chore: sync AI model catalog from models.dev (#20830)

Automated daily sync of `ai-providers.json` from
[models.dev](https://models.dev).

This PR updates pricing, context windows, and model availability based
on the latest data.
New models meeting inclusion criteria (tool calling, pricing data,
context limits) are added automatically.
Deprecated models are detected based on cost-efficiency within the same
model family.

**Please review before merging** — verify no critical models were
incorrectly deprecated.

Co-authored-by: FelixMalfait <6399865+FelixMalfait@users.noreply.github.com>

packages/twenty-server/src/engine/metadata-modules/ai/ai-models/ai-providers.json

@@ -1274,8 +1274,8 @@
         "outputCostPerMillionTokens": 2.5,
         "cachedInputCostPerMillionTokens": 0.2,
         "longContextCost": {
-          "inputCostPerMillionTokens": 4,
-          "outputCostPerMillionTokens": 12,
+          "inputCostPerMillionTokens": 2.5,
+          "outputCostPerMillionTokens": 5,
           "thresholdTokens": 200000,
           "cachedInputCostPerMillionTokens": 0.4
         },
@@ -1291,8 +1291,8 @@
         "outputCostPerMillionTokens": 2.5,
         "cachedInputCostPerMillionTokens": 0.2,
         "longContextCost": {
-          "inputCostPerMillionTokens": 4,
-          "outputCostPerMillionTokens": 12,
+          "inputCostPerMillionTokens": 2.5,
+          "outputCostPerMillionTokens": 5,
           "thresholdTokens": 200000,
           "cachedInputCostPerMillionTokens": 0.4
         },
@@ -1308,6 +1308,12 @@
         "inputCostPerMillionTokens": 1,
         "outputCostPerMillionTokens": 2,
         "cachedInputCostPerMillionTokens": 0.2,
+        "longContextCost": {
+          "inputCostPerMillionTokens": 2,
+          "outputCostPerMillionTokens": 4,
+          "thresholdTokens": 200000,
+          "cachedInputCostPerMillionTokens": 0.4
+        },
         "contextWindowTokens": 256000,
         "maxOutputTokens": 256000,
         "modalities": ["image", "pdf"],