RubyGems - ruby_llm - Versions diffs - 0.1.0.pre41 → 0.1.0.pre42 - Mend

ruby_llm 0.1.0.pre41 → 0.1.0.pre42

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (18) hide show

checksums.yaml +4 -4
data/.rspec_status +5 -4
data/README.md +18 -2
data/lib/ruby_llm/content.rb +1 -9
data/lib/ruby_llm/models.json +345 -452
data/lib/ruby_llm/provider.rb +1 -2
data/lib/ruby_llm/providers/gemini/chat.rb +140 -0
data/lib/ruby_llm/providers/gemini/embeddings.rb +53 -0
data/lib/ruby_llm/providers/gemini/images.rb +51 -0
data/lib/ruby_llm/providers/gemini/media.rb +136 -0
data/lib/ruby_llm/providers/gemini/models.rb +41 -6
data/lib/ruby_llm/providers/gemini/streaming.rb +99 -0
data/lib/ruby_llm/providers/gemini/tools.rb +88 -0
data/lib/ruby_llm/providers/gemini.rb +10 -4
data/lib/ruby_llm/providers/openai/images.rb +0 -2
data/lib/ruby_llm/stream_accumulator.rb +1 -1
data/lib/ruby_llm/version.rb +1 -1
metadata +7 -1

data/lib/ruby_llm/models.json CHANGED Viewed

@@ -2,7 +2,7 @@
   {
     "id": "aqa",
     "created_at": null,
-    "display_name": "AQA",
+    "display_name": "Model that performs Attributed Question Answering.",
     "provider": "gemini",
     "context_window": 7168,
     "max_tokens": 1024,
@@ -14,8 +14,13 @@
     "input_price_per_million": 0.0,
     "output_price_per_million": 0.0,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Model trained to return answers to questions that are grounded in provided sources, along with estimating answerable probability.",
+      "input_token_limit": 7168,
+      "output_token_limit": 1024,
+      "supported_generation_methods": [
+        "generateAnswer"
+      ]
     }
   },
   {
@@ -40,10 +45,10 @@
   {
     "id": "chat-bison-001",
     "created_at": null,
-    "display_name": "Chat Bison 001",
+    "display_name": "PaLM 2 Chat (Legacy)",
     "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
+    "context_window": 4096,
+    "max_tokens": 1024,
     "type": "chat",
     "family": "other",
     "supports_vision": false,
@@ -52,8 +57,14 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "A legacy text-only model optimized for chat conversations",
+      "input_token_limit": 4096,
+      "output_token_limit": 1024,
+      "supported_generation_methods": [
+        "generateMessage",
+        "countMessageTokens"
+      ]
     }
   },
   {
@@ -320,7 +331,7 @@
     "display_name": "Embedding 001",
     "provider": "gemini",
     "context_window": 2048,
-    "max_tokens": 768,
+    "max_tokens": 1,
     "type": "embedding",
     "family": "embedding1",
     "supports_vision": false,
@@ -329,17 +340,22 @@
     "input_price_per_million": 0.0,
     "output_price_per_million": 0.0,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Obtain a distributed representation of a text.",
+      "input_token_limit": 2048,
+      "output_token_limit": 1,
+      "supported_generation_methods": [
+        "embedContent"
+      ]
     }
   },
   {
     "id": "embedding-gecko-001",
     "created_at": null,
-    "display_name": "Embedding Gecko 001",
+    "display_name": "Embedding Gecko",
     "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
+    "context_window": 1024,
+    "max_tokens": 1,
     "type": "embedding",
     "family": "other",
     "supports_vision": false,
@@ -348,35 +364,22 @@
     "input_price_per_million": 0.0,
     "output_price_per_million": 0.0,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "evergreen-custom",
-    "created_at": null,
-    "display_name": "Evergreen Custom",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Obtain a distributed representation of a text.",
+      "input_token_limit": 1024,
+      "output_token_limit": 1,
+      "supported_generation_methods": [
+        "embedText",
+        "countTextTokens"
+      ]
     }
   },
   {
     "id": "gemini-1.0-pro-vision-latest",
     "created_at": null,
-    "display_name": "Gemini 1.0 Pro Vision Latest",
+    "display_name": "Gemini 1.0 Pro Vision",
     "provider": "gemini",
-    "context_window": 32768,
+    "context_window": 12288,
     "max_tokens": 4096,
     "type": "chat",
     "family": "gemini10_pro",
@@ -386,8 +389,14 @@
     "input_price_per_million": 0.5,
     "output_price_per_million": 1.5,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "The original Gemini 1.0 Pro Vision model version which was optimized for image understanding. Gemini 1.0 Pro Vision was deprecated on July 12, 2024. Move to a newer Gemini version.",
+      "input_token_limit": 12288,
+      "output_token_limit": 4096,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
@@ -395,7 +404,7 @@
     "created_at": null,
     "display_name": "Gemini 1.5 Flash",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 1000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash",
