> ## 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 3 27B Instruct API

> Google Gemma 3 27B Instruct API on Venice: 198K context, $0.12 input and $0.20 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-3-27b-instruct","name":"Google Gemma 3 27B Instruct","modality":"text","task":"chat","provider":"google","description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2.","primary":"google-gemma-3-27b-it","variants":["google-gemma-3-27b-it"],"created":1762214400,"updated":1762214400,"privacy":["private"],"openWeights":true},"models":[{"id":"google-gemma-3-27b-it","name":"Google Gemma 3 27B Instruct","type":"text","modality":"text","task":"chat","variant":"standard","provider":"google","created":1762214400,"description":"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2.","source":"https://huggingface.co/google/gemma-3-27b-it","privacy":"private","openWeights":true,"text":{"context":198000,"maxOutput":16384,"quantization":"fp8","caps":{"tools":true,"structured":true,"vision":true,"maxImages":10,"webSearch":true}},"pricing":{"input":0.12,"output":0.2,"blended":0.14},"headline":{"value":0.14,"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-3-27b-instruct"}],"related":{"similar":[{"slug":"openai-gpt-oss-120b","name":"OpenAI GPT OSS 120B","provider":"openai","modality":"text","privacy":["private","e2ee"],"created":1762387200,"headline":{"value":0.1275,"unit":"per 1M tokens","basis":"blended"},"variants":2},{"slug":"mistral-small-3-2-24b-instruct","name":"Mistral Small 3.2 24B Instruct","provider":"mistral","modality":"text","privacy":["private"],"created":1768435200,"headline":{"value":0.132813,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"glm-4-7-flash","name":"GLM 4.7 Flash","provider":"zai","modality":"text","privacy":["private"],"created":1769644800,"headline":{"value":0.145,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"nvidia-nemotron-3-nano-30b","name":"NVIDIA Nemotron 3 Nano 30B","provider":"nvidia","modality":"text","privacy":["private"],"created":1769472000,"headline":{"value":0.13125,"unit":"per 1M tokens","basis":"blended"},"variants":1}],"versions":[{"slug":"google-gemma-4-31b-instruct","name":"Google Gemma 4 31B Instruct","provider":"google","modality":"text","privacy":["private"],"created":1775174400,"headline":{"value":0.18,"unit":"per 1M tokens","basis":"blended"},"variants":1}]},"providers":{"google":{"slug":"google","name":"Google","logo":"/images/icons/models/google.svg"},"openai":{"slug":"openai","name":"OpenAI","logo":"/images/icons/models/openai.svg"},"mistral":{"slug":"mistral","name":"Mistral AI","logo":"/images/icons/models/mistral.svg"},"zai":{"slug":"zai","name":"Z.ai","logo":"/images/icons/models/Zhipu.svg"},"nvidia":{"slug":"nvidia","name":"NVIDIA","logo":"/images/icons/models/nvidia.svg"}},"faq":[{"q":"How much does the Google Gemma 3 27B Instruct API cost?","a":"$0.12 per 1M input tokens and $0.20 per 1M output tokens. Prices are in USD and can be paid in DIEM at parity."},{"q":"What is the Google Gemma 3 27B Instruct model ID?","a":"Use `google-gemma-3-27b-it` as the `model` parameter."},{"q":"Is the Google Gemma 3 27B Instruct API private?","a":"Google Gemma 3 27B 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 3 27B Instruct?","a":"198K tokens of context, with up to 16K output tokens per response."},{"q":"What does Google Gemma 3 27B Instruct support?","a":"Google Gemma 3 27B Instruct supports function calling, structured outputs, image input and web search."},{"q":"Which endpoint does the Google Gemma 3 27B Instruct API use?","a":"Call `POST /chat/completions`. `/responses` (Alpha) is also supported."}]}} />

<div className="vx-static">
  <Accordion title="Plain-text specification">
    # Google Gemma 3 27B Instruct API

    Google Gemma 3 27B Instruct is a large language model by Google, available on the Venice API as `google-gemma-3-27b-it`. It runs privately, with zero data retention.

    Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2.

    ## Google Gemma 3 27B Instruct API pricing

    | Model ID | Variant | Privacy | Price |
    | - | - | - | - |
    | `google-gemma-3-27b-it` | Standard | Private | $0.12 input / $0.20 output per 1M tokens |

    ## Google Gemma 3 27B Instruct specifications

    | Spec | Value |
    | - | - |
    | Provider | Google |
    | Released | Nov 4, 2025 |
    | Privacy | Private |
    | Open weights | Yes |
    | Context window | 198K tokens |
    | Max output | 16K tokens |
    | Served precision | FP8 |

    ## How to use the Google Gemma 3 27B Instruct API

    Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "google-gemma-3-27b-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-3-27b-it",
        "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
      }'
    ```

    ## Google Gemma 3 27B Instruct API FAQ

    ### How much does the Google Gemma 3 27B Instruct API cost?

    $0.12 per 1M input tokens and $0.20 per 1M output tokens. Prices are in USD and can be paid in DIEM at parity.

    ### What is the Google Gemma 3 27B Instruct model ID?

    Use `google-gemma-3-27b-it` as the `model` parameter.

    ### Is the Google Gemma 3 27B Instruct API private?

    Google Gemma 3 27B 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 3 27B Instruct?

    198K tokens of context, with up to 16K output tokens per response.

    ### What does Google Gemma 3 27B Instruct support?

    Google Gemma 3 27B Instruct supports function calling, structured outputs, image input and web search.

    ### Which endpoint does the Google Gemma 3 27B Instruct API use?

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

    ## Related models

    * [Google Gemma 4 31B Instruct API](/models/google-gemma-4-31b-instruct): $0.12 input / $0.36 output per 1M tokens
    * [OpenAI GPT OSS 120B API](/models/openai-gpt-oss-120b): $0.07 input / $0.30 output per 1M tokens
    * [Mistral Small 3.2 24B Instruct API](/models/mistral-small-3-2-24b-instruct): $0.09 input / $0.25 output per 1M tokens
    * [GLM 4.7 Flash API](/models/glm-4-7-flash): $0.06 input / $0.40 output per 1M tokens
    * [NVIDIA Nemotron 3 Nano 30B API](/models/nvidia-nemotron-3-nano-30b): $0.07 input / $0.30 output per 1M tokens
  </Accordion>
</div>


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