From dbf851badf18d6ac96c514d3c3ab6ff908fcbd71 Mon Sep 17 00:00:00 2001
From: Daniel Salazar <daniel.salazar@puter.com>
Date: Fri, 16 Oct 2026 20:33:22 -0400
Subject: [PATCH] Bill Gemini 2.5 Pro at its current list rates

Cache reads are $0.125/M, and prompts over 200k tokens bill every rate at
the long-context tier ($2.50 in, $15 out, $0.25 cached).
---
 .../gemini/GeminiChatProvider.test.ts          | 18 ++++++++++++++++++
 .../drivers/ai-chat/providers/gemini/models.ts | 13 ++++++++++++-
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/src/backend/drivers/ai-chat/providers/gemini/GeminiChatProvider.test.ts b/src/backend/drivers/ai-chat/providers/gemini/GeminiChatProvider.test.ts
index 9024585a6..f992d3ade 100644
--- a/src/backend/drivers/ai-chat/providers/gemini/GeminiChatProvider.test.ts
+++ b/src/backend/drivers/ai-chat/providers/gemini/GeminiChatProvider.test.ts
@@ -612,6 +612,24 @@ describe('GeminiChatProvider pricing tiers', () => {
             expect(listedCosts(entry, NOW)).toBe(entry.costs);
         });
     });
+
+    it('prices gemini-2.5-pro at its list rates on both sides of 200,000 tokens', () => {
+        const entry = GEMINI_MODELS.find((m) => m.id === 'gemini-2.5-pro')!;
+        const now = new Date('2026-10-14T12:00:00Z');
+        expect(costsForRequest(entry, 200_000, now)).toMatchObject({
+            prompt_tokens: 125,
+            completion_tokens: 1000,
+            thinking_tokens: 1000,
+            cached_tokens: 12.5,
+        });
+        expect(costsForRequest(entry, 200_001, now)).toMatchObject({
+            prompt_tokens: 250,
+            completion_tokens: 1500,
+            thinking_tokens: 1500,
+            cached_tokens: 25,
+            grounding_requests: 3_500_000,
+        });
+    });
 });
 
 // ── Non-stream completion ───────────────────────────────────────────
diff --git a/src/backend/drivers/ai-chat/providers/gemini/models.ts b/src/backend/drivers/ai-chat/providers/gemini/models.ts
index 97c8be80d..d4e80e1c4 100644
--- a/src/backend/drivers/ai-chat/providers/gemini/models.ts
+++ b/src/backend/drivers/ai-chat/providers/gemini/models.ts
@@ -407,10 +407,21 @@ export const GEMINI_MODELS: IChatModel[] = [
             prompt_tokens: 125,
             completion_tokens: 1000,
             thinking_tokens: 1000,
-            cached_tokens: 31,
+            cached_tokens: 12.5,
             // Gemini 2.x grounding is $35 / 1,000 requests
             grounding_requests: 3_500_000,
         },
+        pricingOverrides: [
+            {
+                minPromptTokens: 200_000,
+                costs: {
+                    prompt_tokens: 250,
+                    completion_tokens: 1500,
+                    thinking_tokens: 1500,
+                    cached_tokens: 25,
+                },
+            },
+        ],
         max_tokens: 65_536,
     },
     {