[models-bot]

Auto-generated by poc-agent for provider wafer.

---

Note

Low Risk
Config-only pricing update for a single model; no runtime or auth logic changes.

Overview
Updates wafer pricing for DeepSeek-V4-Flash-0423 to match the current provider rates: cache-read input 2e-8 → 2.8e-8, input 7e-8 → 1.4e-7, and output 2.5e-7 → 2.8e-7. No feature, limit, or modality changes—only the costs block for region *.

^{Reviewed by Cursor Bugbot for commit a9a974a. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

SDK live feature checks

Result: failed (1/1 scenarios)

Informational — does not block merge.

Model	Pass	Fail
wafer/DeepSeek-V4-Flash-0423	0	1

Failures

• wafer/DeepSeek-V4-Flash-0423 setup: provider not in SDK live harness registry (add providers.ts + GitHub secret)