feat(microsoft-foundry/DeepSeek-V4-Flash): add new models [bot] - #2763
feat(microsoft-foundry/DeepSeek-V4-Flash): add new models [bot]#2763models-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 d0b4cfa. Configure here.
| costs: | ||
| - input_cost_per_token: 1.9e-7 | ||
| output_cost_per_token: 5.1e-7 | ||
| region: "*" |
There was a problem hiding this comment.
Missing cached input token price
Medium Severity
The new costs block matches the cited Microsoft input and output rates but omits cache_read_input_token_cost. The same source lists cached input at $0.028 per 1M tokens, so cache-hit estimates would use the full input rate.
Reviewed by Cursor Bugbot for commit d0b4cfa. 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/DeepSeek-V4-Flash.Note
Low Risk
Metadata-only YAML catalog addition with no runtime or auth changes.
Overview
Adds a new Microsoft Foundry provider definition for DeepSeek-V4-Flash as an active, serverless chat model with text-in/text-out modalities.
The entry records per-token pricing (input/output), a 1M context window, 128k max output tokens, and links to Azure AI catalog and Microsoft Foundry blog sources.
Reviewed by Cursor Bugbot for commit d0b4cfa. Bugbot is set up for automated code reviews on this repo. Configure here.