> ## 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.

# Hermes 3 Llama 3.1 405b API

> Hermes 3 Llama 3.1 405b API on Venice: 125K context, $1.10 input and $3.00 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":"hermes-3-llama-3-1-405b","name":"Hermes 3 Llama 3.1 405b","modality":"text","task":"chat","provider":"nous","description":"Hermes 3 405B is a frontier level, full parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.","primary":"hermes-3-llama-3.1-405b","variants":["hermes-3-llama-3.1-405b"],"created":1758758400,"updated":1758758400,"privacy":["private"],"openWeights":true},"models":[{"id":"hermes-3-llama-3.1-405b","name":"Hermes 3 Llama 3.1 405b","type":"text","modality":"text","task":"chat","variant":"standard","provider":"nous","created":1758758400,"description":"Hermes 3 405B is a frontier level, full parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.","source":"https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B","privacy":"private","openWeights":true,"text":{"context":128000,"maxOutput":16384,"quantization":"fp8","caps":{"webSearch":true}},"pricing":{"input":1.1,"output":3,"blended":1.575},"headline":{"value":1.575,"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":"hermes-3-llama-3-1-405b"}],"related":{"similar":[{"slug":"gemini-3-flash-preview","name":"Gemini 3 Flash Preview","provider":"google","modality":"text","privacy":["anonymized"],"created":1766102400,"headline":{"value":1.4625,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"glm-5","name":"GLM 5","provider":"zai","modality":"text","privacy":["private"],"created":1770768000,"headline":{"value":1.55,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"qwen-3-5-397b","name":"Qwen 3.5 397B","provider":"alibaba","modality":"text","privacy":["anonymized"],"created":1771200000,"headline":{"value":1.6875,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"grok-4-20","name":"Grok 4.20","provider":"xai","modality":"text","privacy":["private"],"created":1773273600,"headline":{"value":1.7725,"unit":"per 1M tokens","basis":"blended"},"variants":1}],"versions":[]},"providers":{"nous":{"slug":"nous","name":"Nous Research","logo":"/images/icons/models/text.svg"},"google":{"slug":"google","name":"Google","logo":"/images/icons/models/google.svg"},"zai":{"slug":"zai","name":"Z.ai","logo":"/images/icons/models/Zhipu.svg"},"alibaba":{"slug":"alibaba","name":"Alibaba Qwen","logo":"/images/icons/models/qwen.svg"},"xai":{"slug":"xai","name":"xAI","logo":"/images/icons/models/grok.svg"}},"faq":[{"q":"How much does the Hermes 3 Llama 3.1 405b API cost?","a":"$1.10 per 1M input tokens and $3.00 per 1M output tokens. Prices are in USD and can be paid in DIEM at parity."},{"q":"What is the Hermes 3 Llama 3.1 405b model ID?","a":"Use `hermes-3-llama-3.1-405b` as the `model` parameter."},{"q":"Is the Hermes 3 Llama 3.1 405b API private?","a":"Hermes 3 Llama 3.1 405b 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 Hermes 3 Llama 3.1 405b?","a":"125K tokens of context, with up to 16K output tokens per response."},{"q":"What does Hermes 3 Llama 3.1 405b support?","a":"Hermes 3 Llama 3.1 405b supports web search."},{"q":"Which endpoint does the Hermes 3 Llama 3.1 405b API use?","a":"Call `POST /chat/completions`. `/responses` (Alpha) is also supported."}]}} />

<div className="vx-static">
  <Accordion title="Plain-text specification">
    # Hermes 3 Llama 3.1 405b API

    Hermes 3 Llama 3.1 405b is a large language model by Nous Research, available on the Venice API as `hermes-3-llama-3.1-405b`. It runs privately, with zero data retention.

    Hermes 3 405B is a frontier level, full parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.

    ## Hermes 3 Llama 3.1 405b API pricing

    | Model ID | Variant | Privacy | Price |
    | - | - | - | - |
    | `hermes-3-llama-3.1-405b` | Standard | Private | $1.10 input / $3.00 output per 1M tokens |

    ## Hermes 3 Llama 3.1 405b specifications

    | Spec | Value |
    | - | - |
    | Provider | Nous Research |
    | Released | Sep 25, 2025 |
    | Privacy | Private |
    | Open weights | Yes |
    | Context window | 125K tokens |
    | Max output | 16K tokens |
    | Served precision | FP8 |

    ## How to use the Hermes 3 Llama 3.1 405b API

    Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "hermes-3-llama-3.1-405b"` 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": "hermes-3-llama-3.1-405b",
        "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
      }'
    ```

    ## Hermes 3 Llama 3.1 405b API FAQ

    ### How much does the Hermes 3 Llama 3.1 405b API cost?

    $1.10 per 1M input tokens and $3.00 per 1M output tokens. Prices are in USD and can be paid in DIEM at parity.

    ### What is the Hermes 3 Llama 3.1 405b model ID?

    Use `hermes-3-llama-3.1-405b` as the `model` parameter.

    ### Is the Hermes 3 Llama 3.1 405b API private?

    Hermes 3 Llama 3.1 405b 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 Hermes 3 Llama 3.1 405b?

    125K tokens of context, with up to 16K output tokens per response.

    ### What does Hermes 3 Llama 3.1 405b support?

    Hermes 3 Llama 3.1 405b supports web search.

    ### Which endpoint does the Hermes 3 Llama 3.1 405b API use?

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

    ## Related models

    * [Gemini 3 Flash Preview API](/models/gemini-3-flash-preview): $0.70 input / $3.75 output per 1M tokens
    * [GLM 5 API](/models/glm-5): $1.00 input / $3.20 output per 1M tokens
    * [Qwen 3.5 397B API](/models/qwen-3-5-397b): $0.75 input / $4.50 output per 1M tokens
    * [Grok 4.20 API](/models/grok-4-20): $1.42 input / $2.83 output per 1M tokens
  </Accordion>
</div>


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