 tokens. Larger documents must be chunked before embedding.
What's the cheapest alternative?
Gemini Embedding is already among the cheapest embedding models. The next-cheapest free or low-cost option is the OpenAI text-embedding-3-small.