diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 685e63dcc56..0c60ff26635 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -11216,12 +11216,15 @@
     "babbage-002": {
         "deprecation_date": "2026-09-28",
         "input_cost_per_token": 4e-07,
+        "input_cost_per_token_batches": 2e-07,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
-        "output_cost_per_token": 4e-07
+        "output_cost_per_token": 4e-07,
+        "output_cost_per_token_batches": 2e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "bedrock/*/1-month-commitment/cohere.command-light-text-v14": {
         "input_cost_per_second": 0.001902,
@@ -13286,7 +13289,9 @@
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ],
-        "deprecation_date": "2027-02-26"
+        "deprecation_date": "2027-02-26",
+        "input_cost_per_second": 0.0001,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "claude-haiku-4-5-20251001": {
         "deprecation_date": "2026-10-15",
@@ -13334,7 +13339,8 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-3-7-sonnet-20250219": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -13493,7 +13499,8 @@
         "supports_native_structured_output": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-sonnet-4-5-20250929": {
         "deprecation_date": "2026-09-29",
@@ -13567,7 +13574,7 @@
         },
         "supports_output_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-sonnet-4-6": {
         "deprecation_date": "2027-02-17",
@@ -13603,7 +13610,8 @@
         "prompt_cache_min_tokens": 1024,
         "provider_specific_entry": {
             "us": 1.1
-        }
+        },
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -13780,7 +13788,8 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_output_config": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-6": {
         "deprecation_date": "2027-02-05",
@@ -13817,7 +13826,8 @@
         "supports_output_config": true,
         "supports_max_reasoning_effort": true,
         "supports_speed": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-6-20260205": {
         "deprecation_date": "2027-02-05",
@@ -13892,7 +13902,8 @@
         },
         "supports_output_config": true,
         "supports_speed": true,
-        "prompt_cache_min_tokens": 2048
+        "prompt_cache_min_tokens": 2048,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-7-20260416": {
         "deprecation_date": "2027-04-16",
@@ -13970,7 +13981,7 @@
         "supports_output_config": true,
         "prompt_cache_min_tokens": 512,
         "supports_native_structured_output": true,
-        "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-fable-5-1": {
         "deprecation_date": "2027-09-01",
@@ -14011,7 +14022,7 @@
         "supports_output_config": true,
         "prompt_cache_min_tokens": 512,
         "supports_native_structured_output": true,
-        "source": "https://platform.claude.com/docs/en/models/fable-5-1/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-5": {
         "deprecation_date": "2027-07-24",
@@ -14052,7 +14063,7 @@
         "supports_output_config": true,
         "supports_speed": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-8": {
         "deprecation_date": "2027-05-28",
@@ -14092,7 +14103,8 @@
         },
         "supports_output_config": true,
         "supports_speed": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-sonnet-4-20250514": {
         "deprecation_date": "2026-06-15",
@@ -19361,12 +19373,15 @@
     "davinci-002": {
         "deprecation_date": "2026-09-28",
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 1e-06,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "deepgram/base": {
         "input_cost_per_second": 0.00020833,
@@ -22413,15 +22428,18 @@
         "supports_vision": false
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": {
-        "cache_read_input_token_cost": 1.45e-07,
-        "input_cost_per_token": 1.74e-06,
+        "cache_read_input_token_cost": 6e-07,
+        "cache_read_input_token_cost_priority": 6e-07,
+        "input_cost_per_token": 1.2e-06,
+        "input_cost_per_token_priority": 1.2e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 384000,
         "max_tokens": 384000,
         "mode": "chat",
-        "output_cost_per_token": 3.48e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.2e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22430,14 +22448,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": {
         "cache_read_input_token_cost": 4.4e-08,
+        "cache_read_input_token_cost_priority": 5.5e-08,
         "input_cost_per_token": 1.32e-06,
+        "input_cost_per_token_priority": 1.65e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 3.96e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 4.95e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22532,14 +22553,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/glm-5p2": {
         "cache_read_input_token_cost": 1.4e-07,
+        "cache_read_input_token_cost_priority": 1.75e-07,
         "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_priority": 1.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 5.5e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22548,14 +22572,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": {
         "cache_read_input_token_cost": 1.5e-08,
+        "cache_read_input_token_cost_priority": 1.8e-08,
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_priority": 1.8e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 7.2e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22634,14 +22661,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/kimi-k2p6": {
         "cache_read_input_token_cost": 1.6e-07,
+        "cache_read_input_token_cost_priority": 2.2e-07,
         "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_priority": 1.5e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22650,14 +22680,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/kimi-k2p7-code": {
         "cache_read_input_token_cost": 1.9e-07,
+        "cache_read_input_token_cost_priority": 2.85e-07,
         "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_priority": 1.425e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22783,14 +22816,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/minimax-m2p7": {
         "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_priority": 6e-07,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 1.2e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 196608,
         "max_output_tokens": 196608,
         "max_tokens": 196608,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 1.2e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22799,14 +22835,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/minimax-m3": {
         "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 512000,
         "max_output_tokens": 512000,
         "max_tokens": 512000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 1.8e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22882,15 +22921,18 @@
         "supports_vision": false
     },
     "fireworks_ai/deepseek-v4-pro": {
-        "cache_read_input_token_cost": 1.45e-07,
-        "input_cost_per_token": 1.74e-06,
+        "cache_read_input_token_cost": 6e-07,
+        "cache_read_input_token_cost_priority": 6e-07,
+        "input_cost_per_token": 1.2e-06,
+        "input_cost_per_token_priority": 1.2e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 384000,
         "max_tokens": 384000,
         "mode": "chat",
-        "output_cost_per_token": 3.48e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.2e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22946,14 +22988,17 @@
     },
     "fireworks_ai/glm-5p2": {
         "cache_read_input_token_cost": 1.4e-07,
+        "cache_read_input_token_cost_priority": 1.75e-07,
         "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_priority": 1.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 5.5e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22962,14 +23007,17 @@
     },
     "fireworks_ai/gpt-oss-120b": {
         "cache_read_input_token_cost": 1.5e-08,
+        "cache_read_input_token_cost_priority": 1.8e-08,
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_priority": 1.8e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 7.2e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23008,14 +23056,17 @@
     },
     "fireworks_ai/kimi-k2p6": {
         "cache_read_input_token_cost": 1.6e-07,
+        "cache_read_input_token_cost_priority": 2.2e-07,
         "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_priority": 1.5e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23040,14 +23091,17 @@
     },
     "fireworks_ai/kimi-k2p7-code": {
         "cache_read_input_token_cost": 1.9e-07,
+        "cache_read_input_token_cost_priority": 2.85e-07,
         "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_priority": 1.425e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23086,14 +23140,17 @@
     },
     "fireworks_ai/minimax-m2p7": {
         "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_priority": 6e-07,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 1.2e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 196608,
         "max_output_tokens": 196608,
         "max_tokens": 196608,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 1.2e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23102,14 +23159,17 @@
     },
     "fireworks_ai/minimax-m3": {
         "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 512000,
         "max_output_tokens": 512000,
         "max_tokens": 512000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 1.8e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23125,7 +23185,7 @@
         "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 1.6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23374,26 +23434,28 @@
     "ft:babbage-002": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.6e-06,
-        "input_cost_per_token_batches": 2e-07,
+        "input_cost_per_token_batches": 8e-07,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
         "output_cost_per_token": 1.6e-06,
-        "output_cost_per_token_batches": 2e-07
+        "output_cost_per_token_batches": 9e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "ft:davinci-002": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.2e-05,
-        "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_batches": 6e-06,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
         "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_batches": 1e-06
+        "output_cost_per_token_batches": 6e-06,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "ft:gpt-3.5-turbo": {
         "deprecation_date": "2026-10-23",
@@ -23406,6 +23468,7 @@
         "mode": "chat",
         "output_cost_per_token": 6e-06,
         "output_cost_per_token_batches": 3e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_system_messages": true,
         "supports_tool_choice": true
     },
@@ -23462,14 +23525,15 @@
     "ft:gpt-4o-2024-08-06": {
         "cache_read_input_token_cost": 1.875e-06,
         "input_cost_per_token": 3.75e-06,
-        "input_cost_per_token_batches": 1.875e-06,
+        "input_cost_per_token_batches": 2.225e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
-        "output_cost_per_token_batches": 7.5e-06,
+        "output_cost_per_token_batches": 1.25e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -23507,6 +23571,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
         "output_cost_per_token_batches": 6e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -23526,6 +23591,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_batches": 6e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -23544,6 +23610,7 @@
         "mode": "chat",
         "output_cost_per_token": 3.2e-06,
         "output_cost_per_token_batches": 1.6e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -23563,6 +23630,7 @@
         "mode": "chat",
         "output_cost_per_token": 8e-07,
         "output_cost_per_token_batches": 4e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -23582,6 +23650,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.6e-05,
         "output_cost_per_token_batches": 8e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_prompt_caching": true,
@@ -23592,15 +23661,18 @@
     "gemini-2.0-flash": {
         "cache_read_input_token_cost": 2.5e-08,
         "deprecation_date": "2026-06-01",
-        "input_cost_per_audio_token": 7e-07,
-        "input_cost_per_token": 1e-07,
+        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_character": 3.75e-08,
+        "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "source": "https://ai.google.dev/pricing#2_0flash",
+        "output_cost_per_token": 6e-07,
+        "output_cost_per_token_batches": 3e-07,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_modalities": [
             "text",
             "image",
@@ -23669,13 +23741,16 @@
         "cache_read_input_token_cost": 1.875e-08,
         "deprecation_date": "2026-06-01",
         "input_cost_per_audio_token": 7.5e-08,
+        "input_cost_per_character": 1.875e-08,
         "input_cost_per_token": 7.5e-08,
+        "input_cost_per_token_batches": 3.75e-08,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+        "output_cost_per_token_batches": 1.5e-07,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_modalities": [
             "text",
             "image",
@@ -23736,8 +23811,11 @@
         }
     },
     "gemini-2.5-flash": {
+        "cache_read_input_audio_token_cost": 1e-07,
         "deprecation_date": "2026-10-20",
         "cache_read_input_token_cost": 3e-08,
+        "cache_read_input_token_cost_flex": 3e-08,
+        "cache_read_input_token_cost_priority": 5.4e-08,
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -23747,7 +23825,7 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 2.5e-06,
         "output_cost_per_token": 2.5e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -23780,6 +23858,12 @@
             "search_context_size_high": 0.035
         },
         "google_maps_grounding_cost_per_query": 0.025,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.4e-07,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "output_cost_per_token_priority": 4.5e-06,
         "supports_image_size": false
     },
     "gemini-2.5-flash-image": {
@@ -23787,6 +23871,9 @@
         "cache_read_input_token_cost": 3e-08,
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.4e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 32768,
         "max_output_tokens": 32768,
@@ -23796,8 +23883,10 @@
         "output_cost_per_image_token": 3e-05,
         "output_cost_per_reasoning_token": 2.5e-06,
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_flex": 1.25e-06,
         "rpm": 100000,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -23828,10 +23917,19 @@
         "supports_image_size": false
     },
     "gemini-3-pro-image": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -23840,8 +23938,12 @@
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image",
+        "output_cost_per_token_flex": 6e-06,
+        "output_cost_per_token_priority": 2.16e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -23909,9 +24011,13 @@
         "web_search_billing_unit": "per_query"
     },
     "gemini-3.1-flash-image": {
+        "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost_flex": 2.5e-08,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -23920,7 +24026,9 @@
         "output_cost_per_image": 0.0672,
         "output_cost_per_image_token": 6e-05,
         "output_cost_per_token": 3e-06,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -23987,9 +24095,11 @@
     },
     "gemini-3.1-flash-lite-image": {
         "cache_read_input_token_cost": 2.5e-08,
+        "cache_read_input_token_cost_flex": 1.25e-08,
         "input_cost_per_image": 0.00028,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
+        "input_cost_per_token_flex": 1.25e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 4096,
@@ -23999,6 +24109,7 @@
         "output_cost_per_image_token": 3e-05,
         "output_cost_per_token": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-07,
+        "output_cost_per_token_flex": 7.5e-07,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -24073,6 +24184,7 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "gemini-3.1-flash-lite": {
+        "cache_read_input_audio_token_cost": 5e-08,
         "deprecation_date": "2027-05-07",
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
@@ -24092,7 +24204,7 @@
         "output_cost_per_token_batches": 7.5e-07,
         "output_cost_per_token_flex": 7.5e-07,
         "output_cost_per_token_priority": 2.7e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24134,7 +24246,7 @@
         "deprecation_date": "2027-07-21",
         "cache_read_input_token_cost": 3e-08,
         "cache_read_input_token_cost_flex": 1.5e-08,
-        "cache_read_input_token_cost_priority": 5e-08,
+        "cache_read_input_token_cost_priority": 5.4e-08,
         "input_cost_per_token": 3e-07,
         "input_cost_per_token_batches": 1.5e-07,
         "input_cost_per_token_flex": 1.5e-07,
@@ -24149,7 +24261,7 @@
         "output_cost_per_token_batches": 1.25e-06,
         "output_cost_per_token_flex": 1.25e-06,
         "output_cost_per_token_priority": 4.5e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24188,6 +24300,7 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "deep-research-pro-preview-12-2025": {
+        "cache_read_input_token_cost": 2e-07,
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -24200,7 +24313,7 @@
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_batches": 6e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24222,8 +24335,11 @@
         "supports_web_search": true
     },
     "gemini-2.5-flash-lite": {
+        "cache_read_input_audio_token_cost": 3e-08,
         "deprecation_date": "2026-10-20",
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_flex": 1e-08,
+        "cache_read_input_token_cost_priority": 1.8e-08,
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -24233,7 +24349,7 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 4e-07,
         "output_cost_per_token": 4e-07,
-        "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24266,6 +24382,12 @@
             "search_context_size_high": 0.035
         },
         "google_maps_grounding_cost_per_query": 0.025,
+        "input_cost_per_token_batches": 5e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "input_cost_per_token_priority": 1.8e-07,
+        "output_cost_per_token_batches": 2e-07,
+        "output_cost_per_token_flex": 2e-07,
+        "output_cost_per_token_priority": 7.2e-07,
         "supports_image_size": false
     },
     "gemini-2.5-flash-lite-preview-09-2025": {
@@ -24417,7 +24539,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_token": 2e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/vertex_ai/live"
         ],
@@ -24448,7 +24570,8 @@
             "search_context_size_medium": 0.035,
             "search_context_size_high": 0.035
         },
-        "gemini_native_audio": true
+        "gemini_native_audio": true,
+        "input_cost_per_image_token": 3e-06
     },
     "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -24548,6 +24671,9 @@
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
         "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07,
+        "cache_read_input_token_cost_flex": 1.25e-07,
+        "cache_read_input_token_cost_priority": 2.25e-07,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "vertex_ai-language-models",
@@ -24557,7 +24683,7 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions"
@@ -24587,7 +24713,15 @@
             "search_context_size_medium": 0.035,
             "search_context_size_high": 0.035
         },
-        "google_maps_grounding_cost_per_query": 0.025
+        "google_maps_grounding_cost_per_query": 0.025,
+        "input_cost_per_token_above_200k_tokens_priority": 4.5e-06,
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_flex": 6.25e-07,
+        "input_cost_per_token_priority": 2.25e-06,
+        "output_cost_per_token_above_200k_tokens_priority": 2.7e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "output_cost_per_token_priority": 1.8e-05
     },
     "gemini-3-pro-preview": {
         "deprecation_date": "2026-03-26",
