MoonshotAI / MoonshotAI/kimi-cli
Model API error 400 Validation: Unsupported parameter(s): `prompt_cache_key`
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 11.4k
- Forks
- 1.3k
- Avg merge
- 9h 47m
- Merged PRs (30d)
- 2
Description
What version of Kimi Code CLI is running?
0.29.0
Which open platform/subscription were you using?
3rd party API
Which model were you using?
Nvidia nim models
What platform is your computer?
windows
What issue are you seeing?
This was working fine until the latest update today. I believe Nvidia NIM doesn't support this but I have been using their models for weeks with kimi code. This week's update broke it somehow. Is there a setting I can use to disable it? Thanks.
Model API error
400 Validation: Unsupported parameter(s): prompt_cache_key
What steps can reproduce the bug?
Use cli or web and connect to nvidia endpoints. Tried it with a few models and it is the same
What is the expected behavior?
No response
Additional information
No response
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by tracing request construction for the CLI and web paths when connecting to Nvidia NIM endpoints, using the reported 0.29.0 behavior as the baseline. Check where prompt_cache_key was introduced and verify that Nvidia requests no longer receive the unsupported parameter while supported models retain their existing behavior.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api, cli
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 52/100