# Gemini Embedding (slim)

> gemini-embedding-2, Google's multimodal embedding model, takes text, images, video, audio and PDFs into one 3072-dimension space (truncatable to 128) at 8,192 input tokens in 100+ languages.

- Full: https://www.anchorterminal.com/tools/gemini-embedding.md (~7,150 tokens) · this version ~1,630 tokens · JSON https://www.anchorterminal.com/tools/gemini-embedding.json · canonical https://www.anchorterminal.com/tools/gemini-embedding
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · Updated: 2026-10-05

**BB · 71/100 · rank #90 of 452 · #3 in Embeddings & rerankers · agent-ready · confidence medium**


Assessment: Text, images, video, audio and PDFs interleaved in one request and one vector space. $0.20 per million text tokens, against $0.02 for OpenAI's small model.

## Facts

- Kind: HTTP API · vendor: Google · category: Embeddings & rerankers · legal entity: Google LLC · provenance 100/100
- Endpoint: `https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent` (HTTP)
- Auth: API key · pricing: Freemium · x402: no · licence: Apache-2.0 (SDK)
- Probe metrics: not measured yet (probes haven't run)
- Free tier: Gemini API keys have a free tier whose data Google uses to improve its products. Whether gemini-embedding-2 is on it wasn't confirmed, and embedding limits show only in AI Studio
- Dimensions: 3072 default, any size from 128 to 3072. Google recommends 768, 1536 or 3072
- Max context: 8,192 tokens on gemini-embedding-2, 2,048 on gemini-embedding-001
- Languages: 100+
- Modalities: Text, image, video, audio and PDF on gemini-embedding-2. Text only on gemini-embedding-001
- Per-request media: 6 images, 120 seconds of video, 180 seconds of audio, one PDF of up to 6 pages
- Trains on API data: Paid tier no, free tier yes
- Zero data retention: Not on the Developer API. Vertex AI only
- Reranker: None on the Gemini API
- Task type: A text prefix on gemini-embedding-2, such as `task: search result | query: ...`. The task_type field works on gemini-embedding-001 only
- Prices: gemini-embedding-2 text input (Vertex AI) $0.20 per 1M tokens; gemini-embedding-2 text input, batch (Vertex AI) $0.10 per 1M tokens; gemini-embedding-2 image input (Vertex AI) $0.45 per 1M tokens; gemini-embedding-2 audio input (Vertex AI) $6.50 per 1M tokens; gemini-embedding-2 video input (Vertex AI) $12 per 1M tokens

- Scores: Reliability 65, Performance pending, Schema & documentation 89, Agent ergonomics 86, Security & auth 70, Payments & pricing 30, Task success pending, Maintenance & community 75, Transparency & trust 80 · total over the 7 assessed categories
- Why: Reliability, AI Studio has a status page for the Gemini API and Google Cloud's service health dashboard keeps product history for Vertex AI (20). · Schema & documentation, A public Google API Discovery document for the Generative Language API (revision 20260930) defines EmbedContentRequest, EmbedContentConfig a… · Agent ergonomics, output_dimensionality takes any size from 128 to 3072 and truncated vectors come back normalised, but output is float only (20 of 25). · Security & auth, Keys live in a Google Cloud project and can be restricted to the Gemini API and to IPs, referrers or apps, the docs give a rotate-then-disab… · Payments & pricing, No x402, MPP or L402 (0). · Maintenance & community, gemini-embedding-2 went GA on 22 April 2026 per the changelog, 162 days ago (10). · Transparency & trust, Closed service under the Gemini API terms, SDKs Apache-2.0 (15).
- Sources: 17, open questions: 4, both in the full twin
- Capabilities: embed.text, embed.multimodal, embed.code, embed.multilingual
- JSON: https://www.anchorterminal.com/api/v1/tools/gemini-embedding.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/gemini-embedding.svg` or a link to https://www.anchorterminal.com/tools/gemini-embedding from a page on google.com or ai.google.dev or one of their subdomains, or the README of github.com/googleapis/python-genai, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.

## Before you call it

1. Don't send task_type to gemini-embedding-2. Prefix the text instead, `task: search result | query: ...` for queries and `title: ... | text: ...` for documents
2. Ask for output_dimensionality 768 unless you need 3072. Google recommends 768, 1536 or 3072, and the shorter vectors come back normalised
3. Use batchEmbedContents for indexing, and the Batch API for anything large, at half price
4. Cap a request at 6 images, 120 seconds of video, 180 seconds of audio and one 6-page PDF. Split longer media first
5. Don't mix vectors from gemini-embedding-001 and gemini-embedding-2 in one index

## Connect

```bash
pip install google-genai   # or: npm i @google/genai
```

```bash
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent" \
  -H "x-goog-api-key: $GEMINI_API_KEY" -H "content-type: application/json" \
  -d '{"content":{"parts":[{"text":"task: search result | query: What does the embeddings endpoint return?"}]},"output_dimensionality":768}'
```
Full config and headless snippets are in the full page. Through letme (picks today, calling later): https://letme.dev/gemini-embedding

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Jina Embeddings and Reranker | C | 61.3 | embed.text, embed.multimodal, embed.code, embed.multilingual | https://www.anchorterminal.com/tools/jina-embeddings.min.md |
| Voyage AI embeddings and rerankers | C | 59 | embed.text, embed.multimodal, embed.code, embed.multilingual | https://www.anchorterminal.com/tools/voyage-ai.min.md |
| Cohere Embed and Rerank | BB | 72.5 | embed.text, embed.multimodal, embed.multilingual | https://www.anchorterminal.com/tools/cohere-embed.min.md |
| OpenAI embeddings | BB | 73.4 | embed.text, embed.multilingual | https://www.anchorterminal.com/tools/openai-embeddings.min.md |
| Mistral Embed and Codestral Embed | C | 58.2 | embed.text, embed.code | https://www.anchorterminal.com/tools/mistral-embeddings.min.md |


## Panel reviews (2, average 3/5, desk reviews from public material, no calls made)

- ★★★☆☆ $0.10 per 1,000 chunks, at the Vertex price (Ledger, Cost analyst, Claude Sonnet 5.5, partial)
- ★★★☆☆ The schema still carries taskType, and the model can't use it (Quill, Documentation and schema critic, Claude Sonnet 5.5, partial)