@@ -24662,7 +24796,7 @@
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
         "output_cost_per_token_batches": 6e-06,
         "output_cost_per_image": 0.00012,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24696,13 +24830,16 @@
         "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "cache_read_input_token_cost_priority": 3.6e-07,
         "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_flex": 2e-07,
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
             "search_context_size_high": 0.014
         },
         "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token_flex": 1e-06,
+        "output_cost_per_token_flex": 6e-06
     },
     "gemini-3.1-pro-preview-customtools": {
         "prompt_cache_min_tokens": 4096,
@@ -24813,7 +24950,9 @@
         "web_search_billing_unit": "per_query"
     },
     "vertex_ai/gemini-3-flash-preview": {
+        "cache_read_input_audio_token_cost": 1e-07,
         "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
         "input_cost_per_token": 5e-07,
         "input_cost_per_audio_token": 1e-06,
         "litellm_provider": "vertex_ai",
@@ -24822,7 +24961,7 @@
         "max_tokens": 65535,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24859,7 +24998,11 @@
             "search_context_size_high": 0.014
         },
         "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06
     },
     "vertex_ai/gemini-3.5-flash": {
         "prompt_cache_min_tokens": 4096,
@@ -24875,7 +25018,7 @@
         "output_cost_per_reasoning_token": 9e-06,
         "output_cost_per_token": 9e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24938,7 +25081,7 @@
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24995,7 +25138,7 @@
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -25052,7 +25195,7 @@
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -25109,7 +25252,7 @@
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
         "output_cost_per_token_batches": 6e-06,
         "output_cost_per_image": 0.00012,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -25143,13 +25286,16 @@
         "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "cache_read_input_token_cost_priority": 3.6e-07,
         "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_flex": 2e-07,
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
             "search_context_size_high": 0.014
         },
         "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token_flex": 1e-06,
+        "output_cost_per_token_flex": 6e-06
     },
     "vertex_ai/gemini-3.1-pro-preview-customtools": {
         "prompt_cache_min_tokens": 4096,
@@ -25214,13 +25360,15 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_audio_token": 7e-07,
         "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65535,
         "max_tokens": 65535,
         "mode": "chat",
+        "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2e-05,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_modalities": [
             "text"
         ],
@@ -25427,7 +25575,7 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_modalities": [
             "text",
             "image"
@@ -25468,8 +25616,11 @@
     },
     "gemini-embedding-2": {
         "input_cost_per_audio_per_second": 0.00016,
+        "input_cost_per_audio_token": 6.5e-06,
         "input_cost_per_image": 0.00012,
+        "input_cost_per_image_token": 4.5e-07,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_batches": 1e-07,
         "input_cost_per_video_per_second": 0.00079,
         "litellm_provider": "vertex_ai-embedding-models",
         "max_input_tokens": 8192,
@@ -25477,7 +25628,7 @@
         "mode": "embedding",
         "output_cost_per_token": 0,
         "output_vector_size": 3072,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supports_multimodal": true,
         "uses_embed_content": true
     },
@@ -25498,8 +25649,11 @@
     },
     "vertex_ai/gemini-embedding-2": {
         "input_cost_per_audio_per_second": 0.00016,
+        "input_cost_per_audio_token": 6.5e-06,
         "input_cost_per_image": 0.00012,
+        "input_cost_per_image_token": 4.5e-07,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_batches": 1e-07,
         "input_cost_per_video_per_second": 0.00079,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 8192,
@@ -25507,7 +25661,7 @@
         "mode": "embedding",
         "output_cost_per_token": 0,
         "output_vector_size": 3072,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supports_multimodal": true,
         "uses_embed_content": true
     },
@@ -27141,7 +27295,9 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "gemini-3-flash-preview": {
+        "cache_read_input_audio_token_cost": 1e-07,
         "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -27151,7 +27307,7 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 3e-06,
         "output_cost_per_token": 3e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -27189,7 +27345,11 @@
             "search_context_size_high": 0.014
         },
         "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06
     },
     "gemini-omni-flash-preview": {
         "input_cost_per_audio_token": 1.5e-06,
@@ -27202,7 +27362,7 @@
         "output_cost_per_reasoning_token": 9e-06,
         "output_cost_per_token": 9e-06,
         "output_cost_per_video_token": 1.75e-05,
-        "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -27235,7 +27395,7 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 9e-06,
         "output_cost_per_token": 9e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -27298,7 +27458,7 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -27355,7 +27515,7 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -27412,7 +27572,7 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -28870,6 +29030,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_system_messages": true,
@@ -28878,12 +29039,15 @@
     "gpt-3.5-turbo-0125": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token_batches": 7.5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -28893,12 +29057,15 @@
     "gpt-3.5-turbo-1106": {
         "deprecation_date": "2026-09-28",
         "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 2e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -28926,7 +29093,8 @@
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2e-06,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-3.5-turbo-instruct-0914": {
         "input_cost_per_token": 1.5e-06,
@@ -28981,12 +29149,15 @@
     "gpt-4-0613": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-05,
+        "input_cost_per_token_batches": 1.5e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 8192,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-05,
+        "output_cost_per_token_batches": 3e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_system_messages": true,
@@ -29027,12 +29198,15 @@
     "gpt-4-turbo-2024-04-09": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-05,
+        "input_cost_per_token_batches": 5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 3e-05,
+        "output_cost_per_token_batches": 1.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29076,6 +29250,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29118,6 +29293,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29160,6 +29336,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29202,6 +29379,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29240,6 +29418,7 @@
         "output_cost_per_token": 4e-07,
         "output_cost_per_token_batches": 2e-07,
         "output_cost_per_token_priority": 8e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29277,6 +29456,7 @@
         "output_cost_per_token": 4e-07,
         "output_cost_per_token_priority": 8e-07,
         "output_cost_per_token_batches": 2e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29313,6 +29493,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_batches": 5e-06,
         "output_cost_per_token_priority": 1.7e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29335,6 +29516,7 @@
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_batches": 7.5e-06,
         "output_cost_per_token_priority": 2.625e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29357,6 +29539,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_priority": 1.7e-05,
         "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29380,6 +29563,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_priority": 1.7e-05,
         "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29454,6 +29638,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses",
@@ -29490,6 +29675,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -29524,6 +29710,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses",
@@ -29561,6 +29748,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses",
@@ -29598,6 +29786,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses",
@@ -29659,7 +29848,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": false,
-        "deprecation_date": "2027-01-20"
+        "deprecation_date": "2027-01-20",
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-4o-mini": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -29687,7 +29877,8 @@
             "search_context_size_high": 0.025,
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
-        }
+        },
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -29708,6 +29899,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29856,15 +30048,18 @@
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ],
-        "deprecation_date": "2027-02-26"
+        "deprecation_date": "2027-02-26",
+        "input_cost_per_second": 5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-4o-mini-tts": {
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "mode": "audio_speech",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_second": 0.00025,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ],
@@ -29996,7 +30191,9 @@
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ],
-        "deprecation_date": "2027-02-26"
+        "deprecation_date": "2027-02-26",
+        "input_cost_per_second": 0.0001,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-image-1.5": {
         "cache_read_input_token_cost": 1.25e-06,
@@ -30006,7 +30203,10 @@
         "mode": "image_generation",
         "output_cost_per_token": 1e-05,
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations"
         ],
@@ -30021,7 +30221,10 @@
         "mode": "image_generation",
         "output_cost_per_token": 1e-05,
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations"
         ],
@@ -30034,7 +30237,9 @@
         "litellm_provider": "openai",
         "mode": "image_generation",
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -30481,6 +30686,7 @@
         "cache_read_input_token_cost_flex": 6.25e-08,
         "cache_read_input_token_cost_priority": 2.5e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 6.25e-07,
         "input_cost_per_token_flex": 6.25e-07,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -30489,6 +30695,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
         "output_cost_per_token_flex": 5e-06,
         "output_cost_per_token_priority": 2e-05,
         "search_context_cost_per_query": {
@@ -30496,6 +30703,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -30525,6 +30733,7 @@
     },
     "gpt-5.1": {
         "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_flex": 6.25e-08,
         "cache_read_input_token_cost_priority": 2.5e-07,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
@@ -30565,11 +30774,17 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_flex": 6.25e-07,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false
     },
     "gpt-5.1-2025-11-13": {
         "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_flex": 6.25e-08,
         "cache_read_input_token_cost_priority": 2.5e-07,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
@@ -30610,6 +30825,11 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_flex": 6.25e-07,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false
     },
@@ -30661,6 +30881,7 @@
     },
     "gpt-5.2": {
         "cache_read_input_token_cost": 1.75e-07,
+        "cache_read_input_token_cost_flex": 8.75e-08,
         "cache_read_input_token_cost_priority": 3.5e-07,
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
@@ -30702,11 +30923,17 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "input_cost_per_token_batches": 8.75e-07,
+        "input_cost_per_token_flex": 8.75e-07,
+        "output_cost_per_token_batches": 7e-06,
+        "output_cost_per_token_flex": 7e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
     "gpt-5.2-2025-12-11": {
         "cache_read_input_token_cost": 1.75e-07,
+        "cache_read_input_token_cost_flex": 8.75e-08,
         "cache_read_input_token_cost_priority": 3.5e-07,
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
@@ -30748,6 +30975,11 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "input_cost_per_token_batches": 8.75e-07,
+        "input_cost_per_token_flex": 8.75e-07,
+        "output_cost_per_token_batches": 7e-06,
+        "output_cost_per_token_flex": 7e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -30841,17 +31073,20 @@
     },
     "gpt-5.2-pro": {
         "input_cost_per_token": 2.1e-05,
+        "input_cost_per_token_batches": 1.05e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.000168,
+        "output_cost_per_token_batches": 8.4e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/batch",
             "/v1/responses"
@@ -30880,17 +31115,20 @@
     },
     "gpt-5.2-pro-2025-12-11": {
         "input_cost_per_token": 2.1e-05,
+        "input_cost_per_token_batches": 1.05e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.000168,
+        "output_cost_per_token_batches": 8.4e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/batch",
             "/v1/responses"
@@ -30956,6 +31194,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -31092,6 +31331,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -31160,6 +31400,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -31227,6 +31468,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -31290,7 +31532,7 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "source": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_computer_use": true,
         "supports_parallel_function_calling": true
     },
@@ -31460,7 +31702,7 @@
         "reasoning_effort_levels": [
             "medium"
         ],
-        "source": "https://developers.openai.com/api/docs/models/chat-latest",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -31539,7 +31781,8 @@
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 5e-06,
         "output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
-        "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
+        "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.5-2026-04-23": {
         "cache_read_input_token_cost": 5e-07,
@@ -31596,7 +31839,8 @@
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 5e-06,
         "output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
-        "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
+        "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.5-pro": {
         "input_cost_per_token": 3e-05,
@@ -31619,6 +31863,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -31667,6 +31912,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -31744,7 +31990,8 @@
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
         "output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
-        "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
+        "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.4-2026-03-05": {
         "cache_read_input_token_cost": 2.5e-07,
@@ -31796,7 +32043,8 @@
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
         "output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
-        "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
+        "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.4-pro": {
         "input_cost_per_token": 3e-05,
@@ -31845,7 +32093,8 @@
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 3e-05,
-        "output_cost_per_token_above_272k_tokens_flex": 0.000135
+        "output_cost_per_token_above_272k_tokens_flex": 0.000135,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.4-pro-2026-03-05": {
         "input_cost_per_token": 3e-05,
@@ -31894,7 +32143,8 @@
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 3e-05,
-        "output_cost_per_token_above_272k_tokens_flex": 0.000135
+        "output_cost_per_token_above_272k_tokens_flex": 0.000135,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.4-mini": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -31945,6 +32195,7 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -31997,6 +32248,7 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -32046,6 +32298,7 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -32095,6 +32348,7 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -32113,6 +32367,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/batch",
             "/v1/responses"
@@ -32155,6 +32410,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/batch",
             "/v1/responses"
@@ -32187,6 +32443,7 @@
         "cache_read_input_token_cost_priority": 2.5e-07,
         "deprecation_date": "2026-12-11",
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 6.25e-07,
         "input_cost_per_token_flex": 6.25e-07,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -32195,6 +32452,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
         "output_cost_per_token_flex": 5e-06,
         "output_cost_per_token_priority": 2e-05,
         "search_context_cost_per_query": {
@@ -32202,6 +32460,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32526,6 +32785,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses"
         ],
@@ -32556,6 +32816,7 @@
         "cache_read_input_token_cost_flex": 1.25e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
         "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "openai",
@@ -32564,6 +32825,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 1e-06,
         "output_cost_per_token_flex": 1e-06,
         "output_cost_per_token_priority": 3.6e-06,
         "search_context_cost_per_query": {
@@ -32571,6 +32833,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32604,6 +32867,7 @@
         "cache_read_input_token_cost_priority": 4.5e-08,
         "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "openai",
@@ -32612,6 +32876,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 1e-06,
         "output_cost_per_token_flex": 1e-06,
         "output_cost_per_token_priority": 3.6e-06,
         "search_context_cost_per_query": {
@@ -32619,6 +32884,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32650,6 +32916,7 @@
         "cache_read_input_token_cost": 5e-09,
         "cache_read_input_token_cost_flex": 2.5e-09,
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_batches": 2.5e-08,
         "input_cost_per_token_flex": 2.5e-08,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -32658,12 +32925,14 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_batches": 2e-07,
         "output_cost_per_token_flex": 2e-07,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32696,6 +32965,7 @@
         "cache_read_input_token_cost_flex": 2.5e-09,
         "deprecation_date": "2026-12-11",
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_batches": 2.5e-08,
         "input_cost_per_token_priority": 2.5e-06,
         "input_cost_per_token_flex": 2.5e-08,
         "litellm_provider": "openai",
@@ -32704,12 +32974,14 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_batches": 2e-07,
         "output_cost_per_token_flex": 2e-07,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32742,9 +33014,11 @@
         "deprecation_date": "2026-10-23",
         "input_cost_per_image_token": 1e-05,
         "input_cost_per_token": 5e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
         "output_cost_per_image_token": 4e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -32755,9 +33029,11 @@
         "deprecation_date": "2026-12-01",
         "input_cost_per_image_token": 2.5e-06,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
