Title: 404 Error / Account Entitlement Issue with Prototype Endpoint moonshotai/kimi-k2.6

If you are reporting a bug or error, consider submitting a Support Bundle to aiworkbench-ea@nvidia.com. This will help us solve your issue more quickly.

Please describe your issue or request: (tick the boxes after creating this topic):

Please tick the appropriate box to help us categorize your post
Bug or Error
Feature Request
Documentation Issue
Other

Hi everyone,

I am trying to access the prototype NIM endpoint for moonshotai/kimi-k2.6 using my NVIDIA Developer/NIM API key, but I am consistently receiving a 404 Not Found (or empty 404 response) error.

NVIDIA Customer Care (Ticket assisted by Krishna) referred me to this forum to verify my account’s eligibility and request activation/entitlement for this specific Prototype endpoint.

Here are the details of my request:

  • Model Name: moonshotai/kimi-k2.6

  • Endpoint: [https://integrate.api.nvidia.com/v1/chat/completions](https://integrate.api.nvidia.com/v1/chat/completions)

  • API Version: v1 (Chat Completions)

Reproduction Attempt via cURL:

Bash

curl -i -X POST "https://integrate.api.nvidia.com/v1/chat/completions" \
  -H "Authorization: Bearer nvapi-****************" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k2.6",
    "messages": [{"role": "user", "content": "Hi"}],
    "max_tokens": 50
  }'

Response / Error Received:

  • HTTP Status: 404 Not Found (or equivalent model_not_found error)

Could the NIM/developer team please check if my account has the necessary permissions to access this prototype model, or if there is an additional activation step required for my API key to unlock the Kimi K2.6 endpoint?

Thank you for your help!

Best regards,

Leander

Account access issues are not handled here through the forums.
Please check the pinned posts:

for details.

Thank you!

as far as I’m aware, nobody can use kimi k2.6 for now. the model was deprecated for a few days, but after k3’s released, it came back to the catalogue. they probably enabled it back on the catalogue but didn’t reactivate it on their servers.

Hi. Contact help@build.nvidia.com for these kinds of issues.

nobody answers the emails