@@ -405,8 +414,14 @@
     "input_price_per_million": 0.15,
     "output_price_per_million": 0.6,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Alias that points to the most recent stable version of Gemini 1.5 Flash, our fast and versatile multimodal model for scaling across diverse tasks.",
+      "input_token_limit": 1000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
@@ -414,7 +429,7 @@
     "created_at": null,
     "display_name": "Gemini 1.5 Flash 001",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 1000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash",
@@ -424,8 +439,15 @@
     "input_price_per_million": 0.15,
     "output_price_per_million": 0.6,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Stable version of Gemini 1.5 Flash, our fast and versatile multimodal model for scaling across diverse tasks, released in May of 2024.",
+      "input_token_limit": 1000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens",
+        "createCachedContent"
+      ]
     }
   },
   {
@@ -433,7 +455,7 @@
     "created_at": null,
     "display_name": "Gemini 1.5 Flash 001 Tuning",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 16384,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash",
@@ -443,8 +465,15 @@
     "input_price_per_million": 0.15,
     "output_price_per_million": 0.6,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Version of Gemini 1.5 Flash that supports tuning, our fast and versatile multimodal model for scaling across diverse tasks, released in May of 2024.",
+      "input_token_limit": 16384,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens",
+        "createTunedModel"
+      ]
     }
   },
   {
@@ -452,7 +481,7 @@
     "created_at": null,
     "display_name": "Gemini 1.5 Flash 002",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 1000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash",
@@ -462,16 +491,23 @@
     "input_price_per_million": 0.15,
     "output_price_per_million": 0.6,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "002",
+      "description": "Stable version of Gemini 1.5 Flash, our fast and versatile multimodal model for scaling across diverse tasks, released in September of 2024.",
+      "input_token_limit": 1000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens",
+        "createCachedContent"
+      ]
     }
   },
   {
     "id": "gemini-1.5-flash-8b",
     "created_at": null,
-    "display_name": "Gemini 1.5 Flash 8b",
+    "display_name": "Gemini 1.5 Flash-8B",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 1000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash_8b",
@@ -481,16 +517,23 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Stable version of Gemini 1.5 Flash-8B, our smallest and most cost effective Flash model, released in October of 2024.",
+      "input_token_limit": 1000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "createCachedContent",
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-1.5-flash-8b-001",
     "created_at": null,
-    "display_name": "Gemini 1.5 Flash 8b 001",
+    "display_name": "Gemini 1.5 Flash-8B 001",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 1000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash_8b",
@@ -500,16 +543,23 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Stable version of Gemini 1.5 Flash-8B, our smallest and most cost effective Flash model, released in October of 2024.",
+      "input_token_limit": 1000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "createCachedContent",
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-1.5-flash-8b-exp-0827",
     "created_at": null,
-    "display_name": "Gemini 1.5 Flash 8b Exp 0827",
+    "display_name": "Gemini 1.5 Flash 8B Experimental 0827",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 1000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash_8b",
@@ -519,16 +569,22 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Experimental release (August 27th, 2024) of Gemini 1.5 Flash-8B, our smallest and most cost effective Flash model. Replaced by Gemini-1.5-flash-8b-001 (stable).",
+      "input_token_limit": 1000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-1.5-flash-8b-exp-0924",
     "created_at": null,
-    "display_name": "Gemini 1.5 Flash 8b Exp 0924",
+    "display_name": "Gemini 1.5 Flash 8B Experimental 0924",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 1000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash_8b",
@@ -538,16 +594,22 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Experimental release (September 24th, 2024) of Gemini 1.5 Flash-8B, our smallest and most cost effective Flash model. Replaced by Gemini-1.5-flash-8b-001 (stable).",
