> ## Documentation Index
> Fetch the complete documentation index at: https://veniceai-feat-models-redesign.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini Embedding 2 Preview API

> Gemini Embedding 2 Preview embeddings API on Venice: 3,072 dimensions, 2K input tokens, $0.25 per 1M tokens. Anonymized access without your identity.

export const HubMount = ({view, children, ...props}) => {
  const [hub, setHub] = useState(null);
  const [failed, setFailed] = useState(false);
  useEffect(() => {
    let alive = true;
    const w = window;
    if (!w.__veniceModelHub) {
      const urls = w.location.hostname === 'localhost' ? ['http://localhost:3333/data/model-hub.bundle.json', '/data/model-hub.bundle.json'] : ['/data/model-hub.bundle.json'];
      const load = i => fetch(urls[i], {
        cache: 'no-cache'
      }).then(res => {
        if (!res.ok) throw new Error(`bundle ${res.status}`);
        return res.json();
      }).catch(err => i + 1 < urls.length ? load(i + 1) : Promise.reject(err));
      const Frag = <></>.type;
      const h = (type, props, ...kids) => {
        const T = type;
        const {key, ...rest} = props || ({});
        if (!kids.length) return <T key={key} {...rest} />;
        if (kids.length === 1) return <T key={key} {...rest}>{kids[0]}</T>;
        return <T key={key} {...rest}>{kids.map((kid, i) => <Frag key={i}>{kid}</Frag>)}</T>;
      };
      w.__veniceModelHub = load(0).then(bundle => new Function(`return (${bundle.code})`)()({
        h,
        Fragment: Frag,
        useState,
        useEffect,
        useRef,
        useMemo,
        useCallback
      }));
    }
    w.__veniceModelHub.then(instance => {
      if (alive) setHub(instance);
    }).catch(() => {
      w.__veniceModelHub = null;
      if (alive) setFailed(true);
    });
    return () => {
      alive = false;
    };
  }, []);
  const View = hub ? hub[view] : null;
  if (View) return <View {...props}>{children}</View>;
  if (failed) {
    return <div className="vx-mount is-failed">
        <p className="vx-mount-note">The interactive model catalog could not load. The full data is below.</p>
        {children}
      </div>;
  }
  return <div className="vx-mount" aria-busy="true">
      <div className="vx-mount-skeleton" aria-hidden="true"><span /><span /><span /></div>
      <div className="vx-mount-source">{children}</div>
    </div>;
};

<HubMount view="ModelPage" data={{"family":{"slug":"gemini-embedding-2-preview","name":"Gemini Embedding 2 Preview","modality":"embedding","task":"embedding","provider":"google","primary":"gemini-embedding-2-preview","variants":["gemini-embedding-2-preview"],"created":1776384000,"updated":1776384000,"privacy":["anonymized"]},"models":[{"id":"gemini-embedding-2-preview","name":"Gemini Embedding 2 Preview","type":"embedding","modality":"embedding","task":"embedding","variant":"standard","provider":"google","created":1776384000,"privacy":"anonymized","embedding":{"dimensions":3072,"maxInputTokens":2048},"pricing":{"input":0.25},"headline":{"value":0.25,"unit":"per 1M tokens","basis":"input"},"endpoints":[{"id":"embeddings","method":"POST","path":"/embeddings","name":"Create embeddings","status":"stable","recommended":true}],"family":"gemini-embedding-2-preview"}],"related":{"similar":[{"slug":"text-embedding-3-large","name":"Text Embedding 3 Large","provider":"openai","modality":"embedding","privacy":["anonymized"],"created":1776384000,"headline":{"value":0.1625,"unit":"per 1M tokens","basis":"input"},"variants":1},{"slug":"bge-m3","name":"BGE-M3","provider":"baai","modality":"embedding","privacy":["private"],"created":1741924661,"headline":{"value":0.15,"unit":"per 1M tokens","basis":"input"},"variants":1},{"slug":"text-embedding-3-small","name":"Text Embedding 3 Small","provider":"openai","modality":"embedding","privacy":["anonymized"],"created":1776384000,"headline":{"value":0.025,"unit":"per 1M tokens","basis":"input"},"variants":1},{"slug":"bge-en-icl","name":"BGE-EN-ICL","provider":"baai","modality":"embedding","privacy":["private"],"created":1776384000,"headline":{"value":0.0125,"unit":"per 1M tokens","basis":"input"},"variants":1}],"versions":[]},"providers":{"google":{"slug":"google","name":"Google","logo":"/images/icons/models/google.svg"},"openai":{"slug":"openai","name":"OpenAI","logo":"/images/icons/models/openai.svg"},"baai":{"slug":"baai","name":"BAAI","logo":"/images/icons/models/text.svg"}},"faq":[{"q":"How much does the Gemini Embedding 2 Preview API cost?","a":"$0.25 per 1M input tokens. Prices are in USD and can be paid in DIEM at parity."},{"q":"What is the Gemini Embedding 2 Preview model ID?","a":"Use `gemini-embedding-2-preview` as the `model` parameter."},{"q":"Is the Gemini Embedding 2 Preview API private?","a":"Gemini Embedding 2 Preview is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work."},{"q":"How many dimensions do Gemini Embedding 2 Preview embeddings have?","a":"3,072 dimensions, with up to 2K input tokens per item."},{"q":"Which endpoint does the Gemini Embedding 2 Preview API use?","a":"Call `POST /embeddings`."}]}} />

