> ## 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.

# Claude Opus 4.8 API

> Claude Opus 4.8 API on Venice: 1M context, $6.00 input and $30.00 output 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":"claude-opus-4-8","name":"Claude Opus 4.8","modality":"text","task":"chat","provider":"anthropic","description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.","primary":"claude-opus-4-8","variants":["claude-opus-4-8","claude-opus-4-8-fast"],"created":1779926400,"updated":1779926400,"privacy":["anonymized"]},"models":[{"id":"claude-opus-4-8","name":"Claude Opus 4.8","type":"text","modality":"text","task":"chat","variant":"standard","provider":"anthropic","created":1779926400,"description":"Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.","privacy":"anonymized","text":{"context":1000000,"maxOutput":128000,"reasoning":{"supported":true,"effort":["low","medium","high","xhigh","max"],"defaultEffort":"medium"},"caps":{"tools":true,"structured":true,"vision":true,"maxImages":10,"webSearch":true,"code":true}},"pricing":{"input":6,"output":30,"cacheRead":0.6,"cacheWrite":7.5,"blended":12},"headline":{"value":12,"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":"claude-opus-4-8"},{"id":"claude-opus-4-8-fast","name":"Claude Opus 4.8 Fast","type":"text","modality":"text","task":"chat","variant":"fast","provider":"anthropic","created":1779926400,"description":"Claude Opus 4.8 (Fast) is a speed-optimized variant of Anthropic's most capable generally available Opus model, offering the same 1M token context window and strong performance across long-horizon agentic work and complex coding — with lower latency.","privacy":"anonymized","text":{"context":1000000,"maxOutput":128000,"reasoning":{"supported":true,"effort":["low","medium","high","xhigh","max"],"defaultEffort":"medium"},"caps":{"tools":true,"structured":true,"vision":true,"maxImages":10,"webSearch":true,"code":true}},"pricing":{"input":12,"output":60,"cacheRead":1.2,"cacheWrite":15,"blended":24},"headline":{"value":24,"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":"claude-opus-4-8"}],"related":{"similar":[{"slug":"gpt-5-5","name":"GPT-5.5","provider":"openai","modality":"text","privacy":["anonymized"],"created":1776902400,"headline":{"value":14.0625,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"gpt-5-6-sol","name":"GPT-5.6 Sol","provider":"openai","modality":"text","privacy":["anonymized"],"created":1783555200,"headline":{"value":10,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"gpt-5-6-sol-pro","name":"GPT-5.6 Sol Pro","provider":"openai","modality":"text","privacy":["anonymized"],"created":1783555200,"headline":{"value":10,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"claude-opus-4-7","name":"Claude Opus 4.7","provider":"anthropic","modality":"text","privacy":["anonymized"],"created":1776297600,"headline":{"value":12,"unit":"per 1M tokens","basis":"blended"},"variants":1}],"versions":[{"slug":"claude-opus-5-5","name":"Claude Opus 5.5","provider":"anthropic","modality":"text","privacy":["anonymized"],"created":1789689600,"headline":{"value":9.6,"unit":"per 1M tokens","basis":"blended"},"variants":2},{"slug":"claude-opus-5","name":"Claude Opus 5","provider":"anthropic","modality":"text","privacy":["anonymized"],"created":1784764800,"headline":{"value":12,"unit":"per 1M tokens","basis":"blended"},"variants":2},{"slug":"claude-opus-4-7","name":"Claude Opus 4.7","provider":"anthropic","modality":"text","privacy":["anonymized"],"created":1776297600,"headline":{"value":12,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"claude-opus-4-6","name":"Claude Opus 4.6","provider":"anthropic","modality":"text","privacy":["anonymized"],"created":1770249600,"headline":{"value":12,"unit":"per 1M tokens","basis":"blended"},"variants":1},{"slug":"claude-opus-4-5","name":"Claude Opus 4.5","provider":"anthropic","modality":"text","privacy":["anonymized"],"created":1764979200,"headline":{"value":12,"unit":"per 1M tokens","basis":"blended"},"variants":1}]},"providers":{"anthropic":{"slug":"anthropic","name":"Anthropic","logo":"/images/icons/models/opus.svg"},"openai":{"slug":"openai","name":"OpenAI","logo":"/images/icons/models/openai.svg"}},"faq":[{"q":"How much does the Claude Opus 4.8 API cost?","a":"$6.00 per 1M input tokens and $30.00 per 1M output tokens, with cached input at $0.60 per 1M. The Fast variant costs $12.00 input and $60.00 output. Prices are in USD and can be paid in DIEM at parity."},{"q":"What is the Claude Opus 4.8 model ID?","a":"Use `claude-opus-4-8` as the `model` parameter. Other variants: `claude-opus-4-8-fast` (Fast)."},{"q":"Is the Claude Opus 4.8 API private?","a":"Claude Opus 4.8 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":"What is the context window of Claude Opus 4.8?","a":"1M tokens of context, with up to 125K output tokens per response."},{"q":"What does Claude Opus 4.8 support?","a":"Claude Opus 4.8 supports function calling, structured outputs, reasoning, image input, web search and prompt caching. Reasoning effort is adjustable with `reasoning_effort`: low, medium, high, xhigh and max (default medium)."},{"q":"Which endpoint does the Claude Opus 4.8 API use?","a":"Call `POST /chat/completions`. `/responses` (Alpha) is also supported."}]}} />