+      "input_token_limit": 1000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-1.5-flash-8b-latest",
     "created_at": null,
-    "display_name": "Gemini 1.5 Flash 8b Latest",
+    "display_name": "Gemini 1.5 Flash-8B Latest",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 1000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash_8b",
@@ -557,27 +619,15 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-1.5-flash-dark-launch",
-    "created_at": null,
-    "display_name": "Gemini 1.5 Flash Dark Launch",
-    "provider": "gemini",
-    "context_window": 1048576,
-    "max_tokens": 8192,
-    "type": "chat",
-    "family": "gemini15_flash",
-    "supports_vision": true,
-    "supports_functions": true,
-    "supports_json_mode": true,
-    "input_price_per_million": 0.15,
-    "output_price_per_million": 0.6,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Alias that points to the most recent production (non-experimental) release of Gemini 1.5 Flash-8B, our smallest and most cost effective Flash model, released in October of 2024.",
+      "input_token_limit": 1000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "createCachedContent",
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
@@ -585,7 +635,7 @@
     "created_at": null,
     "display_name": "Gemini 1.5 Flash Latest",
     "provider": "gemini",
-    "context_window": 1048576,
+    "context_window": 1000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_flash",
@@ -595,8 +645,14 @@
     "input_price_per_million": 0.15,
     "output_price_per_million": 0.6,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Alias that points to the most recent production (non-experimental) release of Gemini 1.5 Flash, our fast and versatile multimodal model for scaling across diverse tasks.",
+      "input_token_limit": 1000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
@@ -604,7 +660,7 @@
     "created_at": null,
     "display_name": "Gemini 1.5 Pro",
     "provider": "gemini",
-    "context_window": 2097152,
+    "context_window": 2000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_pro",
@@ -614,8 +670,14 @@
     "input_price_per_million": 2.5,
     "output_price_per_million": 10.0,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Stable version of Gemini 1.5 Pro, our mid-size multimodal model that supports up to 2 million tokens, released in May of 2024.",
+      "input_token_limit": 2000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
@@ -623,7 +685,7 @@
     "created_at": null,
     "display_name": "Gemini 1.5 Pro 001",
     "provider": "gemini",
-    "context_window": 2097152,
+    "context_window": 2000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_pro",
@@ -633,8 +695,15 @@
     "input_price_per_million": 2.5,
     "output_price_per_million": 10.0,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Stable version of Gemini 1.5 Pro, our mid-size multimodal model that supports up to 2 million tokens, released in May of 2024.",
+      "input_token_limit": 2000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens",
+        "createCachedContent"
+      ]
     }
   },
   {
@@ -642,7 +711,7 @@
     "created_at": null,
     "display_name": "Gemini 1.5 Pro 002",
     "provider": "gemini",
-    "context_window": 2097152,
+    "context_window": 2000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_pro",
@@ -652,8 +721,15 @@
     "input_price_per_million": 2.5,
     "output_price_per_million": 10.0,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "002",
+      "description": "Stable version of Gemini 1.5 Pro, our mid-size multimodal model that supports up to 2 million tokens, released in September of 2024.",
+      "input_token_limit": 2000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens",
+        "createCachedContent"
+      ]
     }
   },
   {
@@ -661,7 +737,7 @@
     "created_at": null,
     "display_name": "Gemini 1.5 Pro Latest",
     "provider": "gemini",
-    "context_window": 2097152,
+    "context_window": 2000000,
     "max_tokens": 8192,
     "type": "chat",
     "family": "gemini15_pro",
@@ -671,8 +747,14 @@
     "input_price_per_million": 2.5,
     "output_price_per_million": 10.0,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Alias that points to the most recent production (non-experimental) release of Gemini 1.5 Pro, our mid-size multimodal model that supports up to 2 million tokens.",
+      "input_token_limit": 2000000,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
@@ -690,8 +772,14 @@
     "input_price_per_million": 0.1,
     "output_price_per_million": 0.4,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0",
+      "description": "Gemini 2.0 Flash",
+      "input_token_limit": 1048576,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