         "output_cost_per_image_token": 8e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -32778,6 +33054,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1.6e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32811,6 +33088,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1.6e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32844,6 +33122,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 2.4e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32879,6 +33158,7 @@
         "output_cost_per_token": 2.4e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32914,6 +33194,7 @@
         "output_cost_per_token": 2.4e-06,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32939,6 +33220,7 @@
         "cache_read_input_token_cost": 6e-08,
         "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_image_token": 8e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 32000,
@@ -32947,6 +33229,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32981,6 +33264,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1.6e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -37700,12 +37984,15 @@
         "cache_read_input_token_cost": 7.5e-06,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.5e-05,
+        "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 6e-05,
+        "output_cost_per_token_batches": 3e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_pdf_input": true,
@@ -37720,12 +38007,15 @@
         "cache_read_input_token_cost": 7.5e-06,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.5e-05,
+        "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 6e-05,
+        "output_cost_per_token_batches": 3e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -37747,6 +38037,7 @@
         "mode": "responses",
         "output_cost_per_token": 0.0006,
         "output_cost_per_token_batches": 0.0003,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -37780,6 +38071,7 @@
         "mode": "responses",
         "output_cost_per_token": 0.0006,
         "output_cost_per_token_batches": 0.0003,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -37807,6 +38099,7 @@
         "cache_read_input_token_cost_flex": 2.5e-07,
         "cache_read_input_token_cost_priority": 8.75e-07,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "input_cost_per_token_flex": 1e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -37815,6 +38108,7 @@
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 8e-06,
+        "output_cost_per_token_batches": 4e-06,
         "output_cost_per_token_flex": 4e-06,
         "output_cost_per_token_priority": 1.4e-05,
         "search_context_cost_per_query": {
@@ -37822,6 +38116,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/chat/completions",
@@ -37851,6 +38146,7 @@
         "cache_read_input_token_cost_priority": 8.75e-07,
         "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "input_cost_per_token_flex": 1e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -37859,6 +38155,7 @@
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 8e-06,
+        "output_cost_per_token_batches": 4e-06,
         "output_cost_per_token_flex": 4e-06,
         "output_cost_per_token_priority": 1.4e-05,
         "search_context_cost_per_query": {
@@ -37866,6 +38163,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/chat/completions",
@@ -37975,12 +38273,15 @@
         "cache_read_input_token_cost": 5.5e-07,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
+        "input_cost_per_token_batches": 5.5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "output_cost_per_token_batches": 2.2e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_prompt_caching": true,
@@ -37993,12 +38294,15 @@
         "cache_read_input_token_cost": 5.5e-07,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
+        "input_cost_per_token_batches": 5.5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "output_cost_per_token_batches": 2.2e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_prompt_caching": true,
@@ -38022,6 +38326,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -38059,6 +38364,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -38082,10 +38388,11 @@
     },
     "o4-mini": {
         "cache_read_input_token_cost": 2.75e-07,
-        "cache_read_input_token_cost_flex": 1.375e-07,
+        "cache_read_input_token_cost_flex": 1.38e-07,
         "cache_read_input_token_cost_priority": 5e-07,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
+        "input_cost_per_token_batches": 5.5e-07,
         "input_cost_per_token_flex": 5.5e-07,
         "input_cost_per_token_priority": 2e-06,
         "litellm_provider": "openai",
@@ -38094,6 +38401,7 @@
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "output_cost_per_token_batches": 2.2e-06,
         "output_cost_per_token_flex": 2.2e-06,
         "output_cost_per_token_priority": 8e-06,
         "search_context_cost_per_query": {
@@ -38101,6 +38409,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_pdf_input": true,
@@ -38113,10 +38422,11 @@
     },
     "o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 2.75e-07,
-        "cache_read_input_token_cost_flex": 1.375e-07,
+        "cache_read_input_token_cost_flex": 1.38e-07,
         "cache_read_input_token_cost_priority": 5e-07,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
+        "input_cost_per_token_batches": 5.5e-07,
         "input_cost_per_token_flex": 5.5e-07,
         "input_cost_per_token_priority": 2e-06,
         "litellm_provider": "openai",
@@ -38125,6 +38435,7 @@
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "output_cost_per_token_batches": 2.2e-06,
         "output_cost_per_token_flex": 2.2e-06,
         "output_cost_per_token_priority": 8e-06,
         "search_context_cost_per_query": {
@@ -38132,6 +38443,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_pdf_input": true,
@@ -43294,7 +43606,8 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0,
         "output_cost_per_token_batches": 0.0,
-        "output_vector_size": 3072
+        "output_vector_size": 3072,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "text-embedding-3-small": {
         "input_cost_per_token": 2e-08,
@@ -43305,7 +43618,8 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0,
         "output_cost_per_token_batches": 0.0,
-        "output_vector_size": 1536
+        "output_vector_size": 1536,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "text-embedding-ada-002": {
         "input_cost_per_token": 1e-07,
@@ -43314,7 +43628,8 @@
         "max_tokens": 8191,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "output_vector_size": 1536
+        "output_vector_size": 1536,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "text-embedding-ada-002-v2": {
         "input_cost_per_token": 1e-07,
@@ -43485,7 +43800,7 @@
         "input_cost_per_token": 1.2e-06,
         "output_cost_per_token": 1.2e-06,
         "max_input_tokens": 131072,
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": {
         "litellm_provider": "together_ai",
@@ -43497,7 +43812,7 @@
         "input_cost_per_token": 3e-07,
         "output_cost_per_token": 3e-07,
         "max_input_tokens": 32768,
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
         "deprecation_date": "2026-07-10",
@@ -43544,7 +43859,7 @@
         "max_input_tokens": 256000,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
-        "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43606,7 +43921,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 1.7e-06,
-        "source": "https://www.together.ai/models/deepseek-v3-1",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43630,7 +43945,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.04e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43664,6 +43979,7 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 5.9e-07,
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43686,6 +44002,7 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 8.8e-07,
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43697,6 +44014,7 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 1.8e-07,
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43713,7 +44031,7 @@
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
         "max_input_tokens": 32768,
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": {
         "deprecation_date": "2026-04-02",
@@ -43725,7 +44043,7 @@
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 3e-07,
         "max_input_tokens": 32768,
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": {
         "deprecation_date": "2026-04-16",
@@ -43733,6 +44051,7 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 6e-07,
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43759,7 +44078,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://www.together.ai/models/gpt-oss-120b",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43773,7 +44092,7 @@
         "max_input_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://www.together.ai/models/gpt-oss-20b",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43793,7 +44112,7 @@
         "max_input_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.1e-06,
-        "source": "https://www.together.ai/models/glm-4-5-air",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43809,7 +44128,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 2.2e-06,
-        "source": "https://www.together.ai/models/glm-4-6",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43826,7 +44145,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 2e-06,
-        "source": "https://www.together.ai/models/glm-4-7",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43874,7 +44193,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43890,7 +44209,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43904,7 +44223,7 @@
         "max_input_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
-        "source": "https://www.together.ai/models/qwen3-5-397b-a17b",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -43919,7 +44238,7 @@
         "max_tokens": 524288,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -43944,7 +44263,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 2.5e-07,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43959,7 +44278,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_reasoning": true
     },
     "together_ai/Qwen/Qwen3.7-Max": {
@@ -43970,7 +44289,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 7.5e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
     "together_ai/Qwen/Qwen3.7-Plus": {
@@ -43980,7 +44299,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 1.28e-06,
-        "source": "https://docs.together.ai/docs/serverless-models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3.8-2.4T-A95B": {
         "cache_read_input_token_cost": 2.5e-07,
@@ -43990,7 +44309,7 @@
         "max_tokens": 1010000,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
     "together_ai/arize-ai/qwen-2-1.5b-instruct": {
@@ -44000,7 +44319,7 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
-        "source": "https://docs.together.ai/docs/serverless-models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": {
         "cache_read_input_token_cost": 3e-08,
@@ -44010,7 +44329,7 @@
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 2.8e-07,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44042,7 +44361,7 @@
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 3.96e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44067,7 +44386,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 9.7e-07,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -44103,7 +44422,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
     "together_ai/moonshotai/Kimi-K2.7-Code": {
@@ -44115,7 +44434,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44136,7 +44455,7 @@
             "high",
             "max"
         ],
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44154,7 +44473,7 @@
         "max_tokens": 512288,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44180,7 +44499,7 @@
         "max_tokens": 524288,
         "mode": "chat",
         "output_cost_per_token": 4.05e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44196,7 +44515,7 @@
         "max_tokens": 524288,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
     "together_ai/zai-org/GLM-5.2": {
@@ -44208,7 +44527,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44225,7 +44544,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44242,7 +44561,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44255,6 +44574,7 @@
         "input_cost_per_character": 1.5e-05,
         "litellm_provider": "openai",
         "mode": "audio_speech",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ]
@@ -44263,6 +44583,7 @@
         "input_cost_per_character": 3e-05,
         "litellm_provider": "openai",
         "mode": "audio_speech",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ]
@@ -47605,6 +47926,9 @@
         "cache_read_input_token_cost": 3e-08,
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.4e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 32768,
         "max_output_tokens": 32768,
@@ -47614,8 +47938,10 @@
         "output_cost_per_image_token": 3e-05,
         "output_cost_per_reasoning_token": 2.5e-06,
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_flex": 1.25e-06,
         "rpm": 100000,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -47647,10 +47973,19 @@
         "supports_image_size": false
     },
     "vertex_ai/gemini-3-pro-image": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -47659,9 +47994,13 @@
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
+        "output_cost_per_token_flex": 6e-06,
+        "output_cost_per_token_priority": 2.16e-05,
         "supports_reasoning": false,
-        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
     },
     "vertex_ai/gemini-3-pro-image-preview": {
         "input_cost_per_image": 0.0011,
@@ -47680,9 +48019,13 @@
         "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
     },
     "vertex_ai/gemini-3.1-flash-image": {
+        "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost_flex": 2.5e-08,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -47691,8 +48034,10 @@
         "output_cost_per_image": 0.0672,
         "output_cost_per_image_token": 6e-05,
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
         "supports_reasoning": false,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
     },
     "vertex_ai/gemini-3.1-flash-image-preview": {
         "input_cost_per_image": 0.00056,
@@ -47710,9 +48055,11 @@
     },
     "vertex_ai/gemini-3.1-flash-lite-image": {
         "cache_read_input_token_cost": 2.5e-08,
+        "cache_read_input_token_cost_flex": 1.25e-08,
         "input_cost_per_image": 0.00028,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
+        "input_cost_per_token_flex": 1.25e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 4096,
@@ -47722,6 +48069,7 @@
         "output_cost_per_image_token": 3e-05,
         "output_cost_per_token": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-07,
+        "output_cost_per_token_flex": 7.5e-07,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -47796,6 +48144,7 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "vertex_ai/gemini-3.1-flash-lite": {
+        "cache_read_input_audio_token_cost": 5e-08,
         "deprecation_date": "2027-05-07",
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
@@ -47816,7 +48165,7 @@
         "output_cost_per_token_flex": 7.5e-07,
         "output_cost_per_token_priority": 2.7e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -47858,7 +48207,7 @@
         "deprecation_date": "2027-07-21",
         "cache_read_input_token_cost": 3e-08,
         "cache_read_input_token_cost_flex": 1.5e-08,
-        "cache_read_input_token_cost_priority": 5e-08,
+        "cache_read_input_token_cost_priority": 5.4e-08,
         "input_cost_per_token": 3e-07,
         "input_cost_per_token_batches": 1.5e-07,
         "input_cost_per_token_flex": 1.5e-07,
@@ -47874,7 +48223,7 @@
         "output_cost_per_token_flex": 1.25e-06,
         "output_cost_per_token_priority": 4.5e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -47913,6 +48262,7 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "vertex_ai/deep-research-pro-preview-12-2025": {
+        "cache_read_input_token_cost": 2e-07,
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -47925,7 +48275,7 @@
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_batches": 6e-06,
-        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
     },
     "vertex_ai/imagegeneration@006": {
         "litellm_provider": "vertex_ai-image-models",
@@ -49588,7 +49938,8 @@
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ],
-        "deprecation_date": "2027-02-26"
+        "deprecation_date": "2027-02-26",
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "xai/grok-3": {
         "cache_read_input_token_cost": 2e-07,
@@ -52685,10 +53036,11 @@
         "max_tokens": 40960,
         "max_input_tokens": 40960,
         "max_output_tokens": 40960,
-        "input_cost_per_token": 0.0,
+        "input_cost_per_token": 2e-07,
         "output_cost_per_token": 0.0,
         "litellm_provider": "fireworks_ai",
-        "mode": "rerank"
+        "mode": "rerank",
+        "source": "https://api.fireworks.ai/v1/serverless/models"
     },
     "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": {
         "max_tokens": 262144,
@@ -52753,7 +53105,7 @@
         "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 1.6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -54652,12 +55004,13 @@
     },
     "gpt-4o-mini-tts-2025-03-20": {
         "deprecation_date": "2026-07-23",
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "mode": "audio_speech",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_second": 0.00025,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ],
@@ -54670,12 +55023,13 @@
         ]
     },
     "gpt-4o-mini-tts-2025-12-15": {
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "mode": "audio_speech",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_second": 0.00025,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ],
@@ -54690,24 +55044,28 @@
     "gpt-4o-mini-transcribe-2025-03-20": {
         "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1.25e-06,
+        "input_cost_per_second": 5e-05,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "mode": "audio_transcription",
         "output_cost_per_token": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ]
     },
     "gpt-4o-mini-transcribe-2025-12-15": {
         "input_cost_per_audio_token": 1.25e-06,
+        "input_cost_per_second": 5e-05,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "mode": "audio_transcription",
         "output_cost_per_token": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ]
@@ -54726,6 +55084,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -54753,6 +55112,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -54780,6 +55140,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -54831,13 +55192,14 @@
         "supports_parallel_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "deprecation_date": "2027-01-20"
+        "deprecation_date": "2027-01-20",
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-realtime-whisper": {
-        "input_cost_per_second": 0.0002833333333333333,
+        "input_cost_per_second": 0.000283333333333,
         "litellm_provider": "openai",
         "mode": "audio_transcription",
-        "source": "https://developers.openai.com/api/docs/models/gpt-realtime-whisper",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime",
             "/v1/realtime/transcription_sessions"
@@ -54855,7 +55217,7 @@
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.1,
-        "source": "https://platform.openai.com/docs/api-reference/videos",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_modalities": [
             "text",
             "image"
@@ -54869,7 +55231,7 @@
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.3,
-        "source": "https://platform.openai.com/docs/api-reference/videos",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_modalities": [
             "text",
             "image"
@@ -54894,11 +55256,15 @@
     "chatgpt-image-latest": {
         "cache_read_input_token_cost": 1.25e-06,
         "deprecation_date": "2026-12-01",
-        "input_cost_per_image_token": 1e-05,
+        "input_cost_per_image_token": 8e-06,
