From 52c0ff3c38f91ba7759f16237bbeb4e892c12104 Mon Sep 17 00:00:00 2001
From: "@taltas" <6816042+taltas@users.noreply.github.com>
Date: Tue, 13 Oct 2026 19:00:09 +0000
Subject: [PATCH] docs(providers): document Gemini 4 Argon on Gemini and Vertex
 AI pages

---
 docs/providers/gemini.md | 11 +++++++++++
 docs/providers/vertex.md | 11 +++++++++++
 2 files changed, 22 insertions(+)

diff --git a/docs/providers/gemini.md b/docs/providers/gemini.md
index c2f20bda..217a7ed9 100644
--- a/docs/providers/gemini.md
+++ b/docs/providers/gemini.md
@@ -36,6 +36,17 @@ Zoo Code supports all Gemini models available through Google's API and automatic
 
 For the complete, up-to-date model list and capabilities, see [Google's Gemini models documentation](https://ai.google.dev/models/gemini).
 
+### Gemini 4 Argon
+
+[Gemini 4 Argon](https://cloud.google.com/gemini-enterprise-agent-platform/models/guides/gemini-4-argon) (`gemini-4-argon`) is Google's flagship reasoning model and the first model in the Gemini 4 family.
+
+*   **Context window:** 1,048,576 tokens, shared across input, thinking, and output tokens.
+*   **Max output:** 65,536 tokens per streaming request (long decodes up to 1,048,576 tokens are handled via continuation).
+*   **Thinking levels:** Low, Medium (default), and High.
+*   **Caching:** Implicit caching applies automatically to prompt prefixes of 6,144 tokens or more; explicit context caching is not supported.
+*   **Availability:** Paid tier only (not available on the Free tier or the Google AI Pro plan).
+*   **Pricing (per 1M tokens):** Input $2.00, output (including thinking tokens) $10.00, cached input $0.10 — promo pricing through November 30, 2026. From December 1, 2026: input $4.00, output $20.00, cached input $0.20. See the [Gemini API pricing page](https://ai.google.dev/gemini-api/docs/pricing) for details.
+
 ---
 
 ## Configuration in Zoo Code
diff --git a/docs/providers/vertex.md b/docs/providers/vertex.md
index 944dbb54..17d2eb26 100644
--- a/docs/providers/vertex.md
+++ b/docs/providers/vertex.md
@@ -39,6 +39,17 @@ Zoo Code supports all models available through Google Cloud Vertex AI, including
 
 For the complete, up-to-date model list and IDs, see [Vertex AI's models documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models).
 
+### Gemini 4 Argon
+
+[Gemini 4 Argon](https://cloud.google.com/gemini-enterprise-agent-platform/models/guides/gemini-4-argon) (`gemini-4-argon`) is Google's flagship reasoning model and the first model in the Gemini 4 family.
+
+*   **Context window:** 1,048,576 tokens, shared across input, thinking, and output tokens.
+*   **Max output:** 65,536 tokens per streaming request (long decodes up to 1,048,576 tokens are handled via continuation).
+*   **Thinking levels:** Low, Medium (default), and High.
+*   **Caching:** Implicit caching applies automatically to prompt prefixes of 6,144 tokens or more; explicit context caching is not supported.
+*   **Locations:** `global`, `us`, and `eu`.
+*   **Pricing (Standard tier, Global, per 1M tokens):** Input $2.00, output (including thinking tokens) $10.00, cached input $0.10 — promo pricing through November 30, 2026. From December 1, 2026: input $4.00, output $20.00, cached input $0.20. Non-global locations are 10% higher. See the [Vertex AI pricing page](https://cloud.google.com/vertex-ai/generative-ai/pricing) for details.
+
 ---
 
 ## Configuration in Zoo Code