<div className="vx-static">
  <Accordion title="Plain-text specification">
    # Gemini Embedding 2 Preview API

    Gemini Embedding 2 Preview is an embedding model by Google, available on the Venice API as `gemini-embedding-2-preview`. Requests are anonymized, so the provider never sees your identity.

    ## Gemini Embedding 2 Preview API pricing

    | Model ID | Variant | Privacy | Price |
    | - | - | - | - |
    | `gemini-embedding-2-preview` | Standard | Anonymized | \$0.25 per 1M tokens |

    ## Gemini Embedding 2 Preview specifications

    | Spec | Value |
    | - | - |
    | Provider | Google |
    | Released | Apr 17, 2026 |
    | Privacy | Anonymized |
    | Dimensions | 3,072 |
    | Max input | 2K tokens |

    ## How to use the Gemini Embedding 2 Preview API

    Send requests to `POST https://api.venice.ai/api/v1/embeddings` with `"model": "gemini-embedding-2-preview"` and your API key.

    ```bash theme={null}
    curl https://api.venice.ai/api/v1/embeddings \
      -H "Authorization: Bearer $VENICE_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "gemini-embedding-2-preview",
        "input": "Private AI for everyone."
      }'
    ```

    ## Gemini Embedding 2 Preview API FAQ

    ### How much does the Gemini Embedding 2 Preview API cost?

    \$0.25 per 1M input tokens. Prices are in USD and can be paid in DIEM at parity.

    ### What is the Gemini Embedding 2 Preview model ID?

    Use `gemini-embedding-2-preview` as the `model` parameter.

    ### Is the Gemini Embedding 2 Preview API private?

    Gemini Embedding 2 Preview is anonymized: Venice forwards requests to the provider without your identity, but the provider may retain prompt data, so use a private model for sensitive work.

    ### How many dimensions do Gemini Embedding 2 Preview embeddings have?

    3,072 dimensions, with up to 2K input tokens per item.

    ### Which endpoint does the Gemini Embedding 2 Preview API use?

    Call `POST /embeddings`.

    ## Related models

    * [Text Embedding 3 Large API](/models/text-embedding-3-large): \$0.16 per 1M tokens
    * [BGE-M3 API](/models/bge-m3): \$0.15 per 1M tokens
    * [Text Embedding 3 Small API](/models/text-embedding-3-small): \$0.03 per 1M tokens
    * [BGE-EN-ICL API](/models/bge-en-icl): \$0.01 per 1M tokens
  </Accordion>
</div>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.