         "input_cost_per_token": 5e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
-        "output_cost_per_image_token": 4e-05,
+        "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -57373,7 +57739,7 @@
         "input_cost_per_second": 7.5e-05,
         "litellm_provider": "openai",
         "mode": "audio_transcription",
-        "source": "https://developers.openai.com/api/docs/models/gpt-transcribe",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/transcriptions",
             "/v1/realtime/transcription_sessions"
@@ -57388,10 +57754,10 @@
         "supports_audio_input": true
     },
     "gpt-live-transcribe": {
-        "input_cost_per_second": 0.0002833333333333333,
+        "input_cost_per_second": 0.000283333333333,
         "litellm_provider": "openai",
         "mode": "audio_transcription",
-        "source": "https://developers.openai.com/api/docs/models/gpt-live-transcribe",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime",
             "/v1/realtime/transcription_sessions"
@@ -57406,10 +57772,10 @@
         "supports_audio_input": true
     },
     "gpt-live-1": {
-        "input_cost_per_second": 0.0008333333333333334,
+        "input_cost_per_second": 0.000833333333333,
         "litellm_provider": "openai",
         "mode": "realtime",
-        "source": "https://developers.openai.com/api/docs/models/gpt-live-1",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_modalities": [
             "text",
             "audio"
@@ -57423,13 +57789,13 @@
         "supports_function_calling": true
     },
     "gpt-realtime-translate": {
-        "input_cost_per_second": 0.0005666666666666667,
+        "input_cost_per_second": 0.000566666666667,
         "litellm_provider": "openai",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "max_tokens": 2000,
         "mode": "realtime",
-        "source": "https://developers.openai.com/api/docs/models/gpt-realtime-translate",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_modalities": [
             "audio"
         ],
@@ -57457,7 +57823,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "source": "https://platform.claude.com/docs/en/about-claude/models/overview",
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing",
         "supports_adaptive_thinking": true,
         "thinking_always_on": true,
         "supports_mid_conversation_system": true,
@@ -57518,7 +57884,7 @@
         "supports_output_config": true,
         "prompt_cache_min_tokens": 512,
         "supports_native_structured_output": true,
-        "source": "https://platform.claude.com/docs/en/models/mythos-5-1/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-mythos-preview": {
         "cache_creation_input_token_cost": 1.25e-05,
@@ -57874,6 +58240,7 @@
     },
     "vertex_ai/gemini-3.5-live-translate-preview": {
         "input_cost_per_audio_token": 3.5e-06,
+        "input_cost_per_second": 8.83333333333e-05,
         "input_cost_per_token": 3.5e-06,
         "litellm_provider": "vertex_ai",
         "mode": "realtime",
@@ -57976,14 +58343,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 8.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -57992,14 +58362,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash",
+        "output_cost_per_token_priority": 8.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -58015,26 +58388,29 @@
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_vision": true
     },
     "fireworks_ai/accounts/fireworks/models/kimi-k3": {
         "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_priority": 3.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_priority": 1.875e-05,
         "reasoning_effort_levels": [
             "low",
             "high",
             "max"
         ],
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58043,14 +58419,17 @@
     },
     "fireworks_ai/deepseek-v4-flash-0731": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 8.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58059,14 +58438,17 @@
     },
     "fireworks_ai/deepseek-v4p1-flash": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash",
+        "output_cost_per_token_priority": 8.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -58082,7 +58464,7 @@
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_vision": true
@@ -58121,19 +58503,22 @@
     },
     "fireworks_ai/kimi-k3": {
         "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_priority": 3.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_priority": 1.875e-05,
         "reasoning_effort_levels": [
             "low",
             "high",
             "max"
         ],
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58184,12 +58569,15 @@
     },
     "fireworks_ai/qwen3p8-max": {
         "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_priority": 3e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 9e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58205,7 +58593,7 @@
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58237,7 +58625,7 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58253,7 +58641,7 @@
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58285,7 +58673,7 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58294,12 +58682,15 @@
     },
     "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
         "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_priority": 3e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 9e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58315,7 +58706,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 6.6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58352,7 +58743,7 @@
             "high",
             "max"
         ],
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -61050,14 +61441,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/glm-5p3": {
         "cache_read_input_token_cost": 2.6e-07,
+        "cache_read_input_token_cost_priority": 3.25e-07,
         "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_priority": 1.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 5.5e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -61066,13 +61460,16 @@
     },
     "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": {
         "cache_read_input_token_cost": 3e-08,
+        "cache_read_input_token_cost_priority": 3.75e-08,
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_priority": 1.875e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -61100,7 +61497,7 @@
         "max_output_tokens": 40960,
         "max_tokens": 40960,
         "mode": "embedding",
-        "source": "https://docs.fireworks.ai/serverless/pricing"
+        "source": "https://api.fireworks.ai/v1/serverless/models"
     },
     "zai/glm-5.2": {
         "cache_creation_input_token_cost": 0,
@@ -61124,7 +61521,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 4.7e-07,
-        "source": "https://docs.together.ai/docs/serverless-models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/moonshotai/Kimi-K2.6": {
         "deprecation_date": "2026-08-19",
@@ -61134,7 +61531,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/moonshotai/Kimi-K2.5-fp4": {
         "input_cost_per_token": 5e-07,
@@ -61142,7 +61539,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/MiniMaxAI/MiniMax-M2.7": {
         "input_cost_per_token": 3e-07,
@@ -61151,7 +61548,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 196608,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/zai-org/GLM-5": {
         "deprecation_date": "2026-06-22",
@@ -61160,7 +61557,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 202752,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/zai-org/GLM-5.1": {
         "deprecation_date": "2026-07-10",
@@ -61170,7 +61567,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 202752,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/deepseek-ai/DeepSeek-R1-0528": {
         "input_cost_per_token": 3e-06,
@@ -61178,7 +61575,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 163840,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3-Coder-Next-FP8": {
         "deprecation_date": "2026-05-14",
@@ -61187,7 +61584,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3-VL-32B-Instruct": {
         "deprecation_date": "2026-02-25",
@@ -61196,7 +61593,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3-VL-8B-Instruct": {
         "deprecation_date": "2026-04-16",
@@ -61205,7 +61602,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/mistralai/Ministral-3-14B-Instruct-2512": {
         "input_cost_per_token": 2e-07,
@@ -61213,7 +61610,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
         "input_cost_per_token": 6e-08,
@@ -61221,7 +61618,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 131072,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/mistralai/Mistral-7B-Instruct-v0.3": {
         "input_cost_per_token": 2e-07,
@@ -61229,7 +61626,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 32768,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/QwQ-32B": {
         "deprecation_date": "2025-11-13",
@@ -61238,7 +61635,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 131072,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "cerebras/gemma-4-31b": {
         "input_cost_per_token": 9.9e-07,
@@ -65365,5 +65762,263 @@
         "supports_tool_choice": false,
         "supports_response_schema": true,
         "supports_vision": false
+    },
+    "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": {
+        "cache_read_input_token_cost": 3.9e-07,
+        "input_cost_per_token": 2.1e-06,
+        "litellm_provider": "fireworks_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models"
+    },
+    "together_ai/arcee-ai/trinity-mini": {
+        "input_cost_per_token": 4.5e-08,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/deepseek-coder-33b-instruct": {
+        "input_cost_per_token": 8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 2e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+        "input_cost_per_token": 1.8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+        "input_cost_per_token": 1.6e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": {
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "vertex_ai/gemini-2.5-flash-native-audio": {
+        "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_token": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "realtime",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_token": 2e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-2.5-flash-preview-tts": {
+        "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 1e-05,
+        "output_cost_per_token": 1e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-3.1-flash-live-preview": {
+        "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_second": 8.33333333333e-05,
+        "input_cost_per_token": 7.5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "realtime",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_token": 4.5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-3.1-flash-tts-preview": {
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 2e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-3.5-transcribe": {
+        "input_cost_per_audio_token": 2e-06,
+        "input_cost_per_second": 5e-05,
+        "litellm_provider": "vertex_ai",
+        "mode": "audio_transcription",
+        "output_cost_per_token": 1.2e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-3.5-transcribe-live": {
+        "input_cost_per_audio_token": 3.5e-06,
+        "input_cost_per_second": 8.33333333333e-05,
+        "litellm_provider": "vertex_ai",
+        "mode": "audio_transcription",
+        "output_cost_per_token": 2.1e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-omni-1.1-flash": {
+        "input_cost_per_token": 1.5e-06,
+        "litellm_provider": "vertex_ai",
+        "mode": "chat",
+        "output_cost_per_token": 9e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-robotics-er-2": {
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "chat",
+        "output_cost_per_token": 5e-06,
+        "output_cost_per_token_batches": 2.5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemma-4-26b-a4b-it": {
+        "cache_read_input_token_cost": 1.5e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "together_ai/google/gemma-2-27b-it": {
+        "input_cost_per_token": 8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "gpt-5.5-cyber": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 1.25e-05,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_reasoning": true
+    },
+    "gpt-rosalind-research": {
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "together_ai/meta-llama/Llama-3-8b-chat-hf": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 2e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Llama-3.1-405B-Instruct": {
+        "input_cost_per_token": 3.5e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Llama-3.2-1B-Instruct": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6e-08,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Llama-3.2-3B-Instruct": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6e-08,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
+        "input_cost_per_token": 8.8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8.8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 2e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+        "input_cost_per_token": 8.8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8.8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2-1.5B-Instruct": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 2e-08,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2-72B-Instruct": {
+        "input_cost_per_token": 9e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 9e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2-VL-72B-Instruct": {
+        "input_cost_per_token": 1.2e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2.5-14B-Instruct": {
+        "input_cost_per_token": 8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2.5-72B-Instruct": {
+        "input_cost_per_token": 1.2e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": {
+        "input_cost_per_token": 8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": {
+        "input_cost_per_token": 1.95e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-06,
+        "source": "https://api.together.ai/v1/models"
     }
 }
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 685e63dcc56..0c60ff26635 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -11216,12 +11216,15 @@
     "babbage-002": {
         "deprecation_date": "2026-09-28",
         "input_cost_per_token": 4e-07,
+        "input_cost_per_token_batches": 2e-07,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
-        "output_cost_per_token": 4e-07
+        "output_cost_per_token": 4e-07,
+        "output_cost_per_token_batches": 2e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "bedrock/*/1-month-commitment/cohere.command-light-text-v14": {
         "input_cost_per_second": 0.001902,
@@ -13286,7 +13289,9 @@
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ],
-        "deprecation_date": "2027-02-26"
+        "deprecation_date": "2027-02-26",
+        "input_cost_per_second": 0.0001,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "claude-haiku-4-5-20251001": {
         "deprecation_date": "2026-10-15",
@@ -13334,7 +13339,8 @@
         "supports_response_schema": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-3-7-sonnet-20250219": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -13493,7 +13499,8 @@
         "supports_native_structured_output": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-sonnet-4-5-20250929": {
         "deprecation_date": "2026-09-29",
@@ -13567,7 +13574,7 @@
         },
         "supports_output_config": true,
         "prompt_cache_min_tokens": 1024,
-        "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-sonnet-4-6": {
         "deprecation_date": "2027-02-17",
@@ -13603,7 +13610,8 @@
         "prompt_cache_min_tokens": 1024,
         "provider_specific_entry": {
             "us": 1.1
-        }
+        },
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-sonnet-4-5-20250929-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
@@ -13780,7 +13788,8 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_output_config": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-6": {
         "deprecation_date": "2027-02-05",
@@ -13817,7 +13826,8 @@
         "supports_output_config": true,
         "supports_max_reasoning_effort": true,
         "supports_speed": true,
-        "prompt_cache_min_tokens": 4096
+        "prompt_cache_min_tokens": 4096,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-6-20260205": {
         "deprecation_date": "2027-02-05",
@@ -13892,7 +13902,8 @@
         },
         "supports_output_config": true,
         "supports_speed": true,
-        "prompt_cache_min_tokens": 2048
+        "prompt_cache_min_tokens": 2048,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-7-20260416": {
         "deprecation_date": "2027-04-16",
@@ -13970,7 +13981,7 @@
         "supports_output_config": true,
         "prompt_cache_min_tokens": 512,
         "supports_native_structured_output": true,
-        "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-fable-5-1": {
         "deprecation_date": "2027-09-01",
@@ -14011,7 +14022,7 @@
         "supports_output_config": true,
         "prompt_cache_min_tokens": 512,
         "supports_native_structured_output": true,
-        "source": "https://platform.claude.com/docs/en/models/fable-5-1/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-5": {
         "deprecation_date": "2027-07-24",
@@ -14052,7 +14063,7 @@
         "supports_output_config": true,
         "supports_speed": true,
         "prompt_cache_min_tokens": 512,
-        "source": "https://docs.anthropic.com/en/docs/about-claude/models/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-opus-4-8": {
         "deprecation_date": "2027-05-28",
@@ -14092,7 +14103,8 @@
         },
         "supports_output_config": true,
         "supports_speed": true,
-        "prompt_cache_min_tokens": 1024
+        "prompt_cache_min_tokens": 1024,
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-sonnet-4-20250514": {
         "deprecation_date": "2026-06-15",
@@ -19361,12 +19373,15 @@
     "davinci-002": {
         "deprecation_date": "2026-09-28",
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 1e-06,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "deepgram/base": {
         "input_cost_per_second": 0.00020833,
@@ -22413,15 +22428,18 @@
         "supports_vision": false
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro": {
-        "cache_read_input_token_cost": 1.45e-07,
-        "input_cost_per_token": 1.74e-06,
+        "cache_read_input_token_cost": 6e-07,
+        "cache_read_input_token_cost_priority": 6e-07,
+        "input_cost_per_token": 1.2e-06,
+        "input_cost_per_token_priority": 1.2e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 384000,
         "max_tokens": 384000,
         "mode": "chat",
-        "output_cost_per_token": 3.48e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.2e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22430,14 +22448,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-pro-0813": {
         "cache_read_input_token_cost": 4.4e-08,
+        "cache_read_input_token_cost_priority": 5.5e-08,
         "input_cost_per_token": 1.32e-06,
+        "input_cost_per_token_priority": 1.65e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 3.96e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 4.95e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22532,14 +22553,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/glm-5p2": {
         "cache_read_input_token_cost": 1.4e-07,
+        "cache_read_input_token_cost_priority": 1.75e-07,
         "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_priority": 1.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 5.5e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22548,14 +22572,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/gpt-oss-120b": {
         "cache_read_input_token_cost": 1.5e-08,
+        "cache_read_input_token_cost_priority": 1.8e-08,
