> ## 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.

# Inkling API

> Inkling API on Venice: 512K context, $1.25 input and $5.06 output per 1M tokens. Private, with zero data retention. Pricing, specs and code examples.

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":"inkling","name":"Inkling","modality":"text","task":"chat","provider":"inkling","description":"Inkling is a general-purpose multimodal model from Thinking Machines Lab that accepts text, image, and audio inputs and generates text. It is a 66-layer sparse MoE (975B total / 41B active) with hybrid local/global attention, 512K context, and variable thinking effort — suited for chat, coding, tool use, and agentic workflows. Video input is not supported on Venice.","primary":"inkling","variants":["inkling"],"created":1784160000,"updated":1784160000,"privacy":["private"],"openWeights":true},"models":[{"id":"inkling","name":"Inkling","type":"text","modality":"text","task":"chat","variant":"standard","provider":"inkling","created":1784160000,"description":"Inkling is a general-purpose multimodal model from Thinking Machines Lab that accepts text, image, and audio inputs and generates text. It is a 66-layer sparse MoE (975B total / 41B active) with hybrid local/global attention, 512K context, and variable thinking effort — suited for chat, coding, tool use, and agentic workflows. Video input is not supported on Venice.","source":"https://huggingface.co/thinkingmachines/Inkling-NVFP4","privacy":"private","openWeights":true,"text":{"context":524288,"maxOutput":65536,"quantization":"fp8","reasoning":{"supported":true,"effort":["none","low","medium","high"],"defaultEffort":"high"},"caps":{"tools":true,"structured":true,"vision":true,"maxImages":10,"audioInput":true,"webSearch":true,"code":true}},"pricing":{"input":1.25,"output":5.0625,"cacheRead":0.2125,"blended":2.203125},"headline":{"value":2.203125,"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":"inkling"}],"related":{"similar":[{"slug":"glm-5-2","name":"GLM 5.2","provider":"zai","modality":"text","privacy":["private","e2ee"],"created":1781568000,"headline":{"value":2.15,"unit":"per 1M tokens","basis":"blended"},"variants":2},{"slug":"deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","provider":"deepseek","modality":"text","privacy":["private"],"created":1786665600,"headline":{"value":2.475,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"gemini-3-6-flash","name":"Gemini 3.6 Flash","provider":"google","modality":"text","privacy":["anonymized"],"created":1783555200,"headline":{"value":1.875,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"deepseek-v4-pro","name":"DeepSeek V4 Pro","provider":"deepseek","modality":"text","privacy":["private"],"created":1776988800,"headline":{"value":2.06275,"unit":"per 1M tokens","basis":"blended"},"variants":1}],"versions":[]},"providers":{"inkling":{"slug":"inkling","name":"Inkling","logo":"/images/icons/models/text.svg","inferred":true},"zai":{"slug":"zai","name":"Z.ai","logo":"/images/icons/models/Zhipu.svg"},"deepseek":{"slug":"deepseek","name":"DeepSeek","logo":"/images/icons/models/deepseek.svg"},"google":{"slug":"google","name":"Google","logo":"/images/icons/models/google.svg"}},"faq":[{"q":"How much does the Inkling API cost?","a":"$1.25 per 1M input tokens and $5.06 per 1M output tokens, with cached input at $0.21 per 1M. Prices are in USD and can be paid in DIEM at parity."},{"q":"What is the Inkling model ID?","a":"Use `inkling` as the `model` parameter."},{"q":"Is the Inkling API private?","a":"Inkling 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 Inkling?","a":"512K tokens of context, with up to 64K output tokens per response."},{"q":"What does Inkling support?","a":"Inkling 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 high)."},{"q":"Which endpoint does the Inkling API use?","a":"Call `POST /chat/completions`. `/responses` (Alpha) is also supported."}]}} />

<div className="vx-static">
  <Accordion title="Plain-text specification">
    # Inkling API

    Inkling is a large language model by Inkling, available on the Venice API as `inkling`. It runs privately, with zero data retention.

    Inkling is a general-purpose multimodal model from Thinking Machines Lab that accepts text, image, and audio inputs and generates text. It is a 66-layer sparse MoE (975B total / 41B active) with hybrid local/global attention, 512K context, and variable thinking effort — suited for chat, coding, tool use, and agentic workflows. Video input is not supported on Venice.

    ## Inkling API pricing

    | Model ID | Variant | Privacy | Price |
    | - | - | - | - |
    | `inkling` | Standard | Private | $1.25 input / $5.06 output per 1M tokens |

    ## Inkling specifications

    | Spec | Value |
    | - | - |
    | Provider | Inkling |
    | Released | Jul 16, 2026 |
    | Privacy | Private |
    | Open weights | Yes |
    | Context window | 512K tokens |
    | Max output | 64K tokens |
    | Reasoning effort | none, low, medium, high |
    | Served precision | FP8 |

    ## How to use the Inkling API

    Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "inkling"` 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": "inkling",
        "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
        "reasoning_effort": "high"
      }'
    ```

    ## Inkling API FAQ

    ### How much does the Inkling API cost?

    $1.25 per 1M input tokens and $5.06 per 1M output tokens, with cached input at \$0.21 per 1M. Prices are in USD and can be paid in DIEM at parity.

    ### What is the Inkling model ID?

    Use `inkling` as the `model` parameter.

    ### Is the Inkling API private?

    Inkling 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 Inkling?

    512K tokens of context, with up to 64K output tokens per response.

    ### What does Inkling support?

    Inkling 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 high).

    ### Which endpoint does the Inkling API use?

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

    ## Related models

    * [GLM 5.2 API](/models/glm-5-2): $1.40 input / $4.40 output per 1M tokens
    * [DeepSeek V4 Pro 0813 API](/models/deepseek-v4-pro-0813): $1.65 input / $4.95 output per 1M tokens
    * [Gemini 3.6 Flash API](/models/gemini-3-6-flash): $0.94 input / $4.69 output per 1M tokens
    * [DeepSeek V4 Pro API](/models/deepseek-v4-pro): $1.65 input / $3.30 output per 1M tokens
  </Accordion>
</div>


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