feat(microsoft-foundry/Kimi-K3-2026-07-29): add new models [bot] - #2744
feat(microsoft-foundry/Kimi-K3-2026-07-29): add new models [bot]#2744models-bot[bot] wants to merge 2 commits into
Conversation
|
/test-models |
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes using default effort and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit f928a59. Configure here.
| - cache_read_input_token_cost: 3.3e-7 | ||
| input_cost_per_token: 0.0000033 | ||
| output_cost_per_token: 0.0000165 | ||
| region: global |
There was a problem hiding this comment.
Wrong cost region for Kimi K3
Medium Severity
The new cost row uses region: global with the published FW-Kimi-K3 US Data Zone Standard rates. Foundry does not list Global Standard pricing for this model, so Data Zone deployments will not match this entry.
Reviewed by Cursor Bugbot for commit f928a59. Configure here.
LordGameleo
left a comment
LordGameleo
left a comment
There was a problem hiding this comment.
Approving: bot-generated model addition. Required check (Validate YAML files) is green; the gateway-test trigger failure is a CI infra issue, not a model validation failure.
1 participant
Auto-generated by model-addition-agent for
microsoft-foundry/Kimi-K3-2026-07-29.Note
Low Risk
Adds static model metadata only; no runtime, auth, or routing logic changes.
Overview
Adds a new Microsoft Foundry provider definition for
Kimi-K3-2026-07-29, registering it as an active, serverless chat model with thinking enabled.The entry documents 1M-token context, text + image input, global token pricing (including prompt-cache read cost), and capabilities such as function calling, tool choice, system messages, and prompt caching, with links to Azure catalog and pricing sources.
Reviewed by Cursor Bugbot for commit f928a59. Bugbot is set up for automated code reviews on this repo. Configure here.