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_priority": 1.8e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 7.2e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22634,14 +22661,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/kimi-k2p6": {
         "cache_read_input_token_cost": 1.6e-07,
+        "cache_read_input_token_cost_priority": 2.2e-07,
         "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_priority": 1.5e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22650,14 +22680,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/kimi-k2p7-code": {
         "cache_read_input_token_cost": 1.9e-07,
+        "cache_read_input_token_cost_priority": 2.85e-07,
         "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_priority": 1.425e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22783,14 +22816,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/minimax-m2p7": {
         "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_priority": 6e-07,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 1.2e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 196608,
         "max_output_tokens": 196608,
         "max_tokens": 196608,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 1.2e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22799,14 +22835,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/minimax-m3": {
         "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 512000,
         "max_output_tokens": 512000,
         "max_tokens": 512000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 1.8e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22882,15 +22921,18 @@
         "supports_vision": false
     },
     "fireworks_ai/deepseek-v4-pro": {
-        "cache_read_input_token_cost": 1.45e-07,
-        "input_cost_per_token": 1.74e-06,
+        "cache_read_input_token_cost": 6e-07,
+        "cache_read_input_token_cost_priority": 6e-07,
+        "input_cost_per_token": 1.2e-06,
+        "input_cost_per_token_priority": 1.2e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 384000,
         "max_tokens": 384000,
         "mode": "chat",
-        "output_cost_per_token": 3.48e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_priority": 1.2e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22946,14 +22988,17 @@
     },
     "fireworks_ai/glm-5p2": {
         "cache_read_input_token_cost": 1.4e-07,
+        "cache_read_input_token_cost_priority": 1.75e-07,
         "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_priority": 1.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 5.5e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -22962,14 +23007,17 @@
     },
     "fireworks_ai/gpt-oss-120b": {
         "cache_read_input_token_cost": 1.5e-08,
+        "cache_read_input_token_cost_priority": 1.8e-08,
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_priority": 1.8e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 131072,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 7.2e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23008,14 +23056,17 @@
     },
     "fireworks_ai/kimi-k2p6": {
         "cache_read_input_token_cost": 1.6e-07,
+        "cache_read_input_token_cost_priority": 2.2e-07,
         "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_priority": 1.5e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23040,14 +23091,17 @@
     },
     "fireworks_ai/kimi-k2p7-code": {
         "cache_read_input_token_cost": 1.9e-07,
+        "cache_read_input_token_cost_priority": 2.85e-07,
         "input_cost_per_token": 9.5e-07,
+        "input_cost_per_token_priority": 1.425e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23086,14 +23140,17 @@
     },
     "fireworks_ai/minimax-m2p7": {
         "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_priority": 6e-07,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 1.2e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 196608,
         "max_output_tokens": 196608,
         "max_tokens": 196608,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 1.2e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23102,14 +23159,17 @@
     },
     "fireworks_ai/minimax-m3": {
         "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_priority": 9e-08,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 512000,
         "max_output_tokens": 512000,
         "max_tokens": 512000,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 1.8e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23125,7 +23185,7 @@
         "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 1.6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -23374,26 +23434,28 @@
     "ft:babbage-002": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.6e-06,
-        "input_cost_per_token_batches": 2e-07,
+        "input_cost_per_token_batches": 8e-07,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
         "output_cost_per_token": 1.6e-06,
-        "output_cost_per_token_batches": 2e-07
+        "output_cost_per_token_batches": 9e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "ft:davinci-002": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.2e-05,
-        "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_batches": 6e-06,
         "litellm_provider": "text-completion-openai",
         "max_input_tokens": 16384,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
         "output_cost_per_token": 1.2e-05,
-        "output_cost_per_token_batches": 1e-06
+        "output_cost_per_token_batches": 6e-06,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "ft:gpt-3.5-turbo": {
         "deprecation_date": "2026-10-23",
@@ -23406,6 +23468,7 @@
         "mode": "chat",
         "output_cost_per_token": 6e-06,
         "output_cost_per_token_batches": 3e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_system_messages": true,
         "supports_tool_choice": true
     },
@@ -23462,14 +23525,15 @@
     "ft:gpt-4o-2024-08-06": {
         "cache_read_input_token_cost": 1.875e-06,
         "input_cost_per_token": 3.75e-06,
-        "input_cost_per_token_batches": 1.875e-06,
+        "input_cost_per_token_batches": 2.225e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
         "max_output_tokens": 16384,
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
-        "output_cost_per_token_batches": 7.5e-06,
+        "output_cost_per_token_batches": 1.25e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -23507,6 +23571,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
         "output_cost_per_token_batches": 6e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -23526,6 +23591,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_batches": 6e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -23544,6 +23610,7 @@
         "mode": "chat",
         "output_cost_per_token": 3.2e-06,
         "output_cost_per_token_batches": 1.6e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -23563,6 +23630,7 @@
         "mode": "chat",
         "output_cost_per_token": 8e-07,
         "output_cost_per_token_batches": 4e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -23582,6 +23650,7 @@
         "mode": "chat",
         "output_cost_per_token": 1.6e-05,
         "output_cost_per_token_batches": 8e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_prompt_caching": true,
@@ -23592,15 +23661,18 @@
     "gemini-2.0-flash": {
         "cache_read_input_token_cost": 2.5e-08,
         "deprecation_date": "2026-06-01",
-        "input_cost_per_audio_token": 7e-07,
-        "input_cost_per_token": 1e-07,
+        "input_cost_per_audio_token": 1e-06,
+        "input_cost_per_character": 3.75e-08,
+        "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_batches": 7.5e-08,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 4e-07,
-        "source": "https://ai.google.dev/pricing#2_0flash",
+        "output_cost_per_token": 6e-07,
+        "output_cost_per_token_batches": 3e-07,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_modalities": [
             "text",
             "image",
@@ -23669,13 +23741,16 @@
         "cache_read_input_token_cost": 1.875e-08,
         "deprecation_date": "2026-06-01",
         "input_cost_per_audio_token": 7.5e-08,
+        "input_cost_per_character": 1.875e-08,
         "input_cost_per_token": 7.5e-08,
+        "input_cost_per_token_batches": 3.75e-08,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 8192,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models#gemini-2.0-flash",
+        "output_cost_per_token_batches": 1.5e-07,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_modalities": [
             "text",
             "image",
@@ -23736,8 +23811,11 @@
         }
     },
     "gemini-2.5-flash": {
+        "cache_read_input_audio_token_cost": 1e-07,
         "deprecation_date": "2026-10-20",
         "cache_read_input_token_cost": 3e-08,
+        "cache_read_input_token_cost_flex": 3e-08,
+        "cache_read_input_token_cost_priority": 5.4e-08,
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -23747,7 +23825,7 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 2.5e-06,
         "output_cost_per_token": 2.5e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -23780,6 +23858,12 @@
             "search_context_size_high": 0.035
         },
         "google_maps_grounding_cost_per_query": 0.025,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.4e-07,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_flex": 1.25e-06,
+        "output_cost_per_token_priority": 4.5e-06,
         "supports_image_size": false
     },
     "gemini-2.5-flash-image": {
@@ -23787,6 +23871,9 @@
         "cache_read_input_token_cost": 3e-08,
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.4e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 32768,
         "max_output_tokens": 32768,
@@ -23796,8 +23883,10 @@
         "output_cost_per_image_token": 3e-05,
         "output_cost_per_reasoning_token": 2.5e-06,
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_flex": 1.25e-06,
         "rpm": 100000,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -23828,10 +23917,19 @@
         "supports_image_size": false
     },
     "gemini-3-pro-image": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -23840,8 +23938,12 @@
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3-pro-image",
+        "output_cost_per_token_flex": 6e-06,
+        "output_cost_per_token_priority": 2.16e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -23909,9 +24011,13 @@
         "web_search_billing_unit": "per_query"
     },
     "gemini-3.1-flash-image": {
+        "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost_flex": 2.5e-08,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -23920,7 +24026,9 @@
         "output_cost_per_image": 0.0672,
         "output_cost_per_image_token": 6e-05,
         "output_cost_per_token": 3e-06,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -23987,9 +24095,11 @@
     },
     "gemini-3.1-flash-lite-image": {
         "cache_read_input_token_cost": 2.5e-08,
+        "cache_read_input_token_cost_flex": 1.25e-08,
         "input_cost_per_image": 0.00028,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
+        "input_cost_per_token_flex": 1.25e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 4096,
@@ -23999,6 +24109,7 @@
         "output_cost_per_image_token": 3e-05,
         "output_cost_per_token": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-07,
+        "output_cost_per_token_flex": 7.5e-07,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -24073,6 +24184,7 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "gemini-3.1-flash-lite": {
+        "cache_read_input_audio_token_cost": 5e-08,
         "deprecation_date": "2027-05-07",
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
@@ -24092,7 +24204,7 @@
         "output_cost_per_token_batches": 7.5e-07,
         "output_cost_per_token_flex": 7.5e-07,
         "output_cost_per_token_priority": 2.7e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24134,7 +24246,7 @@
         "deprecation_date": "2027-07-21",
         "cache_read_input_token_cost": 3e-08,
         "cache_read_input_token_cost_flex": 1.5e-08,
-        "cache_read_input_token_cost_priority": 5e-08,
+        "cache_read_input_token_cost_priority": 5.4e-08,
         "input_cost_per_token": 3e-07,
         "input_cost_per_token_batches": 1.5e-07,
         "input_cost_per_token_flex": 1.5e-07,
@@ -24149,7 +24261,7 @@
         "output_cost_per_token_batches": 1.25e-06,
         "output_cost_per_token_flex": 1.25e-06,
         "output_cost_per_token_priority": 4.5e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24188,6 +24300,7 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "deep-research-pro-preview-12-2025": {
+        "cache_read_input_token_cost": 2e-07,
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -24200,7 +24313,7 @@
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_batches": 6e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24222,8 +24335,11 @@
         "supports_web_search": true
     },
     "gemini-2.5-flash-lite": {
+        "cache_read_input_audio_token_cost": 3e-08,
         "deprecation_date": "2026-10-20",
         "cache_read_input_token_cost": 1e-08,
+        "cache_read_input_token_cost_flex": 1e-08,
+        "cache_read_input_token_cost_priority": 1.8e-08,
         "input_cost_per_audio_token": 3e-07,
         "input_cost_per_token": 1e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -24233,7 +24349,7 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 4e-07,
         "output_cost_per_token": 4e-07,
-        "source": "https://ai.google.dev/gemini-api/docs/models#gemini-2.5-flash-preview",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24266,6 +24382,12 @@
             "search_context_size_high": 0.035
         },
         "google_maps_grounding_cost_per_query": 0.025,
+        "input_cost_per_token_batches": 5e-08,
+        "input_cost_per_token_flex": 5e-08,
+        "input_cost_per_token_priority": 1.8e-07,
+        "output_cost_per_token_batches": 2e-07,
+        "output_cost_per_token_flex": 2e-07,
+        "output_cost_per_token_priority": 7.2e-07,
         "supports_image_size": false
     },
     "gemini-2.5-flash-lite-preview-09-2025": {
@@ -24417,7 +24539,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_token": 2e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/vertex_ai/live"
         ],
@@ -24448,7 +24570,8 @@
             "search_context_size_medium": 0.035,
             "search_context_size_high": 0.035
         },
-        "gemini_native_audio": true
+        "gemini_native_audio": true,
+        "input_cost_per_image_token": 3e-06
     },
     "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -24548,6 +24671,9 @@
         "cache_read_input_token_cost": 1.25e-07,
         "cache_read_input_token_cost_above_200k_tokens": 2.5e-07,
         "cache_creation_input_token_cost_above_200k_tokens": 2.5e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 4.5e-07,
+        "cache_read_input_token_cost_flex": 1.25e-07,
+        "cache_read_input_token_cost_priority": 2.25e-07,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "vertex_ai-language-models",
@@ -24557,7 +24683,7 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions"
@@ -24587,7 +24713,15 @@
             "search_context_size_medium": 0.035,
             "search_context_size_high": 0.035
         },
-        "google_maps_grounding_cost_per_query": 0.025
+        "google_maps_grounding_cost_per_query": 0.025,
+        "input_cost_per_token_above_200k_tokens_priority": 4.5e-06,
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_flex": 6.25e-07,
+        "input_cost_per_token_priority": 2.25e-06,
+        "output_cost_per_token_above_200k_tokens_priority": 2.7e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "output_cost_per_token_priority": 1.8e-05
     },
     "gemini-3-pro-preview": {
         "deprecation_date": "2026-03-26",
@@ -24662,7 +24796,7 @@
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
         "output_cost_per_token_batches": 6e-06,
         "output_cost_per_image": 0.00012,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24696,13 +24830,16 @@
         "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "cache_read_input_token_cost_priority": 3.6e-07,
         "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_flex": 2e-07,
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
             "search_context_size_high": 0.014
         },
         "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token_flex": 1e-06,
+        "output_cost_per_token_flex": 6e-06
     },
     "gemini-3.1-pro-preview-customtools": {
         "prompt_cache_min_tokens": 4096,
@@ -24813,7 +24950,9 @@
         "web_search_billing_unit": "per_query"
     },
     "vertex_ai/gemini-3-flash-preview": {
+        "cache_read_input_audio_token_cost": 1e-07,
         "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
         "input_cost_per_token": 5e-07,
         "input_cost_per_audio_token": 1e-06,
         "litellm_provider": "vertex_ai",
@@ -24822,7 +24961,7 @@
         "max_tokens": 65535,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24859,7 +24998,11 @@
             "search_context_size_high": 0.014
         },
         "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06
     },
     "vertex_ai/gemini-3.5-flash": {
         "prompt_cache_min_tokens": 4096,
@@ -24875,7 +25018,7 @@
         "output_cost_per_reasoning_token": 9e-06,
         "output_cost_per_token": 9e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24938,7 +25081,7 @@
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -24995,7 +25138,7 @@
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -25052,7 +25195,7 @@
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -25109,7 +25252,7 @@
         "output_cost_per_token_above_200k_tokens": 1.8e-05,
         "output_cost_per_token_batches": 6e-06,
         "output_cost_per_image": 0.00012,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -25143,13 +25286,16 @@
         "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "cache_read_input_token_cost_priority": 3.6e-07,
         "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_flex": 2e-07,
         "search_context_cost_per_query": {
             "search_context_size_low": 0.014,
             "search_context_size_medium": 0.014,
             "search_context_size_high": 0.014
         },
         "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token_flex": 1e-06,
+        "output_cost_per_token_flex": 6e-06
     },
     "vertex_ai/gemini-3.1-pro-preview-customtools": {
         "prompt_cache_min_tokens": 4096,
@@ -25214,13 +25360,15 @@
         "cache_read_input_token_cost": 1.25e-07,
         "input_cost_per_audio_token": 7e-07,
         "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 1048576,
         "max_output_tokens": 65535,
         "max_tokens": 65535,
         "mode": "chat",
+        "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2e-05,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_modalities": [
             "text"
         ],
@@ -25427,7 +25575,7 @@
         "mode": "chat",
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_above_200k_tokens": 1.5e-05,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/computer-use",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_modalities": [
             "text",
             "image"
@@ -25468,8 +25616,11 @@
     },
     "gemini-embedding-2": {
         "input_cost_per_audio_per_second": 0.00016,
+        "input_cost_per_audio_token": 6.5e-06,
         "input_cost_per_image": 0.00012,
+        "input_cost_per_image_token": 4.5e-07,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_batches": 1e-07,
         "input_cost_per_video_per_second": 0.00079,
         "litellm_provider": "vertex_ai-embedding-models",
         "max_input_tokens": 8192,
@@ -25477,7 +25628,7 @@
         "mode": "embedding",
         "output_cost_per_token": 0,
         "output_vector_size": 3072,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supports_multimodal": true,
         "uses_embed_content": true
     },
@@ -25498,8 +25649,11 @@
     },
     "vertex_ai/gemini-embedding-2": {
         "input_cost_per_audio_per_second": 0.00016,
+        "input_cost_per_audio_token": 6.5e-06,
         "input_cost_per_image": 0.00012,
+        "input_cost_per_image_token": 4.5e-07,
         "input_cost_per_token": 2e-07,
+        "input_cost_per_token_batches": 1e-07,
