[Docs] Document Gemini 4 Argon on Gemini and Vertex AI provider pages

[zoomote]

​Opened on behalf of @taltas. Follow up by mentioning @roomote, in the web UI, or in Discord.

What changed

Added a "Gemini 4 Argon" section under "Available Models" on two provider pages:

• docs/providers/gemini.md (Google Gemini)
• docs/providers/vertex.md (GCP Vertex AI)

Each section documents the model ID (gemini-4-argon), the shared 1,048,576-token context window, the 65,536-token single-request output cap, thinking levels (Low / Medium default / High), implicit-only caching (6,144-token prefix minimum, no explicit caching), and the promo pricing (input $2.00, output $10.00 including thinking tokens, cached input $0.10 per 1M tokens through November 30, 2026; $4.00 / $20.00 / $0.20 from December 1, 2026). The Vertex page also lists the available locations (global, us, eu) and the +10% non-global pricing note. The Gemini page notes the model is paid tier only.

Why this change was made

Zoo Code added gemini-4-argon to its Gemini API and Vertex AI provider registries in the paired Zoo-Code PR (see "Related PRs"). The documentation convention is that functionality changes ship with matching docs, and the provider pages are the place users check for model capabilities and cost.

Impact

Users evaluating Gemini 4 Argon can see its context size, output limits, thinking levels, and current promo pricing (including the December 1, 2026 price change) directly on both provider pages. No structural docs changes: no redirects, sidebar, or navigation updates were needed.

pnpm run check-types passes. Content was verified against https://cloud.google.com/gemini-enterprise-agent-platform/models/guides/gemini-4-argon, https://cloud.google.com/vertex-ai/generative-ai/pricing, and https://ai.google.dev/gemini-api/docs/pricing, and rendered locally in the Docusaurus dev server (see screenshots).

Screenshots

Related PRs

• Zoo-Code: [Feat] Add Gemini 4 Argon to Gemini and Vertex AI providers Zoo-Code#2043