AI API PricesEmbeddings › Gemini Embedding

Gemini Embedding pricing

Gemini Embedding from Google — embeddings API at $0.150 per 1M tokens, 3072 dimensions, 2,048-token max input. Multimodal embeddings; Matryoshka (768 / 1536 / 3072).

Per 1M tokens
$0.150
input tokens
Dimensions
3072
vector size
Max input
2K
tokens / request
Model string
gemini-embedding-001
Google

multimodal Billed per input token · prices USD, last verified 2026-06-27.

Gemini Embedding cost calculator

Estimate the bill for embedding a corpus. Enter total tokens (≈ words × 1.3).

One-time embedding cost

Re-embedding on model changes repeats this cost. Compare all models on the embeddings pricing page.

Gemini Embedding vs other embedding models

Cost per 1M tokens, cheapest first — Gemini Embedding highlighted.

ModelProviderPer 1MDimensionsMax input
BGE-M3open BAAI $0.010 1024 8K
text-embedding-3-small OpenAI $0.020 1536 8K
Jina Embeddings v3 Jina AI $0.020 1024 8K
Voyage-3.5 Voyage AI $0.060 1024 32K
Mistral Embed Mistral $0.100 1024 8K
Cohere Embed v4 Cohere $0.120 1536 128K
text-embedding-3-large OpenAI $0.130 3072 8K
Gemini Embedding Google $0.150 3072 2K
Cheaper than Gemini Embedding? BGE-M3 runs $0.010 per 1M tokens. See the full embeddings API pricing comparison.

How Gemini Embedding pricing works

Gemini Embedding bills per input token at $0.150 per million — there are no output tokens, since the response is a fixed 3072-dimension vector. Cost scales only with how much text you embed, so the levers are corpus size and how often you re-embed.

Higher dimensions improve retrieval marginally but increase vector-database storage and query cost proportionally — many models (including this one where noted) support shortening dimensions to trade a little accuracy for big storage savings.

Gemini Embedding pricing FAQ

How much does Gemini Embedding cost?

Gemini Embedding costs $0.150 per 1M input tokens. Embedding 1 million typical documents of ~500 tokens each (500M tokens) would cost about $75.00.

How many dimensions does Gemini Embedding output?

Gemini Embedding returns 3072-dimension vectors, and supports Matryoshka shortening to smaller dimensions to cut storage. Its max input is 2,048 tokens per request.

Is there a cheaper embedding model than Gemini Embedding?

Yes — BGE-M3 (BAAI) is cheaper at $0.010 per 1M tokens. The cheapest tracked here is BGE-M3 at $0.010.

Compare embedding models