         "input_cost_per_video_per_second": 0.00079,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 8192,
@@ -25507,7 +25661,7 @@
         "mode": "embedding",
         "output_cost_per_token": 0,
         "output_vector_size": 3072,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supports_multimodal": true,
         "uses_embed_content": true
     },
@@ -27141,7 +27295,9 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "gemini-3-flash-preview": {
+        "cache_read_input_audio_token_cost": 1e-07,
         "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost_flex": 5e-08,
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "vertex_ai-language-models",
@@ -27151,7 +27307,7 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 3e-06,
         "output_cost_per_token": 3e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -27189,7 +27345,11 @@
             "search_context_size_high": 0.014
         },
         "web_search_billing_unit": "per_query",
-        "google_maps_grounding_cost_per_query": 0.014
+        "google_maps_grounding_cost_per_query": 0.014,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06
     },
     "gemini-omni-flash-preview": {
         "input_cost_per_audio_token": 1.5e-06,
@@ -27202,7 +27362,7 @@
         "output_cost_per_reasoning_token": 9e-06,
         "output_cost_per_token": 9e-06,
         "output_cost_per_video_token": 1.75e-05,
-        "source": "https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/omni-flash-preview",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -27235,7 +27395,7 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 9e-06,
         "output_cost_per_token": 9e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -27298,7 +27458,7 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -27355,7 +27515,7 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -27412,7 +27572,7 @@
         "output_cost_per_token": 3.75e-06,
         "output_cost_per_token_batches": 1.875e-06,
         "output_cost_per_token_flex": 1.875e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -28870,6 +29030,7 @@
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_system_messages": true,
@@ -28878,12 +29039,15 @@
     "gpt-3.5-turbo-0125": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token_batches": 7.5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -28893,12 +29057,15 @@
     "gpt-3.5-turbo-1106": {
         "deprecation_date": "2026-09-28",
         "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 16385,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 2e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -28926,7 +29093,8 @@
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "completion",
-        "output_cost_per_token": 2e-06
+        "output_cost_per_token": 2e-06,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-3.5-turbo-instruct-0914": {
         "input_cost_per_token": 1.5e-06,
@@ -28981,12 +29149,15 @@
     "gpt-4-0613": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 3e-05,
+        "input_cost_per_token_batches": 1.5e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 8192,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 6e-05,
+        "output_cost_per_token_batches": 3e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_system_messages": true,
@@ -29027,12 +29198,15 @@
     "gpt-4-turbo-2024-04-09": {
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1e-05,
+        "input_cost_per_token_batches": 5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 128000,
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
         "output_cost_per_token": 3e-05,
+        "output_cost_per_token_batches": 1.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29076,6 +29250,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29118,6 +29293,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29160,6 +29336,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29202,6 +29379,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29240,6 +29418,7 @@
         "output_cost_per_token": 4e-07,
         "output_cost_per_token_batches": 2e-07,
         "output_cost_per_token_priority": 8e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29277,6 +29456,7 @@
         "output_cost_per_token": 4e-07,
         "output_cost_per_token_priority": 8e-07,
         "output_cost_per_token_batches": 2e-07,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -29313,6 +29493,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_batches": 5e-06,
         "output_cost_per_token_priority": 1.7e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29335,6 +29516,7 @@
         "output_cost_per_token": 1.5e-05,
         "output_cost_per_token_batches": 7.5e-06,
         "output_cost_per_token_priority": 2.625e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29357,6 +29539,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_priority": 1.7e-05,
         "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29380,6 +29563,7 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_priority": 1.7e-05,
         "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29454,6 +29638,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses",
@@ -29490,6 +29675,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions"
         ],
@@ -29524,6 +29710,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses",
@@ -29561,6 +29748,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses",
@@ -29598,6 +29786,7 @@
         "mode": "chat",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses",
@@ -29659,7 +29848,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": false,
-        "deprecation_date": "2027-01-20"
+        "deprecation_date": "2027-01-20",
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-4o-mini": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -29687,7 +29877,8 @@
             "search_context_size_high": 0.025,
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
-        }
+        },
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -29708,6 +29899,7 @@
             "search_context_size_low": 0.025,
             "search_context_size_medium": 0.025
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -29856,15 +30048,18 @@
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ],
-        "deprecation_date": "2027-02-26"
+        "deprecation_date": "2027-02-26",
+        "input_cost_per_second": 5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-4o-mini-tts": {
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "mode": "audio_speech",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_second": 0.00025,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ],
@@ -29996,7 +30191,9 @@
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ],
-        "deprecation_date": "2027-02-26"
+        "deprecation_date": "2027-02-26",
+        "input_cost_per_second": 0.0001,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-image-1.5": {
         "cache_read_input_token_cost": 1.25e-06,
@@ -30006,7 +30203,10 @@
         "mode": "image_generation",
         "output_cost_per_token": 1e-05,
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations"
         ],
@@ -30021,7 +30221,10 @@
         "mode": "image_generation",
         "output_cost_per_token": 1e-05,
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations"
         ],
@@ -30034,7 +30237,9 @@
         "litellm_provider": "openai",
         "mode": "image_generation",
         "input_cost_per_image_token": 8e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "output_cost_per_image_token": 3e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -30481,6 +30686,7 @@
         "cache_read_input_token_cost_flex": 6.25e-08,
         "cache_read_input_token_cost_priority": 2.5e-07,
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 6.25e-07,
         "input_cost_per_token_flex": 6.25e-07,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -30489,6 +30695,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
         "output_cost_per_token_flex": 5e-06,
         "output_cost_per_token_priority": 2e-05,
         "search_context_cost_per_query": {
@@ -30496,6 +30703,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -30525,6 +30733,7 @@
     },
     "gpt-5.1": {
         "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_flex": 6.25e-08,
         "cache_read_input_token_cost_priority": 2.5e-07,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
@@ -30565,11 +30774,17 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_flex": 6.25e-07,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false
     },
     "gpt-5.1-2025-11-13": {
         "cache_read_input_token_cost": 1.25e-07,
+        "cache_read_input_token_cost_flex": 6.25e-08,
         "cache_read_input_token_cost_priority": 2.5e-07,
         "input_cost_per_token": 1.25e-06,
         "input_cost_per_token_priority": 2.5e-06,
@@ -30610,6 +30825,11 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "input_cost_per_token_batches": 6.25e-07,
+        "input_cost_per_token_flex": 6.25e-07,
+        "output_cost_per_token_batches": 5e-06,
+        "output_cost_per_token_flex": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": false,
         "supports_minimal_reasoning_effort": false
     },
@@ -30661,6 +30881,7 @@
     },
     "gpt-5.2": {
         "cache_read_input_token_cost": 1.75e-07,
+        "cache_read_input_token_cost_flex": 8.75e-08,
         "cache_read_input_token_cost_priority": 3.5e-07,
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
@@ -30702,11 +30923,17 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "input_cost_per_token_batches": 8.75e-07,
+        "input_cost_per_token_flex": 8.75e-07,
+        "output_cost_per_token_batches": 7e-06,
+        "output_cost_per_token_flex": 7e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
     "gpt-5.2-2025-12-11": {
         "cache_read_input_token_cost": 1.75e-07,
+        "cache_read_input_token_cost_flex": 8.75e-08,
         "cache_read_input_token_cost_priority": 3.5e-07,
         "input_cost_per_token": 1.75e-06,
         "input_cost_per_token_priority": 3.5e-06,
@@ -30748,6 +30975,11 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "input_cost_per_token_batches": 8.75e-07,
+        "input_cost_per_token_flex": 8.75e-07,
+        "output_cost_per_token_batches": 7e-06,
+        "output_cost_per_token_flex": 7e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -30841,17 +31073,20 @@
     },
     "gpt-5.2-pro": {
         "input_cost_per_token": 2.1e-05,
+        "input_cost_per_token_batches": 1.05e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.000168,
+        "output_cost_per_token_batches": 8.4e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/batch",
             "/v1/responses"
@@ -30880,17 +31115,20 @@
     },
     "gpt-5.2-pro-2025-12-11": {
         "input_cost_per_token": 2.1e-05,
+        "input_cost_per_token_batches": 1.05e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 272000,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "responses",
         "output_cost_per_token": 0.000168,
+        "output_cost_per_token_batches": 8.4e-05,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/batch",
             "/v1/responses"
@@ -30956,6 +31194,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -31092,6 +31331,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -31160,6 +31400,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -31227,6 +31468,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -31290,7 +31532,7 @@
         "supports_tool_choice": true,
         "supports_vision": true,
         "supports_web_search": true,
-        "source": "https://developers.openai.com/api/docs/models/gpt-5.6-cyber",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_computer_use": true,
         "supports_parallel_function_calling": true
     },
@@ -31460,7 +31702,7 @@
         "reasoning_effort_levels": [
             "medium"
         ],
-        "source": "https://developers.openai.com/api/docs/models/chat-latest",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/responses"
@@ -31539,7 +31781,8 @@
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 5e-06,
         "output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
-        "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
+        "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.5-2026-04-23": {
         "cache_read_input_token_cost": 5e-07,
@@ -31596,7 +31839,8 @@
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 5e-06,
         "output_cost_per_token_above_272k_tokens_flex": 2.25e-05,
-        "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07
+        "cache_read_input_token_cost_above_272k_tokens_flex": 5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.5-pro": {
         "input_cost_per_token": 3e-05,
@@ -31619,6 +31863,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -31667,6 +31912,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -31744,7 +31990,8 @@
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
         "output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
-        "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
+        "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.4-2026-03-05": {
         "cache_read_input_token_cost": 2.5e-07,
@@ -31796,7 +32043,8 @@
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 2.5e-06,
         "output_cost_per_token_above_272k_tokens_flex": 1.125e-05,
-        "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07
+        "cache_read_input_token_cost_above_272k_tokens_flex": 2.5e-07,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.4-pro": {
         "input_cost_per_token": 3e-05,
@@ -31845,7 +32093,8 @@
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 3e-05,
-        "output_cost_per_token_above_272k_tokens_flex": 0.000135
+        "output_cost_per_token_above_272k_tokens_flex": 0.000135,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.4-pro-2026-03-05": {
         "input_cost_per_token": 3e-05,
@@ -31894,7 +32143,8 @@
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false,
         "input_cost_per_token_above_272k_tokens_flex": 3e-05,
-        "output_cost_per_token_above_272k_tokens_flex": 0.000135
+        "output_cost_per_token_above_272k_tokens_flex": 0.000135,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-5.4-mini": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -31945,6 +32195,7 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -31997,6 +32248,7 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -32046,6 +32298,7 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -32095,6 +32348,7 @@
         "supports_web_search": true,
         "supports_none_reasoning_effort": true,
         "default_reasoning_effort": "none",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": false
     },
@@ -32113,6 +32367,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/batch",
             "/v1/responses"
@@ -32155,6 +32410,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/batch",
             "/v1/responses"
@@ -32187,6 +32443,7 @@
         "cache_read_input_token_cost_priority": 2.5e-07,
         "deprecation_date": "2026-12-11",
         "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_batches": 6.25e-07,
         "input_cost_per_token_flex": 6.25e-07,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -32195,6 +32452,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
         "output_cost_per_token_flex": 5e-06,
         "output_cost_per_token_priority": 2e-05,
         "search_context_cost_per_query": {
@@ -32202,6 +32460,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32526,6 +32785,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses"
         ],
@@ -32556,6 +32816,7 @@
         "cache_read_input_token_cost_flex": 1.25e-08,
         "cache_read_input_token_cost_priority": 4.5e-08,
         "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "openai",
@@ -32564,6 +32825,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 1e-06,
         "output_cost_per_token_flex": 1e-06,
         "output_cost_per_token_priority": 3.6e-06,
         "search_context_cost_per_query": {
@@ -32571,6 +32833,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32604,6 +32867,7 @@
         "cache_read_input_token_cost_priority": 4.5e-08,
         "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token_batches": 1.25e-07,
         "input_cost_per_token_flex": 1.25e-07,
         "input_cost_per_token_priority": 4.5e-07,
         "litellm_provider": "openai",
@@ -32612,6 +32876,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
+        "output_cost_per_token_batches": 1e-06,
         "output_cost_per_token_flex": 1e-06,
         "output_cost_per_token_priority": 3.6e-06,
         "search_context_cost_per_query": {
@@ -32619,6 +32884,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32650,6 +32916,7 @@
         "cache_read_input_token_cost": 5e-09,
         "cache_read_input_token_cost_flex": 2.5e-09,
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_batches": 2.5e-08,
         "input_cost_per_token_flex": 2.5e-08,
         "input_cost_per_token_priority": 2.5e-06,
         "litellm_provider": "openai",
@@ -32658,12 +32925,14 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_batches": 2e-07,
         "output_cost_per_token_flex": 2e-07,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32696,6 +32965,7 @@
         "cache_read_input_token_cost_flex": 2.5e-09,
         "deprecation_date": "2026-12-11",
         "input_cost_per_token": 5e-08,
+        "input_cost_per_token_batches": 2.5e-08,
         "input_cost_per_token_priority": 2.5e-06,
         "input_cost_per_token_flex": 2.5e-08,
         "litellm_provider": "openai",
@@ -32704,12 +32974,14 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
+        "output_cost_per_token_batches": 2e-07,
         "output_cost_per_token_flex": 2e-07,
         "search_context_cost_per_query": {
             "search_context_size_high": 0.01,
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/batch",
@@ -32742,9 +33014,11 @@
         "deprecation_date": "2026-10-23",
         "input_cost_per_image_token": 1e-05,
         "input_cost_per_token": 5e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
         "output_cost_per_image_token": 4e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -32755,9 +33029,11 @@
         "deprecation_date": "2026-12-01",
         "input_cost_per_image_token": 2.5e-06,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
         "output_cost_per_image_token": 8e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -32778,6 +33054,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1.6e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32811,6 +33088,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1.6e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32844,6 +33122,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 2.4e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32879,6 +33158,7 @@
         "output_cost_per_token": 2.4e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32914,6 +33194,7 @@
         "output_cost_per_token": 2.4e-06,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32939,6 +33220,7 @@
         "cache_read_input_token_cost": 6e-08,
         "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1e-05,
+        "input_cost_per_image_token": 8e-07,
         "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 32000,
@@ -32947,6 +33229,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -32981,6 +33264,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 6.4e-05,
         "output_cost_per_token": 1.6e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -37700,12 +37984,15 @@
         "cache_read_input_token_cost": 7.5e-06,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.5e-05,
+        "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 6e-05,
+        "output_cost_per_token_batches": 3e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_pdf_input": true,
@@ -37720,12 +38007,15 @@
         "cache_read_input_token_cost": 7.5e-06,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.5e-05,
+        "input_cost_per_token_batches": 7.5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 6e-05,
+        "output_cost_per_token_batches": 3e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -37747,6 +38037,7 @@
         "mode": "responses",
         "output_cost_per_token": 0.0006,
