> ## 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.

# Google Gemma 4 26B A4B Instruct API

> Google Gemma 4 26B A4B Instruct API on Venice: 250K context, $0.13 input and $0.40 output per 1M tokens. Private, with zero data retention.

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":"google-gemma-4-26b-a4b-instruct","name":"Google Gemma 4 26B A4B Instruct","modality":"text","task":"chat","provider":"google","description":"Gemma 4 26B A4B is a Mixture-of-Experts model from Google DeepMind with 26B total parameters and only 4B active per token, offering fast inference at high quality. It handles text, image, and video input, supports 256K context, function calling, and reasoning with configurable thinking modes.","primary":"google-gemma-4-26b-a4b-it","variants":["google-gemma-4-26b-a4b-it"],"created":1775088000,"updated":1775088000,"privacy":["private"],"openWeights":true},"models":[{"id":"google-gemma-4-26b-a4b-it","name":"Google Gemma 4 26B A4B Instruct","type":"text","modality":"text","task":"chat","variant":"standard","provider":"google","created":1775088000,"description":"Gemma 4 26B A4B is a Mixture-of-Experts model from Google DeepMind with 26B total parameters and only 4B active per token, offering fast inference at high quality. It handles text, image, and video input, supports 256K context, function calling, and reasoning with configurable thinking modes.","source":"https://huggingface.co/google/gemma-4-26B-A4B-it","privacy":"private","openWeights":true,"text":{"context":256000,"maxOutput":8192,"quantization":"bf16","reasoning":{"supported":true,"effort":["none","low","medium","high"],"defaultEffort":"low"},"caps":{"tools":true,"structured":true,"vision":true,"maxImages":10,"videoInput":true,"webSearch":true,"logprobs":true}},"pricing":{"input":0.13,"output":0.4,"cacheRead":0.05,"blended":0.1975},"headline":{"value":0.1975,"unit":"per 1M tokens","basis":"blended"},"endpoints":[{"id":"chat","method":"POST","path":"/chat/completions","name":"Chat Completions","status":"stable","recommended":true},{"id":"responses","method":"POST","path":"/responses","name":"Responses","status":"alpha"}],"family":"google-gemma-4-26b-a4b-instruct"}],"related":{"similar":[{"slug":"deepseek-v4-flash-0423","name":"DeepSeek V4 Flash 0423","provider":"deepseek","modality":"text","privacy":["private","e2ee"],"created":1776988800,"headline":{"value":0.17225,"unit":"per 1M tokens","basis":"blended"},"variants":2},{"slug":"deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","provider":"deepseek","modality":"text","privacy":["private"],"created":1785456000,"headline":{"value":0.21875,"unit":"per 1M tokens","basis":"blended"},"variants":2},{"slug":"glm-4-7-flash-heretic","name":"GLM 4.7 Flash Heretic","provider":"community","modality":"text","privacy":["private"],"created":1770163200,"headline":{"value":0.1525,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"mimo-v2-6-flash","name":"MiMo-V2.6-Flash","provider":"xiaomi","modality":"text","privacy":["private"],"created":1790553600,"headline":{"value":0.21875,"unit":"per 1M tokens","basis":"blended"},"variants":1}],"versions":[]},"providers":{"google":{"slug":"google","name":"Google","logo":"/images/icons/models/google.svg"},"deepseek":{"slug":"deepseek","name":"DeepSeek","logo":"/images/icons/models/deepseek.svg"},"community":{"slug":"community","name":"Community","logo":"/images/icons/models/image.svg"},"xiaomi":{"slug":"xiaomi","name":"Xiaomi","logo":"/images/icons/models/text.svg"}},"faq":[{"q":"How much does the Google Gemma 4 26B A4B Instruct API cost?","a":"$0.13 per 1M input tokens and $0.40 per 1M output tokens, with cached input at $0.05 per 1M. Prices are in USD and can be paid in DIEM at parity."},{"q":"What is the Google Gemma 4 26B A4B Instruct model ID?","a":"Use `google-gemma-4-26b-a4b-it` as the `model` parameter."},{"q":"Is the Google Gemma 4 26B A4B Instruct API private?","a":"Google Gemma 4 26B A4B Instruct is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training."},{"q":"What is the context window of Google Gemma 4 26B A4B Instruct?","a":"250K tokens of context, with up to 8K output tokens per response."},{"q":"What does Google Gemma 4 26B A4B Instruct support?","a":"Google Gemma 4 26B A4B Instruct supports function calling, structured outputs, reasoning, image input, web search and prompt caching. Reasoning effort is adjustable with `reasoning_effort`: none, low, medium and high (default low)."},{"q":"Which endpoint does the Google Gemma 4 26B A4B Instruct API use?","a":"Call `POST /chat/completions`. `/responses` (Alpha) is also supported."}]}} />