@@ -709,71 +797,20 @@
     "input_price_per_million": 0.1,
     "output_price_per_million": 0.4,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-2.0-flash-001-bidi-test",
-    "created_at": null,
-    "display_name": "Gemini 2.0 Flash 001 Bidi Test",
-    "provider": "gemini",
-    "context_window": 1048576,
-    "max_tokens": 8192,
-    "type": "chat",
-    "family": "gemini20_flash",
-    "supports_vision": true,
-    "supports_functions": true,
-    "supports_json_mode": true,
-    "input_price_per_million": 0.1,
-    "output_price_per_million": 0.4,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-2.0-flash-audiogen-rev17",
-    "created_at": null,
-    "display_name": "Gemini 2.0 Flash Audiogen Rev17",
-    "provider": "gemini",
-    "context_window": 1048576,
-    "max_tokens": 8192,
-    "type": "chat",
-    "family": "gemini20_flash",
-    "supports_vision": true,
-    "supports_functions": true,
-    "supports_json_mode": true,
-    "input_price_per_million": 0.1,
-    "output_price_per_million": 0.4,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0",
+      "description": "Stable version of Gemini 2.0 Flash, our fast and versatile multimodal model for scaling across diverse tasks, released in January of 2025.",
+      "input_token_limit": 1048576,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-2.0-flash-exp",
     "created_at": null,
-    "display_name": "Gemini 2.0 Flash Exp",
-    "provider": "gemini",
-    "context_window": 1048576,
-    "max_tokens": 8192,
-    "type": "chat",
-    "family": "gemini20_flash",
-    "supports_vision": true,
-    "supports_functions": true,
-    "supports_json_mode": true,
-    "input_price_per_million": 0.1,
-    "output_price_per_million": 0.4,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-2.0-flash-jarvis",
-    "created_at": null,
-    "display_name": "Gemini 2.0 Flash Jarvis",
+    "display_name": "Gemini 2.0 Flash Experimental",
     "provider": "gemini",
     "context_window": 1048576,
     "max_tokens": 8192,
@@ -785,14 +822,21 @@
     "input_price_per_million": 0.1,
     "output_price_per_million": 0.4,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0",
+      "description": "Gemini 2.0 Flash Experimental",
+      "input_token_limit": 1048576,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens",
+        "bidiGenerateContent"
+      ]
     }
   },
   {
     "id": "gemini-2.0-flash-lite",
     "created_at": null,
-    "display_name": "Gemini 2.0 Flash Lite",
+    "display_name": "Gemini 2.0 Flash-Lite",
     "provider": "gemini",
     "context_window": 1048576,
     "max_tokens": 8192,
@@ -804,14 +848,20 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0",
+      "description": "Gemini 2.0 Flash-Lite",
+      "input_token_limit": 1048576,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-2.0-flash-lite-001",
     "created_at": null,
-    "display_name": "Gemini 2.0 Flash Lite 001",
+    "display_name": "Gemini 2.0 Flash-Lite 001",
     "provider": "gemini",
     "context_window": 1048576,
     "max_tokens": 8192,
@@ -823,55 +873,23 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-2.0-flash-mmgen-rev17",
-    "created_at": null,
-    "display_name": "Gemini 2.0 Flash Mmgen Rev17",
-    "provider": "gemini",
-    "context_window": 1048576,
-    "max_tokens": 8192,
-    "type": "chat",
-    "family": "gemini20_flash",
-    "supports_vision": true,
-    "supports_functions": true,
-    "supports_json_mode": true,
-    "input_price_per_million": 0.1,
-    "output_price_per_million": 0.4,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-2.0-flash-thinking-001",
-    "created_at": null,
-    "display_name": "Gemini 2.0 Flash Thinking 001",
-    "provider": "gemini",
-    "context_window": 1048576,
-    "max_tokens": 8192,
-    "type": "chat",
-    "family": "gemini20_flash",
-    "supports_vision": true,
-    "supports_functions": true,
-    "supports_json_mode": true,
-    "input_price_per_million": 0.1,
-    "output_price_per_million": 0.4,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0",
+      "description": "Stable version of Gemini 2.0 Flash Lite",
+      "input_token_limit": 1048576,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-2.0-flash-thinking-exp",
     "created_at": null,
-    "display_name": "Gemini 2.0 Flash Thinking Exp",
+    "display_name": "Gemini 2.0 Flash Thinking Experimental 01-21",
     "provider": "gemini",
     "context_window": 1048576,
-    "max_tokens": 8192,
+    "max_tokens": 65536,
     "type": "chat",
     "family": "gemini20_flash",
     "supports_vision": true,
@@ -880,17 +898,23 @@
     "input_price_per_million": 0.1,
     "output_price_per_million": 0.4,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0-exp-01-21",