         "output_cost_per_token_batches": 0.0003,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -37780,6 +38071,7 @@
         "mode": "responses",
         "output_cost_per_token": 0.0006,
         "output_cost_per_token_batches": 0.0003,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -37807,6 +38099,7 @@
         "cache_read_input_token_cost_flex": 2.5e-07,
         "cache_read_input_token_cost_priority": 8.75e-07,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "input_cost_per_token_flex": 1e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -37815,6 +38108,7 @@
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 8e-06,
+        "output_cost_per_token_batches": 4e-06,
         "output_cost_per_token_flex": 4e-06,
         "output_cost_per_token_priority": 1.4e-05,
         "search_context_cost_per_query": {
@@ -37822,6 +38116,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/chat/completions",
@@ -37851,6 +38146,7 @@
         "cache_read_input_token_cost_priority": 8.75e-07,
         "deprecation_date": "2026-12-11",
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
         "input_cost_per_token_flex": 1e-06,
         "input_cost_per_token_priority": 3.5e-06,
         "litellm_provider": "openai",
@@ -37859,6 +38155,7 @@
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 8e-06,
+        "output_cost_per_token_batches": 4e-06,
         "output_cost_per_token_flex": 4e-06,
         "output_cost_per_token_priority": 1.4e-05,
         "search_context_cost_per_query": {
@@ -37866,6 +38163,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/chat/completions",
@@ -37975,12 +38273,15 @@
         "cache_read_input_token_cost": 5.5e-07,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
+        "input_cost_per_token_batches": 5.5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "output_cost_per_token_batches": 2.2e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_prompt_caching": true,
@@ -37993,12 +38294,15 @@
         "cache_read_input_token_cost": 5.5e-07,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
+        "input_cost_per_token_batches": 5.5e-07,
         "litellm_provider": "openai",
         "max_input_tokens": 200000,
         "max_output_tokens": 100000,
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "output_cost_per_token_batches": 2.2e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_prompt_caching": true,
@@ -38022,6 +38326,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -38059,6 +38364,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/responses",
             "/v1/batch"
@@ -38082,10 +38388,11 @@
     },
     "o4-mini": {
         "cache_read_input_token_cost": 2.75e-07,
-        "cache_read_input_token_cost_flex": 1.375e-07,
+        "cache_read_input_token_cost_flex": 1.38e-07,
         "cache_read_input_token_cost_priority": 5e-07,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
+        "input_cost_per_token_batches": 5.5e-07,
         "input_cost_per_token_flex": 5.5e-07,
         "input_cost_per_token_priority": 2e-06,
         "litellm_provider": "openai",
@@ -38094,6 +38401,7 @@
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "output_cost_per_token_batches": 2.2e-06,
         "output_cost_per_token_flex": 2.2e-06,
         "output_cost_per_token_priority": 8e-06,
         "search_context_cost_per_query": {
@@ -38101,6 +38409,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_pdf_input": true,
@@ -38113,10 +38422,11 @@
     },
     "o4-mini-2025-04-16": {
         "cache_read_input_token_cost": 2.75e-07,
-        "cache_read_input_token_cost_flex": 1.375e-07,
+        "cache_read_input_token_cost_flex": 1.38e-07,
         "cache_read_input_token_cost_priority": 5e-07,
         "deprecation_date": "2026-10-23",
         "input_cost_per_token": 1.1e-06,
+        "input_cost_per_token_batches": 5.5e-07,
         "input_cost_per_token_flex": 5.5e-07,
         "input_cost_per_token_priority": 2e-06,
         "litellm_provider": "openai",
@@ -38125,6 +38435,7 @@
         "max_tokens": 100000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "output_cost_per_token_batches": 2.2e-06,
         "output_cost_per_token_flex": 2.2e-06,
         "output_cost_per_token_priority": 8e-06,
         "search_context_cost_per_query": {
@@ -38132,6 +38443,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": false,
         "supports_pdf_input": true,
@@ -43294,7 +43606,8 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0,
         "output_cost_per_token_batches": 0.0,
-        "output_vector_size": 3072
+        "output_vector_size": 3072,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "text-embedding-3-small": {
         "input_cost_per_token": 2e-08,
@@ -43305,7 +43618,8 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0,
         "output_cost_per_token_batches": 0.0,
-        "output_vector_size": 1536
+        "output_vector_size": 1536,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "text-embedding-ada-002": {
         "input_cost_per_token": 1e-07,
@@ -43314,7 +43628,8 @@
         "max_tokens": 8191,
         "mode": "embedding",
         "output_cost_per_token": 0.0,
-        "output_vector_size": 1536
+        "output_vector_size": 1536,
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "text-embedding-ada-002-v2": {
         "input_cost_per_token": 1e-07,
@@ -43485,7 +43800,7 @@
         "input_cost_per_token": 1.2e-06,
         "output_cost_per_token": 1.2e-06,
         "max_input_tokens": 131072,
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen2.5-7B-Instruct-Turbo": {
         "litellm_provider": "together_ai",
@@ -43497,7 +43812,7 @@
         "input_cost_per_token": 3e-07,
         "output_cost_per_token": 3e-07,
         "max_input_tokens": 32768,
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3-235B-A22B-Instruct-2507-tput": {
         "deprecation_date": "2026-07-10",
@@ -43544,7 +43859,7 @@
         "max_input_tokens": 256000,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
-        "source": "https://www.together.ai/models/qwen3-coder-480b-a35b-instruct",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43606,7 +43921,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 1.7e-06,
-        "source": "https://www.together.ai/models/deepseek-v3-1",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43630,7 +43945,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.04e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43664,6 +43979,7 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 5.9e-07,
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43686,6 +44002,7 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 8.8e-07,
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43697,6 +44014,7 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 1.8e-07,
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43713,7 +44031,7 @@
         "input_cost_per_token": 2e-07,
         "output_cost_per_token": 2e-07,
         "max_input_tokens": 32768,
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/mistralai/Mistral-Small-24B-Instruct-2501": {
         "deprecation_date": "2026-04-02",
@@ -43725,7 +44043,7 @@
         "input_cost_per_token": 1e-07,
         "output_cost_per_token": 3e-07,
         "max_input_tokens": 32768,
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/mistralai/Mixtral-8x7B-Instruct-v0.1": {
         "deprecation_date": "2026-04-16",
@@ -43733,6 +44051,7 @@
         "litellm_provider": "together_ai",
         "mode": "chat",
         "output_cost_per_token": 6e-07,
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43759,7 +44078,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 6e-07,
-        "source": "https://www.together.ai/models/gpt-oss-120b",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43773,7 +44092,7 @@
         "max_input_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 2e-07,
-        "source": "https://www.together.ai/models/gpt-oss-20b",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43793,7 +44112,7 @@
         "max_input_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 1.1e-06,
-        "source": "https://www.together.ai/models/glm-4-5-air",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43809,7 +44128,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 2.2e-06,
-        "source": "https://www.together.ai/models/glm-4-6",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43826,7 +44145,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 2e-06,
-        "source": "https://www.together.ai/models/glm-4-7",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43874,7 +44193,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://www.together.ai/models/qwen3-next-80b-a3b-instruct",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43890,7 +44209,7 @@
         },
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://www.together.ai/models/qwen3-next-80b-a3b-thinking",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -43904,7 +44223,7 @@
         "max_input_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
-        "source": "https://www.together.ai/models/qwen3-5-397b-a17b",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -43919,7 +44238,7 @@
         "max_tokens": 524288,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -43944,7 +44263,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 2.5e-07,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_reasoning": true,
@@ -43959,7 +44278,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 3e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_reasoning": true
     },
     "together_ai/Qwen/Qwen3.7-Max": {
@@ -43970,7 +44289,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 7.5e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
     "together_ai/Qwen/Qwen3.7-Plus": {
@@ -43980,7 +44299,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 1.28e-06,
-        "source": "https://docs.together.ai/docs/serverless-models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3.8-2.4T-A95B": {
         "cache_read_input_token_cost": 2.5e-07,
@@ -43990,7 +44309,7 @@
         "max_tokens": 1010000,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
     "together_ai/arize-ai/qwen-2-1.5b-instruct": {
@@ -44000,7 +44319,7 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 1e-07,
-        "source": "https://docs.together.ai/docs/serverless-models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/deepseek-ai/DeepSeek-V4-Flash-0731": {
         "cache_read_input_token_cost": 3e-08,
@@ -44010,7 +44329,7 @@
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 2.8e-07,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44042,7 +44361,7 @@
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 3.96e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44067,7 +44386,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 9.7e-07,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_response_schema": true,
@@ -44103,7 +44422,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
     "together_ai/moonshotai/Kimi-K2.7-Code": {
@@ -44115,7 +44434,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44136,7 +44455,7 @@
             "high",
             "max"
         ],
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44154,7 +44473,7 @@
         "max_tokens": 512288,
         "mode": "chat",
         "output_cost_per_token": 3.6e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44180,7 +44499,7 @@
         "max_tokens": 524288,
         "mode": "chat",
         "output_cost_per_token": 4.05e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44196,7 +44515,7 @@
         "max_tokens": 524288,
         "mode": "chat",
         "output_cost_per_token": 1.2e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_prompt_caching": true
     },
     "together_ai/zai-org/GLM-5.2": {
@@ -44208,7 +44527,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44225,7 +44544,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44242,7 +44561,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
-        "source": "https://docs.together.ai/docs/serverless-models",
+        "source": "https://api.together.ai/v1/models",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_prompt_caching": true,
@@ -44255,6 +44574,7 @@
         "input_cost_per_character": 1.5e-05,
         "litellm_provider": "openai",
         "mode": "audio_speech",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ]
@@ -44263,6 +44583,7 @@
         "input_cost_per_character": 3e-05,
         "litellm_provider": "openai",
         "mode": "audio_speech",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ]
@@ -47605,6 +47926,9 @@
         "cache_read_input_token_cost": 3e-08,
         "input_cost_per_audio_token": 1e-06,
         "input_cost_per_token": 3e-07,
+        "input_cost_per_token_batches": 1.5e-07,
+        "input_cost_per_token_flex": 1.5e-07,
+        "input_cost_per_token_priority": 5.4e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 32768,
         "max_output_tokens": 32768,
@@ -47614,8 +47938,10 @@
         "output_cost_per_image_token": 3e-05,
         "output_cost_per_reasoning_token": 2.5e-06,
         "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_batches": 1.25e-06,
+        "output_cost_per_token_flex": 1.25e-06,
         "rpm": 100000,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/image-generation#edit-an-image",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -47647,10 +47973,19 @@
         "supports_image_size": false
     },
     "vertex_ai/gemini-3-pro-image": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "cache_read_input_token_cost_above_200k_tokens_priority": 7.2e-07,
+        "cache_read_input_token_cost_flex": 1e-07,
+        "cache_read_input_token_cost_priority": 3.6e-07,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "input_cost_per_token_above_200k_tokens_priority": 7.2e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_flex": 1e-06,
+        "input_cost_per_token_priority": 3.6e-06,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -47659,9 +47994,13 @@
         "output_cost_per_image": 0.134,
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_above_200k_tokens": 1.8e-05,
+        "output_cost_per_token_above_200k_tokens_priority": 3.24e-05,
         "output_cost_per_token_batches": 6e-06,
+        "output_cost_per_token_flex": 6e-06,
+        "output_cost_per_token_priority": 2.16e-05,
         "supports_reasoning": false,
-        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
     },
     "vertex_ai/gemini-3-pro-image-preview": {
         "input_cost_per_image": 0.0011,
@@ -47680,9 +48019,13 @@
         "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
     },
     "vertex_ai/gemini-3.1-flash-image": {
+        "cache_read_input_token_cost": 5e-08,
+        "cache_read_input_token_cost_flex": 2.5e-08,
         "deprecation_date": "2027-05-28",
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "input_cost_per_token_flex": 2.5e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 32768,
@@ -47691,8 +48034,10 @@
         "output_cost_per_image": 0.0672,
         "output_cost_per_image_token": 6e-05,
         "output_cost_per_token": 3e-06,
+        "output_cost_per_token_batches": 1.5e-06,
+        "output_cost_per_token_flex": 1.5e-06,
         "supports_reasoning": false,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
     },
     "vertex_ai/gemini-3.1-flash-image-preview": {
         "input_cost_per_image": 0.00056,
@@ -47710,9 +48055,11 @@
     },
     "vertex_ai/gemini-3.1-flash-lite-image": {
         "cache_read_input_token_cost": 2.5e-08,
+        "cache_read_input_token_cost_flex": 1.25e-08,
         "input_cost_per_image": 0.00028,
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
+        "input_cost_per_token_flex": 1.25e-07,
         "litellm_provider": "vertex_ai-language-models",
         "max_input_tokens": 65536,
         "max_output_tokens": 4096,
@@ -47722,6 +48069,7 @@
         "output_cost_per_image_token": 3e-05,
         "output_cost_per_token": 1.5e-06,
         "output_cost_per_token_batches": 7.5e-07,
+        "output_cost_per_token_flex": 7.5e-07,
         "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
@@ -47796,6 +48144,7 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "vertex_ai/gemini-3.1-flash-lite": {
+        "cache_read_input_audio_token_cost": 5e-08,
         "deprecation_date": "2027-05-07",
         "cache_read_input_token_cost": 2.5e-08,
         "cache_read_input_token_cost_flex": 1.25e-08,
@@ -47816,7 +48165,7 @@
         "output_cost_per_token_flex": 7.5e-07,
         "output_cost_per_token_priority": 2.7e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -47858,7 +48207,7 @@
         "deprecation_date": "2027-07-21",
         "cache_read_input_token_cost": 3e-08,
         "cache_read_input_token_cost_flex": 1.5e-08,
-        "cache_read_input_token_cost_priority": 5e-08,
+        "cache_read_input_token_cost_priority": 5.4e-08,
         "input_cost_per_token": 3e-07,
         "input_cost_per_token_batches": 1.5e-07,
         "input_cost_per_token_flex": 1.5e-07,
@@ -47874,7 +48223,7 @@
         "output_cost_per_token_flex": 1.25e-06,
         "output_cost_per_token_priority": 4.5e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
-        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -47913,6 +48262,7 @@
         "google_maps_grounding_cost_per_query": 0.014
     },
     "vertex_ai/deep-research-pro-preview-12-2025": {
+        "cache_read_input_token_cost": 2e-07,
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
         "input_cost_per_token_batches": 1e-06,
@@ -47925,7 +48275,7 @@
         "output_cost_per_image_token": 0.00012,
         "output_cost_per_token": 1.2e-05,
         "output_cost_per_token_batches": 6e-06,
-        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
     },
     "vertex_ai/imagegeneration@006": {
         "litellm_provider": "vertex_ai-image-models",
@@ -49588,7 +49938,8 @@
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ],
-        "deprecation_date": "2027-02-26"
+        "deprecation_date": "2027-02-26",
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "xai/grok-3": {
         "cache_read_input_token_cost": 2e-07,
@@ -52685,10 +53036,11 @@
         "max_tokens": 40960,
         "max_input_tokens": 40960,
         "max_output_tokens": 40960,
-        "input_cost_per_token": 0.0,
+        "input_cost_per_token": 2e-07,
         "output_cost_per_token": 0.0,
         "litellm_provider": "fireworks_ai",
-        "mode": "rerank"
+        "mode": "rerank",
+        "source": "https://api.fireworks.ai/v1/serverless/models"
     },
     "fireworks_ai/accounts/fireworks/models/qwen3-vl-235b-a22b-instruct": {
         "max_tokens": 262144,
@@ -52753,7 +53105,7 @@
         "max_tokens": 65536,
         "mode": "chat",
         "output_cost_per_token": 1.6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -54652,12 +55004,13 @@
     },
     "gpt-4o-mini-tts-2025-03-20": {
         "deprecation_date": "2026-07-23",
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "mode": "audio_speech",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_second": 0.00025,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ],
@@ -54670,12 +55023,13 @@
         ]
     },
     "gpt-4o-mini-tts-2025-12-15": {
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_token": 6e-07,
         "litellm_provider": "openai",
         "mode": "audio_speech",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_second": 0.00025,
         "output_cost_per_token": 1e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/speech"
         ],
@@ -54690,24 +55044,28 @@
     "gpt-4o-mini-transcribe-2025-03-20": {
         "deprecation_date": "2027-01-20",
         "input_cost_per_audio_token": 1.25e-06,
+        "input_cost_per_second": 5e-05,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "mode": "audio_transcription",
         "output_cost_per_token": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ]
     },
     "gpt-4o-mini-transcribe-2025-12-15": {
         "input_cost_per_audio_token": 1.25e-06,
+        "input_cost_per_second": 5e-05,
         "input_cost_per_token": 1.25e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "mode": "audio_transcription",
         "output_cost_per_token": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
         ]
