feat(wafer/deepseek-v4-pro): add new models [bot]

[models-bot]

Auto-generated by model-addition-agent for wafer/deepseek-v4-pro.

---

Note

Low Risk
Single new YAML model metadata file with no runtime or auth changes.

Overview
Adds a new Wafer provider catalog entry for deepseek-v4-pro, registering it as an active serverless chat model.

The definition includes token pricing (including cache-read input), a 1M context window, function calling, and thinking: true with configurable reasoning_effort (none through max). Documentation is linked via Wafer’s serverless API reference.

^{Reviewed by Cursor Bugbot for commit a3a1b9d. Bugbot is set up for automated code reviews on this repo. Configure here.}

[github-actions]

/test-models

[harshiv-26]

Gateway test setup failed for wafer

The test job aborted before any tests ran. Error:

Failed to apply virtual-account 'gateway-tester-v2-b65fd1f8-5': {"statusCode":500,"message":"Error applying the manifest of type virtual-account"}

This is usually a transient infra issue (catalogue build, TrueFoundry API, GitHub archive). Try /test-models again, or check the job logs.

[cursor]

Cursor Bugbot has reviewed your changes 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 a3a1b9d. Configure here.}

[cursor]

DeepSeek Pro costs wrong tier

Medium Severity

The costs block lists input_cost_per_token 1.2e-6 and output_cost_per_token 2.4e-6, which match Wafer’s GLM-5.2 input rate with a 2× output ratio, not DeepSeek V4 Pro serverless pricing on the same provider (V4 Flash is published around $0.14/$0.28 per M tokens; Pro is typically ~3× that tier, not ~8.5×).

 

^{Reviewed by Cursor Bugbot for commit a3a1b9d. Configure here.}