+      "description": "Experimental release (January 21st, 2025) of Gemini 2.0 Flash Thinking",
+      "input_token_limit": 1048576,
+      "output_token_limit": 65536,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-2.0-flash-thinking-exp-01-21",
     "created_at": null,
-    "display_name": "Gemini 2.0 Flash Thinking Exp 01 21",
+    "display_name": "Gemini 2.0 Flash Thinking Experimental 01-21",
     "provider": "gemini",
     "context_window": 1048576,
-    "max_tokens": 8192,
+    "max_tokens": 65536,
     "type": "chat",
     "family": "gemini20_flash",
     "supports_vision": true,
@@ -899,36 +923,23 @@
     "input_price_per_million": 0.1,
     "output_price_per_million": 0.4,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0-exp-01-21",
+      "description": "Experimental release (January 21st, 2025) of Gemini 2.0 Flash Thinking",
+      "input_token_limit": 1048576,
+      "output_token_limit": 65536,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-2.0-flash-thinking-exp-1219",
     "created_at": null,
-    "display_name": "Gemini 2.0 Flash Thinking Exp 1219",
-    "provider": "gemini",
-    "context_window": 1048576,
-    "max_tokens": 8192,
-    "type": "chat",
-    "family": "gemini20_flash",
-    "supports_vision": true,
-    "supports_functions": true,
-    "supports_json_mode": true,
-    "input_price_per_million": 0.1,
-    "output_price_per_million": 0.4,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-2.0-flash-thinking-exp-no-thoughts",
-    "created_at": null,
-    "display_name": "Gemini 2.0 Flash Thinking Exp No Thoughts",
+    "display_name": "Gemini 2.0 Flash Thinking Experimental",
     "provider": "gemini",
     "context_window": 1048576,
-    "max_tokens": 8192,
+    "max_tokens": 65536,
     "type": "chat",
     "family": "gemini20_flash",
     "supports_vision": true,
@@ -937,17 +948,23 @@
     "input_price_per_million": 0.1,
     "output_price_per_million": 0.4,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0",
+      "description": "Gemini 2.0 Flash Thinking Experimental",
+      "input_token_limit": 1048576,
+      "output_token_limit": 65536,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-2.0-pro-exp",
     "created_at": null,
-    "display_name": "Gemini 2.0 Pro Exp",
+    "display_name": "Gemini 2.0 Pro Experimental",
     "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
+    "context_window": 2097152,
+    "max_tokens": 8192,
     "type": "chat",
     "family": "other",
     "supports_vision": true,
@@ -956,17 +973,23 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0",
+      "description": "Experimental release (February 5th, 2025) of Gemini 2.0 Pro",
+      "input_token_limit": 2097152,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-2.0-pro-exp-02-05",
     "created_at": null,
-    "display_name": "Gemini 2.0 Pro Exp 02 05",
+    "display_name": "Gemini 2.0 Pro Experimental 02-05",
     "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
+    "context_window": 2097152,
+    "max_tokens": 8192,
     "type": "chat",
     "family": "other",
     "supports_vision": true,
@@ -975,17 +998,23 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0",
+      "description": "Experimental release (February 5th, 2025) of Gemini 2.0 Pro",
+      "input_token_limit": 2097152,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-exp-1206",
     "created_at": null,
-    "display_name": "Gemini Exp 1206",
+    "display_name": "Gemini Experimental 1206",
     "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
+    "context_window": 2097152,
+    "max_tokens": 8192,
     "type": "chat",
     "family": "other",
     "supports_vision": false,
@@ -994,73 +1023,22 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "2.0",
+      "description": "Experimental release (February 5th, 2025) of Gemini 2.0 Pro",
+      "input_token_limit": 2097152,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
     "id": "gemini-pro-vision",
     "created_at": null,
-    "display_name": "Gemini Pro Vision",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-test-23",
-    "created_at": null,
-    "display_name": "Gemini Test 23",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemini-tool-test",
-    "created_at": null,
-    "display_name": "Gemini Tool Test",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "gemma-3-27b-it",
-    "created_at": null,
-    "display_name": "Gemma 3 27b It",
+    "display_name": "Gemini 1.0 Pro Vision",
     "provider": "gemini",
-    "context_window": 32768,
+    "context_window": 12288,
     "max_tokens": 4096,
     "type": "chat",
     "family": "other",
