Merge pull request #264 from suurt8ll/chore/add-new-models

chore(gemini): add `gemini-3.1-flash-lite` and `gemini-3.5-flash`

Author: suurt8ll

plugins/pipes/gemini_models.yaml

@@ -5,7 +5,78 @@
 
 
 
-
+gemini-3.5-flash:
+  description: "Gemini 3.5 Flash provides sustained frontier-level intelligence optimized for real-world tasks at a higher speed and lower cost. Designed for the agentic era, it excels at sub-agent deployment, multi-step workflows, and long-horizon tasks at scale. This model is particularly effective for rapid agentic loops involving complex coding cycles and iterations."
+  knowledge_cutoff: "2025-01"
+  latest_update: "2026-05"
+  supported_data_types:
+    inputs: [Text, Image, Video, Audio, PDF]
+    outputs: [Text]
+  tokens:
+    input: 1048576
+    output: 65536
+  capabilities:
+    audio_generation: false
+    batch_api: true
+    caching: true
+    code_execution: true
+    file_search: true
+    function_calling: true
+    grounding_google_maps: true
+    image_generation: false
+    live_api: false
+    search_grounding: true
+    structured_outputs: true
+    thinking: true
+    url_context: true
+  pricing:
+    free_tier: true
+    excluded_features: [search_grounding, grounding_google_maps]
+    input:
+      - up_to_tokens: null
+        price_per_million: 1.50
+    output:
+      - up_to_tokens: null
+        price_per_million: 9.00
+    caching:
+      - up_to_tokens: null
+        price_per_million: 0.15
+gemini-3.1-flash-lite:
+  description: "Gemini 3.1 Flash-Lite is a low-latency, cost-effective multimodal model optimized for high-frequency, lightweight tasks. The model supports text, image, video, audio, and PDF inputs, and is designed for high-volume agentic workflows, simple data extraction, and applications where latency and API cost are the primary constraints."
+  knowledge_cutoff: "2025-01"
+  latest_update: "2026-05"
+  supported_data_types:
+    inputs: [Text, Image, Video, Audio, PDF]
+    outputs: [Text]
+  tokens:
+    input: 1048576
+    output: 65536
+  capabilities:
+    audio_generation: false
+    batch_api: true
+    caching: true
+    code_execution: true
+    file_search: true
+    function_calling: true
+    grounding_google_maps: false
+    image_generation: false
+    live_api: false
+    search_grounding: true
+    structured_outputs: true
+    thinking: true
+    url_context: true
+  pricing:
+    free_tier: true
+    excluded_features: [search_grounding]
+    input:
+      - up_to_tokens: null
+        price_per_million: 0.25
+    output:
+      - up_to_tokens: null
+        price_per_million: 1.50
+    caching:
+      - up_to_tokens: null
+        price_per_million: 0.025
 gemini-3.1-flash-lite-preview:
   description: "Our most cost-efficient multimodal model, offering the fastest performance for high-frequency, lightweight tasks. Gemini 3.1 Flash-Lite is best for high-volume agentic tasks, simple data extraction, and extremely low-latency applications where budget and speed are the primary constraints."
   knowledge_cutoff: "2025-01"