<div className="vx-static">
  <Accordion title="Plain-text specification">
    # Claude Opus 4.8 API

    Claude Opus 4.8 is a large language model by Anthropic, available on the Venice API as `claude-opus-4-8`. Requests are anonymized, so the provider never sees your identity.

    Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports long-horizon agentic work, complex multi-step coding, and memory-driven tasks where coherence over extended sessions matters. It features a 1M token context window, 128K max output tokens, adaptive thinking, and strong multimodal capabilities.

    ## Claude Opus 4.8 API pricing

    | Model ID | Variant | Privacy | Price |
    | - | - | - | - |
    | `claude-opus-4-8` | Standard | Anonymized | $6.00 input / $30.00 output per 1M tokens |
    | `claude-opus-4-8-fast` | Fast | Anonymized | $12.00 input / $60.00 output per 1M tokens |

    ## Claude Opus 4.8 specifications

    | Spec | Value |
    | - | - |
    | Provider | Anthropic |
    | Released | May 28, 2026 |
    | Privacy | Anonymized |
    | Context window | 1M tokens |
    | Max output | 125K tokens |
    | Reasoning effort | low, medium, high, xhigh, max |

    ## How to use the Claude Opus 4.8 API

    Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "claude-opus-4-8"` 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": "claude-opus-4-8",
        "messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }],
        "reasoning_effort": "medium"
      }'
    ```

    ## Claude Opus 4.8 API FAQ

    ### How much does the Claude Opus 4.8 API cost?

    $6.00 per 1M input tokens and $30.00 per 1M output tokens, with cached input at $0.60 per 1M. The Fast variant costs $12.00 input and \$60.00 output. Prices are in USD and can be paid in DIEM at parity.

    ### What is the Claude Opus 4.8 model ID?

    Use `claude-opus-4-8` as the `model` parameter. Other variants: `claude-opus-4-8-fast` (Fast).

    ### Is the Claude Opus 4.8 API private?

    Claude Opus 4.8 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.

    ### What is the context window of Claude Opus 4.8?

    1M tokens of context, with up to 125K output tokens per response.

    ### What does Claude Opus 4.8 support?

    Claude Opus 4.8 supports function calling, structured outputs, reasoning, image input, web search and prompt caching. Reasoning effort is adjustable with `reasoning_effort`: low, medium, high, xhigh and max (default medium).

    ### Which endpoint does the Claude Opus 4.8 API use?

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

    ## Related models

    * [Claude Opus 5.5 API](/models/claude-opus-5-5): $4.80 input / $24.00 output per 1M tokens
    * [Claude Opus 5 API](/models/claude-opus-5): $6.00 input / $30.00 output per 1M tokens
    * [Claude Opus 4.7 API](/models/claude-opus-4-7): $6.00 input / $30.00 output per 1M tokens
    * [Claude Opus 4.6 API](/models/claude-opus-4-6): $6.00 input / $30.00 output per 1M tokens
    * [Claude Opus 4.5 API](/models/claude-opus-4-5): $6.00 input / $30.00 output per 1M tokens
    * [GPT-5.5 API](/models/gpt-5-5): $6.25 input / $37.50 output per 1M tokens
    * [GPT-5.6 Sol API](/models/gpt-5-6-sol): $5.00 input / $25.00 output per 1M tokens
    * [GPT-5.6 Sol Pro API](/models/gpt-5-6-sol-pro): $5.00 input / $25.00 output per 1M tokens
  </Accordion>
</div>


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