@@ -1070,8 +1048,14 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "The original Gemini 1.0 Pro Vision model version which was optimized for image understanding. Gemini 1.0 Pro Vision was deprecated on July 12, 2024. Move to a newer Gemini version.",
+      "input_token_limit": 12288,
+      "output_token_limit": 4096,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
@@ -1625,51 +1609,13 @@
       "owned_by": "system"
     }
   },
-  {
-    "id": "image-verification-001",
-    "created_at": null,
-    "display_name": "Image Verification 001",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
   {
     "id": "imagen-3.0-generate-002",
     "created_at": null,
-    "display_name": "Imagen 3.0 Generate 002",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "image",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "imagen-3.0-generate-002-exp",
-    "created_at": null,
-    "display_name": "Imagen 3.0 Generate 002 Exp",
+    "display_name": "Imagen 3.0 002 model",
     "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
+    "context_window": 480,
+    "max_tokens": 8192,
     "type": "image",
     "family": "other",
     "supports_vision": false,
@@ -1678,17 +1624,22 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "002",
+      "description": "Vertex served Imagen 3.0 002 model",
+      "input_token_limit": 480,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "predict"
+      ]
     }
   },
   {
     "id": "learnlm-1.5-pro-experimental",
     "created_at": null,
-    "display_name": "Learnlm 1.5 Pro Experimental",
+    "display_name": "LearnLM 1.5 Pro Experimental",
     "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
+    "context_window": 32767,
+    "max_tokens": 8192,
     "type": "chat",
     "family": "other",
     "supports_vision": false,
@@ -1697,8 +1648,14 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "Alias that points to the most recent stable version of Gemini 1.5 Pro, our mid-size multimodal model that supports up to 2 million tokens.",
+      "input_token_limit": 32767,
+      "output_token_limit": 8192,
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens"
+      ]
     }
   },
   {
@@ -1818,67 +1775,10 @@
   {
     "id": "text-bison-001",
     "created_at": null,
-    "display_name": "Text Bison 001",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "text-bison-recitation-off",
-    "created_at": null,
-    "display_name": "Text Bison Recitation Off",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "text-bison-safety-off",
-    "created_at": null,
-    "display_name": "Text Bison Safety Off",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
-  {
-    "id": "text-bison-safety-recitation-off",
-    "created_at": null,
-    "display_name": "Text Bison Safety Recitation Off",
+    "display_name": "PaLM 2 (Legacy)",
     "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
+    "context_window": 8196,
+    "max_tokens": 1024,
     "type": "chat",
     "family": "other",
     "supports_vision": false,
@@ -1887,8 +1787,15 @@
     "input_price_per_million": 0.075,
     "output_price_per_million": 0.3,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "001",
+      "description": "A legacy model that understands text and generates text as an output",
+      "input_token_limit": 8196,
+      "output_token_limit": 1024,
+      "supported_generation_methods": [
+        "generateText",
+        "countTextTokens",
+        "createTunedTextModel"
+      ]
     }
   },
   {
@@ -1897,7 +1804,7 @@
     "display_name": "Text Embedding 004",
     "provider": "gemini",
     "context_window": 2048,
-    "max_tokens": 768,
+    "max_tokens": 1,
     "type": "embedding",
     "family": "embedding4",
     "supports_vision": false,
@@ -1906,8 +1813,13 @@
     "input_price_per_million": 0.0,
     "output_price_per_million": 0.0,
     "metadata": {
-      "object": "model",
-      "owned_by": "google"
+      "version": "004",
+      "description": "Obtain a distributed representation of a text.",
+      "input_token_limit": 2048,
+      "output_token_limit": 1,
+      "supported_generation_methods": [
+        "embedContent"
+      ]
     }
   },
   {
@@ -2043,25 +1955,6 @@
       "owned_by": "system"
     }
   },
-  {
-    "id": "veo-2.0-generate-001",
-    "created_at": null,
-    "display_name": "Veo 2.0 Generate 001",
-    "provider": "gemini",
-    "context_window": 32768,
-    "max_tokens": 4096,
-    "type": "chat",
-    "family": "other",
-    "supports_vision": false,
-    "supports_functions": false,
-    "supports_json_mode": false,
-    "input_price_per_million": 0.075,
-    "output_price_per_million": 0.3,
-    "metadata": {
-      "object": "model",
-      "owned_by": "google"
-    }
-  },
   {
     "id": "whisper-1",
     "created_at": "2023-02-27T22:13:04+01:00",