> ## 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.
# GPT-4o API
> GPT-4o API on Venice: 125K context, $3.13 input and $12.50 output per 1M tokens. Anonymized access without your identity. Supports function calling and vision.
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 ${res.status}`);
return res.json();
}).catch(err => i + 1 < urls.length ? load(i + 1) : Promise.reject(err));
const Frag = <>.type;
const h = (type, props, ...kids) => {
const T = type;
const {key, ...rest} = props || ({});
if (!kids.length) return ;
if (kids.length === 1) return {kids[0]};
return {kids.map((kid, i) => {kid})};
};
w.__veniceModelHub = load(0).then(bundle => new Function(`return (${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 {children};
if (failed) {
return
The interactive model catalog could not load. The full data is below.
{children}
;
}
return
{children}
;
};
# GPT-4o API
GPT-4o is a large language model by OpenAI, available on the Venice API as `openai-gpt-4o-2024-11-20`. Requests are anonymized, so the provider never sees your identity.
OpenAI's multimodal flagship model with vision capabilities, strong reasoning, and broad knowledge. Popular for its balanced performance across tasks. Version: 2024-11-20.
## GPT-4o API pricing
| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `openai-gpt-4o-2024-11-20` | Standard | Anonymized | $3.13 input / $12.50 output per 1M tokens |
## GPT-4o specifications
| Spec | Value |
| - | - |
| Provider | OpenAI |
| Released | Feb 28, 2026 |
| Privacy | Anonymized |
| Context window | 125K tokens |
| Max output | 16K tokens |
## How to use the GPT-4o API
Send requests to `POST https://api.venice.ai/api/v1/chat/completions` with `"model": "openai-gpt-4o-2024-11-20"` 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": "openai-gpt-4o-2024-11-20",
"messages": [{ "role": "user", "content": "Explain TEE attestation in two sentences." }]
}'
```
## GPT-4o API FAQ
### How much does the GPT-4o API cost?
$3.13 per 1M input tokens and $12.50 per 1M output tokens. Prices are in USD and can be paid in DIEM at parity.
### What is the GPT-4o model ID?
Use `openai-gpt-4o-2024-11-20` as the `model` parameter.
### Is the GPT-4o API private?
GPT-4o 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 GPT-4o?
125K tokens of context, with up to 16K output tokens per response.
### What does GPT-4o support?
GPT-4o supports function calling, structured outputs, image input and web search.
### Which endpoint does the GPT-4o API use?
Call `POST /chat/completions`. `/responses` (Alpha) is also supported.
## Related models
* [Gemini 3.1 Pro Preview API](/models/gemini-3-1-pro-preview): $2.50 input / $15.00 output per 1M tokens
* [Claude Sonnet 5 API](/models/claude-sonnet-5): $3.00 input / $15.00 output per 1M tokens
* [Claude Sonnet 4.6 API](/models/claude-sonnet-4-6): $3.60 input / $18.00 output per 1M tokens
* [Aion 3.0 API](/models/aion-3-0): $3.75 input / $7.50 output per 1M tokens
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.