<div className="vx-static">
  <Accordion title="Plain-text specification">
    # Google Gemma 4 26B A4B Instruct API

    Google Gemma 4 26B A4B Instruct is a large language model by Google, available on the Venice API as `google-gemma-4-26b-a4b-it`. It runs privately, with zero data retention.

    Gemma 4 26B A4B is a Mixture-of-Experts model from Google DeepMind with 26B total parameters and only 4B active per token, offering fast inference at high quality. It handles text, image, and video input, supports 256K context, function calling, and reasoning with configurable thinking modes.

    ## Google Gemma 4 26B A4B Instruct API pricing

    | Model ID | Variant | Privacy | Price |
    | - | - | - | - |
    | `google-gemma-4-26b-a4b-it` | Standard | Private | $0.13 input / $0.40 output per 1M tokens |

    ## Google Gemma 4 26B A4B Instruct specifications

    | Spec | Value |
    | - | - |
    | Provider | Google |
    | Released | Apr 2, 2026 |
    | Privacy | Private |
    | Open weights | Yes |
    | Context window | 250K tokens |
    | Max output | 8K tokens |
    | Reasoning effort | none, low, medium, high |
    | Served precision | BF16 |

    ## How to use the Google Gemma 4 26B A4B Instruct API

    Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "google-gemma-4-26b-a4b-it"` and your API key.

    ```bash theme={null}
    curl https://api.venice.ai/api/v1/chat/completions \
      -H "Authorization: Bearer $VENICE_API_KEY" \
      -H "Content-Type: application/json" \
      -d '{
        "model": "google-gemma-4-26b-a4b-it",
        "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
        "reasoning_effort": "low"
      }'
    ```

    ## Google Gemma 4 26B A4B Instruct API FAQ

    ### How much does the Google Gemma 4 26B A4B Instruct API cost?

    $0.13 per 1M input tokens and $0.40 per 1M output tokens, with cached input at \$0.05 per 1M. Prices are in USD and can be paid in DIEM at parity.

    ### What is the Google Gemma 4 26B A4B Instruct model ID?

    Use `google-gemma-4-26b-a4b-it` as the `model` parameter.

    ### Is the Google Gemma 4 26B A4B Instruct API private?

    Google Gemma 4 26B A4B Instruct is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

    ### What is the context window of Google Gemma 4 26B A4B Instruct?

    250K tokens of context, with up to 8K output tokens per response.

    ### What does Google Gemma 4 26B A4B Instruct support?

    Google Gemma 4 26B A4B Instruct supports function calling, structured outputs, reasoning, image input, web search and prompt caching. Reasoning effort is adjustable with `reasoning_effort`: none, low, medium and high (default low).

    ### Which endpoint does the Google Gemma 4 26B A4B Instruct API use?

    Call `POST /chat/completions`. `/responses` (Alpha) is also supported.

    ## Related models

    * [DeepSeek V4 Flash 0423 API](/models/deepseek-v4-flash-0423): $0.14 input / $0.28 output per 1M tokens
    * [DeepSeek V4 Flash 0731 API](/models/deepseek-v4-flash-0731): $0.17 input / $0.35 output per 1M tokens
    * [GLM 4.7 Flash Heretic API](/models/glm-4-7-flash-heretic): $0.07 input / $0.40 output per 1M tokens
    * [MiMo-V2.6-Flash API](/models/mimo-v2-6-flash): $0.17 input / $0.35 output per 1M tokens
  </Accordion>
</div>


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