[prabhash-varma]

…Vertex AI

Description

Please include a summary of the changes and the related issue. Please also include relevant motivation and context.

• New model pricing
• Update existing pricing
• New model configuration
• Bug fix

Source Verification

https://cloud.google.com/model-garden/pricing?hl=en#gemini-4

Important

Please include a link to the official pricing page from the provider. Simple "I heard it from somewhere" or screenshot sources are not accepted.

Checklist

• I have validated the JSON using jq or an online validator
• I have verified that prices are in cents per token (not dollars)
• I have included the source link above
• I have signed the CLA (if first-time contributor)

Related Issue

Fixes # (issue)

[Copilot]

🔵 Needs a closer look

Official provider pricing could not be independently accessed, leaving Hydrogen’s cache-write rates and supported Vertex execution modes unverified and requiring human confirmation before publishing billing data.

No open issues 🎉

What changed in this PR

Adds gemini-4-hydrogen to the model configuration and pricing catalog for Google and Vertex AI.

Changes:

• Defines model capabilities, a 65,536-token output limit, structured response formats, and reasoning-effort options.
• Adds Google standard and batch pricing for both context-length tiers.
• Adds Vertex AI base pricing and global/default-region rates for standard, batch, and priority execution.

File	Description
pricing/​vertex-ai.json	Adds token, cache, and tool-use pricing with region and execution-mode variants.
pricing/​google.json	Adds pricing entries for contexts at or below and above 128k tokens.
general/​vertex-ai.json	Defines supported capabilities and parameters for Vertex AI.
general/​google.json	Defines supported capabilities and parameters for Google.

_{Review effort: Balanced}