# Is meta/llama-4-scout-17b-16e-instruct disabled for api?

**URL:** <https://forums.developer.nvidia.com/t/is-meta-llama-4-scout-17b-16e-instruct-disabled-for-api/365710>\
**Category:** Models\
**Tags:** developer-support, question, llama\
**Created:** [April 6, 2026, 6:33am UTC](https://forums.developer.nvidia.com/t/is-meta-llama-4-scout-17b-16e-instruct-disabled-for-api/365710 "2026-04-06T06:33:38Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![pinku6860](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@pinku6860](https://forums.developer.nvidia.com/u/pinku6860)\
**Post date:** [April 6, 2026, 6:33am UTC](https://forums.developer.nvidia.com/t/is-meta-llama-4-scout-17b-16e-instruct-disabled-for-api/365710/1 "2026-04-06T06:33:38Z")

</div>

Hey, Thanks for the access to write about the problem, i want to use the meta/llama-4-scout-17b-16e-instruct through api but it says this:  
`Status: 404`  
`Response: {“status”:404,“title”:“Not Found”,“detail”:“Function ‘b6bb6e01-780e-4ba0-a5b8-379f00ed9b1c’: Not found for account ‘cL_otl9NJS8fDxZdJoXnjmq7srGCuM6t2LXdrdeBC_w’”}`

this is the code:

```auto
import requests

API_KEY = “your-api”

Correct endpoint for multimodal models

invoke_url = “https://integrate.api.nvidia.com/v1/chat/completions”

headers = {
“Authorization”: f"Bearer {API_KEY}",
“Accept”: “application/json”,
“Content-Type”: “application/json”
}

payload = {
“model”: “meta/llama-4-scout-17b-16e-instruct”,
“messages”: [
{“role”: “user”, “content”: “Hello, what can you do?”}
],
“max_tokens”: 512,
“stream”: False
}

response = requests.post(invoke_url, headers=headers, json=payload)
print(“Status:”, response.status_code)
print(“Response:”, response.text)

```

i test with this if model is available or not but i can see its there:

```auto
import requests

response = requests.get(
“https://integrate.api.nvidia.com/v1/models”,
headers={“Authorization”: “Bearer your-api”}
)
print(response.json())

```

as you can see the response of above script in the image below:

 ![image](https://global.discourse-cdn.com/nvidia/original/4X/a/c/b/acb049add46b7a454a8758a93cbdf9032abd7adf.png)