@@ -54726,6 +55084,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -54753,6 +55112,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
         "supports_pdf_input": true,
@@ -54780,6 +55140,7 @@
         "mode": "realtime",
         "output_cost_per_audio_token": 2e-05,
         "output_cost_per_token": 2.4e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime"
         ],
@@ -54831,13 +55192,14 @@
         "supports_parallel_function_calling": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "deprecation_date": "2027-01-20"
+        "deprecation_date": "2027-01-20",
+        "source": "https://developers.openai.com/api/docs/pricing"
     },
     "gpt-realtime-whisper": {
-        "input_cost_per_second": 0.0002833333333333333,
+        "input_cost_per_second": 0.000283333333333,
         "litellm_provider": "openai",
         "mode": "audio_transcription",
-        "source": "https://developers.openai.com/api/docs/models/gpt-realtime-whisper",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime",
             "/v1/realtime/transcription_sessions"
@@ -54855,7 +55217,7 @@
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.1,
-        "source": "https://platform.openai.com/docs/api-reference/videos",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_modalities": [
             "text",
             "image"
@@ -54869,7 +55231,7 @@
         "litellm_provider": "openai",
         "mode": "video_generation",
         "output_cost_per_video_per_second": 0.3,
-        "source": "https://platform.openai.com/docs/api-reference/videos",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_modalities": [
             "text",
             "image"
@@ -54894,11 +55256,15 @@
     "chatgpt-image-latest": {
         "cache_read_input_token_cost": 1.25e-06,
         "deprecation_date": "2026-12-01",
-        "input_cost_per_image_token": 1e-05,
+        "input_cost_per_image_token": 8e-06,
         "input_cost_per_token": 5e-06,
+        "input_cost_per_token_batches": 2.5e-06,
         "litellm_provider": "openai",
         "mode": "image_generation",
-        "output_cost_per_image_token": 4e-05,
+        "output_cost_per_image_token": 3.2e-05,
+        "output_cost_per_token": 1e-05,
+        "output_cost_per_token_batches": 5e-06,
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/images/generations",
             "/v1/images/edits"
@@ -57373,7 +57739,7 @@
         "input_cost_per_second": 7.5e-05,
         "litellm_provider": "openai",
         "mode": "audio_transcription",
-        "source": "https://developers.openai.com/api/docs/models/gpt-transcribe",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/audio/transcriptions",
             "/v1/realtime/transcription_sessions"
@@ -57388,10 +57754,10 @@
         "supports_audio_input": true
     },
     "gpt-live-transcribe": {
-        "input_cost_per_second": 0.0002833333333333333,
+        "input_cost_per_second": 0.000283333333333,
         "litellm_provider": "openai",
         "mode": "audio_transcription",
-        "source": "https://developers.openai.com/api/docs/models/gpt-live-transcribe",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_endpoints": [
             "/v1/realtime",
             "/v1/realtime/transcription_sessions"
@@ -57406,10 +57772,10 @@
         "supports_audio_input": true
     },
     "gpt-live-1": {
-        "input_cost_per_second": 0.0008333333333333334,
+        "input_cost_per_second": 0.000833333333333,
         "litellm_provider": "openai",
         "mode": "realtime",
-        "source": "https://developers.openai.com/api/docs/models/gpt-live-1",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_modalities": [
             "text",
             "audio"
@@ -57423,13 +57789,13 @@
         "supports_function_calling": true
     },
     "gpt-realtime-translate": {
-        "input_cost_per_second": 0.0005666666666666667,
+        "input_cost_per_second": 0.000566666666667,
         "litellm_provider": "openai",
         "max_input_tokens": 16000,
         "max_output_tokens": 2000,
         "max_tokens": 2000,
         "mode": "realtime",
-        "source": "https://developers.openai.com/api/docs/models/gpt-realtime-translate",
+        "source": "https://developers.openai.com/api/docs/pricing",
         "supported_modalities": [
             "audio"
         ],
@@ -57457,7 +57823,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
-        "source": "https://platform.claude.com/docs/en/about-claude/models/overview",
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing",
         "supports_adaptive_thinking": true,
         "thinking_always_on": true,
         "supports_mid_conversation_system": true,
@@ -57518,7 +57884,7 @@
         "supports_output_config": true,
         "prompt_cache_min_tokens": 512,
         "supports_native_structured_output": true,
-        "source": "https://platform.claude.com/docs/en/models/mythos-5-1/overview"
+        "source": "https://platform.claude.com/docs/en/about-claude/pricing"
     },
     "claude-mythos-preview": {
         "cache_creation_input_token_cost": 1.25e-05,
@@ -57874,6 +58240,7 @@
     },
     "vertex_ai/gemini-3.5-live-translate-preview": {
         "input_cost_per_audio_token": 3.5e-06,
+        "input_cost_per_second": 8.83333333333e-05,
         "input_cost_per_token": 3.5e-06,
         "litellm_provider": "vertex_ai",
         "mode": "realtime",
@@ -57976,14 +58343,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 8.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -57992,14 +58362,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/deepseek-v4p1-flash": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash",
+        "output_cost_per_token_priority": 8.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -58015,26 +58388,29 @@
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_vision": true
     },
     "fireworks_ai/accounts/fireworks/models/kimi-k3": {
         "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_priority": 3.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_priority": 1.875e-05,
         "reasoning_effort_levels": [
             "low",
             "high",
             "max"
         ],
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58043,14 +58419,17 @@
     },
     "fireworks_ai/deepseek-v4-flash-0731": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 8.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58059,14 +58438,17 @@
     },
     "fireworks_ai/deepseek-v4p1-flash": {
         "cache_read_input_token_cost": 7e-09,
+        "cache_read_input_token_cost_priority": 8.75e-09,
         "input_cost_per_token": 2.2e-07,
+        "input_cost_per_token_priority": 2.75e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 393216,
         "max_tokens": 393216,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://fireworks.ai/models/deepseek-ai/deepseek-v4p1-flash",
+        "output_cost_per_token_priority": 8.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_prompt_caching": true,
         "supports_reasoning": true,
@@ -58082,7 +58464,7 @@
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 6.6e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_tool_choice": true,
         "supports_vision": true
@@ -58121,19 +58503,22 @@
     },
     "fireworks_ai/kimi-k3": {
         "cache_read_input_token_cost": 3e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 3e-06,
+        "input_cost_per_token_priority": 3.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 1.5e-05,
+        "output_cost_per_token_priority": 1.875e-05,
         "reasoning_effort_levels": [
             "low",
             "high",
             "max"
         ],
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58184,12 +58569,15 @@
     },
     "fireworks_ai/qwen3p8-max": {
         "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_priority": 3e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 9e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58205,7 +58593,7 @@
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58237,7 +58625,7 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58253,7 +58641,7 @@
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58285,7 +58673,7 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 2.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58294,12 +58682,15 @@
     },
     "fireworks_ai/accounts/fireworks/models/qwen3p8-max": {
         "cache_read_input_token_cost": 2.5e-07,
+        "cache_read_input_token_cost_priority": 3.75e-07,
         "input_cost_per_token": 2e-06,
+        "input_cost_per_token_priority": 3e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 9e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58315,7 +58706,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 6.6e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -58352,7 +58743,7 @@
             "high",
             "max"
         ],
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -61050,14 +61441,17 @@
     },
     "fireworks_ai/accounts/fireworks/models/glm-5p3": {
         "cache_read_input_token_cost": 2.6e-07,
+        "cache_read_input_token_cost_priority": 3.25e-07,
         "input_cost_per_token": 1.4e-06,
+        "input_cost_per_token_priority": 1.75e-06,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 5.5e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -61066,13 +61460,16 @@
     },
     "fireworks_ai/accounts/fireworks/models/glm-5p3-flash": {
         "cache_read_input_token_cost": 3e-08,
+        "cache_read_input_token_cost_priority": 3.75e-08,
         "input_cost_per_token": 1.5e-07,
+        "input_cost_per_token_priority": 1.875e-07,
         "litellm_provider": "fireworks_ai",
         "max_input_tokens": 1048576,
         "max_tokens": 1048576,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
-        "source": "https://docs.fireworks.ai/serverless/pricing",
+        "output_cost_per_token_priority": 6.25e-07,
+        "source": "https://api.fireworks.ai/v1/serverless/models",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -61100,7 +61497,7 @@
         "max_output_tokens": 40960,
         "max_tokens": 40960,
         "mode": "embedding",
-        "source": "https://docs.fireworks.ai/serverless/pricing"
+        "source": "https://api.fireworks.ai/v1/serverless/models"
     },
     "zai/glm-5.2": {
         "cache_creation_input_token_cost": 0,
@@ -61124,7 +61521,7 @@
         "max_tokens": 1000000,
         "mode": "chat",
         "output_cost_per_token": 4.7e-07,
-        "source": "https://docs.together.ai/docs/serverless-models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/moonshotai/Kimi-K2.6": {
         "deprecation_date": "2026-08-19",
@@ -61134,7 +61531,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/moonshotai/Kimi-K2.5-fp4": {
         "input_cost_per_token": 5e-07,
@@ -61142,7 +61539,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/MiniMaxAI/MiniMax-M2.7": {
         "input_cost_per_token": 3e-07,
@@ -61151,7 +61548,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 196608,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/zai-org/GLM-5": {
         "deprecation_date": "2026-06-22",
@@ -61160,7 +61557,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 202752,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/zai-org/GLM-5.1": {
         "deprecation_date": "2026-07-10",
@@ -61170,7 +61567,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 202752,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/deepseek-ai/DeepSeek-R1-0528": {
         "input_cost_per_token": 3e-06,
@@ -61178,7 +61575,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 163840,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3-Coder-Next-FP8": {
         "deprecation_date": "2026-05-14",
@@ -61187,7 +61584,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3-VL-32B-Instruct": {
         "deprecation_date": "2026-02-25",
@@ -61196,7 +61593,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/Qwen3-VL-8B-Instruct": {
         "deprecation_date": "2026-04-16",
@@ -61205,7 +61602,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/mistralai/Ministral-3-14B-Instruct-2512": {
         "input_cost_per_token": 2e-07,
@@ -61213,7 +61610,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 262144,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
         "input_cost_per_token": 6e-08,
@@ -61221,7 +61618,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 131072,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/mistralai/Mistral-7B-Instruct-v0.3": {
         "input_cost_per_token": 2e-07,
@@ -61229,7 +61626,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 32768,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "together_ai/Qwen/QwQ-32B": {
         "deprecation_date": "2025-11-13",
@@ -61238,7 +61635,7 @@
         "litellm_provider": "together_ai",
         "max_input_tokens": 131072,
         "mode": "chat",
-        "source": "https://api.together.xyz/v1/models"
+        "source": "https://api.together.ai/v1/models"
     },
     "cerebras/gemma-4-31b": {
         "input_cost_per_token": 9.9e-07,
@@ -65365,5 +65762,263 @@
         "supports_tool_choice": false,
         "supports_response_schema": true,
         "supports_vision": false
+    },
+    "fireworks_ai/accounts/fireworks/routers/glm-5p3-fast": {
+        "cache_read_input_token_cost": 3.9e-07,
+        "input_cost_per_token": 2.1e-06,
+        "litellm_provider": "fireworks_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6.6e-06,
+        "source": "https://api.fireworks.ai/v1/serverless/models"
+    },
+    "together_ai/arcee-ai/trinity-mini": {
+        "input_cost_per_token": 4.5e-08,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/deepseek-coder-33b-instruct": {
+        "input_cost_per_token": 8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/DeepSeek-R1-Distill-Llama-70B": {
+        "input_cost_per_token": 2e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 2e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B": {
+        "input_cost_per_token": 1.8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B": {
+        "input_cost_per_token": 1.6e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.6e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/deepseek-ai/DeepSeek-V4.1-Flash": {
+        "cache_read_input_token_cost": 6e-09,
+        "input_cost_per_token": 3e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "vertex_ai/gemini-2.5-flash-native-audio": {
+        "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_token": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "realtime",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_token": 2e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-2.5-flash-preview-tts": {
+        "input_cost_per_token": 5e-07,
+        "input_cost_per_token_batches": 2.5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 1e-05,
+        "output_cost_per_token": 1e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-3.1-flash-live-preview": {
+        "input_cost_per_audio_token": 3e-06,
+        "input_cost_per_second": 8.33333333333e-05,
+        "input_cost_per_token": 7.5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "realtime",
+        "output_cost_per_audio_token": 1.2e-05,
+        "output_cost_per_token": 4.5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-3.1-flash-tts-preview": {
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "audio_speech",
+        "output_cost_per_audio_token": 2e-05,
+        "output_cost_per_token": 2e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-3.5-transcribe": {
+        "input_cost_per_audio_token": 2e-06,
+        "input_cost_per_second": 5e-05,
+        "litellm_provider": "vertex_ai",
+        "mode": "audio_transcription",
+        "output_cost_per_token": 1.2e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-3.5-transcribe-live": {
+        "input_cost_per_audio_token": 3.5e-06,
+        "input_cost_per_second": 8.33333333333e-05,
+        "litellm_provider": "vertex_ai",
+        "mode": "audio_transcription",
+        "output_cost_per_token": 2.1e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-omni-1.1-flash": {
+        "input_cost_per_token": 1.5e-06,
+        "litellm_provider": "vertex_ai",
+        "mode": "chat",
+        "output_cost_per_token": 9e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemini-robotics-er-2": {
+        "cache_read_input_token_cost": 1e-07,
+        "input_cost_per_token": 1e-06,
+        "input_cost_per_token_batches": 5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "chat",
+        "output_cost_per_token": 5e-06,
+        "output_cost_per_token_batches": 2.5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "vertex_ai/gemma-4-26b-a4b-it": {
+        "cache_read_input_token_cost": 1.5e-08,
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "vertex_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing"
+    },
+    "together_ai/google/gemma-2-27b-it": {
+        "input_cost_per_token": 8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "gpt-5.5-cyber": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 1.25e-05,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "output_cost_per_token": 7.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing",
+        "supports_reasoning": true
+    },
+    "gpt-rosalind-research": {
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-05,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "together_ai/meta-llama/Llama-3-8b-chat-hf": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 2e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Llama-3.1-405B-Instruct": {
+        "input_cost_per_token": 3.5e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 3.5e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Llama-3.2-1B-Instruct": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6e-08,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Llama-3.2-3B-Instruct": {
+        "input_cost_per_token": 6e-08,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6e-08,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Meta-Llama-3-70B-Instruct-Turbo": {
+        "input_cost_per_token": 8.8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8.8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/meta-llama/Meta-Llama-3-8B-Instruct": {
+        "input_cost_per_token": 2e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 2e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO": {
+        "input_cost_per_token": 6e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 6e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF": {
+        "input_cost_per_token": 8.8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8.8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2-1.5B-Instruct": {
+        "input_cost_per_token": 2e-08,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 2e-08,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2-72B-Instruct": {
+        "input_cost_per_token": 9e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 9e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2-VL-72B-Instruct": {
+        "input_cost_per_token": 1.2e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2.5-14B-Instruct": {
+        "input_cost_per_token": 8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2.5-72B-Instruct": {
+        "input_cost_per_token": 1.2e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 1.2e-06,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2.5-Coder-32B-Instruct": {
+        "input_cost_per_token": 8e-07,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-07,
+        "source": "https://api.together.ai/v1/models"
+    },
+    "together_ai/Qwen/Qwen2.5-VL-72B-Instruct": {
+        "input_cost_per_token": 1.95e-06,
+        "litellm_provider": "together_ai",
+        "mode": "chat",
+        "output_cost_per_token": 8e-06,
+        "source": "https://api.together.ai/v1/models"
     }
 }
diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
index 2fadb1fd959..2289de9a951 100644
--- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
+++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
@@ -4560,7 +4560,7 @@ GEMINI_35_FLASH_LITE_TIER_RATES_BY_SURFACE = [
     ("gemini", "priority", 5.4e-07, 4.5e-06, 5e-08),
     ("vertex_ai", None, 3e-07, 2.5e-06, 3e-08),
     ("vertex_ai", "flex", 1.5e-07, 1.25e-06, 1.5e-08),
-    ("vertex_ai", "priority", 5.4e-07, 4.5e-06, 5e-08),
+    ("vertex_ai", "priority", 5.4e-07, 4.5e-06, 5.4e-08),
 ]