> ## 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.
# Multilingual E5 Large Instruct API
> Multilingual E5 Large Instruct embeddings API on Venice: 1,024 dimensions, 512 input tokens, $0.013 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 ${res.status}`);
return res.json();
}).catch(err => i + 1 < urls.length ? load(i + 1) : Promise.reject(err));
const Frag = <>.type;
const h = (type, props, ...kids) => {
const T = type;
const {key, ...rest} = props || ({});
if (!kids.length) return ;
if (kids.length === 1) return {kids[0]};
return {kids.map((kid, i) => {kid})};
};
w.__veniceModelHub = load(0).then(bundle => new Function(`return (${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}
;
};
# Multilingual E5 Large Instruct API
Multilingual E5 Large Instruct is an embedding model by Microsoft, available on the Venice API as `text-embedding-multilingual-e5-large-instruct`. It runs privately, with zero data retention.
## Multilingual E5 Large Instruct API pricing
| Model ID | Variant | Privacy | Price |
| - | - | - | - |
| `text-embedding-multilingual-e5-large-instruct` | Standard | Private | \$0.01 per 1M tokens |
## Multilingual E5 Large Instruct specifications
| Spec | Value |
| - | - |
| Provider | Microsoft |
| Released | Apr 17, 2026 |
| Privacy | Private |
| Open weights | Yes |
| Dimensions | 1,024 |
| Max input | 512 tokens |
## How to use the Multilingual E5 Large Instruct API
Send requests to `POST https://api.venice.ai/api/v1/embeddings` with `"model": "text-embedding-multilingual-e5-large-instruct"` and your API key.
```bash theme={null}
curl https://api.venice.ai/api/v1/embeddings \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "text-embedding-multilingual-e5-large-instruct",
"input": "Private AI for everyone."
}'
```
## Multilingual E5 Large Instruct API FAQ
### How much does the Multilingual E5 Large Instruct API cost?
\$0.013 per 1M input tokens. Prices are in USD and can be paid in DIEM at parity.
### What is the Multilingual E5 Large Instruct model ID?
Use `text-embedding-multilingual-e5-large-instruct` as the `model` parameter.
### Is the Multilingual E5 Large Instruct API private?
Multilingual E5 Large Instruct is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.
### How many dimensions do Multilingual E5 Large Instruct embeddings have?
1,024 dimensions, with up to 512 input tokens per item.
### Which endpoint does the Multilingual E5 Large Instruct API use?
Call `POST /embeddings`.
## Related models
* [BGE-EN-ICL API](/models/bge-en-icl): \$0.01 per 1M tokens
* [Nemotron Embed VL 1B v2 API](/models/nemotron-embed-vl-1b-v2): \$0.01 per 1M tokens
* [Qwen3 Embedding 0.6B API](/models/qwen3-embedding-0-6b): \$0.01 per 1M tokens
* [Qwen3 Embedding 8B API](/models/qwen3-embedding-8b): \$0.01 per 1M tokens
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.