diff --git a/litellm/llms/bedrock/chat/converse_transformation.py b/litellm/llms/bedrock/chat/converse_transformation.py
index fa24f8be893..4cdf387a11d 100644
--- a/litellm/llms/bedrock/chat/converse_transformation.py
+++ b/litellm/llms/bedrock/chat/converse_transformation.py
@@ -4,6 +4,7 @@ Translating between OpenAI's `/chat/completion` format and Amazon's `/converse`
 
 import copy
 import json
+import re
 import time
 import types
 from collections.abc import Mapping
@@ -293,6 +294,10 @@ class AmazonConverseConfig(BaseConfig):
                     llm_provider="bedrock",
                 )
 
+    @staticmethod
+    def _is_openai_gpt_reasoning_model(model: str) -> bool:
+        return re.search(r"openai\.gpt-\d", model) is not None
+
     def _is_nova_2_model(self, model: str) -> bool:
         """
         Check if the model is a Nova 2 model that supports reasoningConfig.
@@ -423,14 +428,14 @@ class AmazonConverseConfig(BaseConfig):
         Handle the reasoning_effort parameter based on the model type.
 
         - GPT-OSS models: passed through unchanged via additionalModelRequestFields.
-        - OpenAI GPT-5.x models: mapped to ``reasoning.effort`` via additionalModelRequestFields.
+        - OpenAI GPT-5.x and GPT-6 models: mapped to ``reasoning.effort`` via additionalModelRequestFields.
         - Nova 2 models: transformed to reasoningConfig.
         - Anthropic models: mapped to ``thinking`` (and ``output_config.effort`` on
           adaptive Claude 4.6 / 4.7).
         """
         if "gpt-oss" in model:
             optional_params["reasoning_effort"] = reasoning_effort
-        elif "openai.gpt-5" in model:
+        elif self._is_openai_gpt_reasoning_model(model):
             reasoning: Final[BedrockConverseGptReasoningEffortBlock] = {"effort": reasoning_effort}
             optional_params["reasoning"] = reasoning
         elif self._is_nova_2_model(model):
@@ -564,7 +569,11 @@ class AmazonConverseConfig(BaseConfig):
             # only anthropic and mistral support tool choice config. otherwise (E.g. cohere) will fail the call - https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_ToolChoice.html
             supported_params.append("tool_choice")
 
-        if "gpt-oss" in model or "openai.gpt-5" in model or "openai.gpt-5" in base_model:
+        if (
+            "gpt-oss" in model
+            or self._is_openai_gpt_reasoning_model(model)
+            or self._is_openai_gpt_reasoning_model(base_model)
+        ):
             supported_params.append("reasoning_effort")
         elif self._is_nova_2_model(model):
             # Nova 2 models support reasoning_effort (transformed to reasoningConfig)
@@ -920,7 +929,7 @@ class AmazonConverseConfig(BaseConfig):
                 optional_params["_parallel_tool_use_config"] = {
                     "tool_choice": {"type": "auto", "disable_parallel_tool_use": not value}
                 }
-            if param == "thinking" and "openai.gpt-5" not in model:
+            if param == "thinking" and not self._is_openai_gpt_reasoning_model(model):
                 if (
                     isinstance(value, dict)
                     and value.get("type") == "adaptive"
@@ -1805,6 +1814,7 @@ class AmazonConverseConfig(BaseConfig):
             data=request_data,
             messages=messages,
             encoding=encoding,
+            json_mode=json_mode,
         )
 
     def _transform_reasoning_content(self, reasoning_content_blocks: list[BedrockConverseReasoningContentBlock]) -> str:
@@ -2237,6 +2247,7 @@ class AmazonConverseConfig(BaseConfig):
         data: dict | str,
         messages: list,
         encoding,
+        json_mode: bool | None = None,
     ) -> ModelResponse:
         ## LOGGING
         if logging_obj is not None:
@@ -2247,7 +2258,9 @@ class AmazonConverseConfig(BaseConfig):
                 additional_args={"complete_input_dict": data},
             )
 
-        json_mode: Final[bool | None] = optional_params.get("json_mode", None)
+        resolved_json_mode: Final[bool | None] = (
+            json_mode if json_mode is not None else optional_params.get("json_mode", None)
+        )
         ## RESPONSE OBJECT
         try:
             completion_response: Final = ConverseResponseBlock(**response.json())
@@ -2339,7 +2352,7 @@ class AmazonConverseConfig(BaseConfig):
             chat_completion_message["thinking_blocks"] = self._transform_thinking_blocks(reasoningContentBlocks)
         chat_completion_message["content"] = content_str
         filtered_tools: Final = self._filter_json_mode_tools(
-            json_mode=json_mode,
+            json_mode=resolved_json_mode,
             tools=tools,
             chat_completion_message=chat_completion_message,
         )
@@ -2363,7 +2376,7 @@ class AmazonConverseConfig(BaseConfig):
         # When json_mode filtered out all synthetic tool calls the response
         # is plain content, not a pending tool invocation. Fix finish_reason
         # so callers (e.g. OpenAI SDK) don't misinterpret it.
-        if json_mode and not filtered_tools and tools:
+        if resolved_json_mode and not filtered_tools and tools:
             initial_finish_reason = "stop"
 
         (
diff --git a/litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py b/litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py
index a0e32c8aa22..90a2692f68a 100644
--- a/litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py
+++ b/litellm/llms/bedrock/chat/invoke_transformations/base_invoke_transformation.py
@@ -340,6 +340,7 @@ class AmazonInvokeConfig(BaseConfig, BaseAWSLLM):
                     optional_params=optional_params,
                     litellm_params=litellm_params,
                     encoding=encoding,
+                    json_mode=json_mode,
                 )
             elif provider == "twelvelabs":
                 return litellm.AmazonTwelveLabsPegasusConfig().transform_response(
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 54ebdc85be9..0d2eda93323 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -364,7 +364,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "amazon.nova-2-lite-v1:0": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -380,6 +381,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -399,6 +401,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -416,6 +419,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -435,6 +439,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -452,6 +457,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -471,6 +477,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -488,6 +495,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -507,6 +515,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -537,7 +546,8 @@
         "output_cost_per_token": 1.4e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "amazon.nova-pro-v1:0": {
         "input_cost_per_token": 8e-07,
@@ -551,7 +561,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "amazon.nova-sonic-v1:0": {
         "deprecation_date": "2026-09-14",
@@ -756,6 +767,14 @@
         "mode": "chat",
         "supports_video_input": true
     },
+    "global.twelvelabs.pegasus-1-2-v1:0": {
+        "input_cost_per_video_per_second": 0.00049,
+        "output_cost_per_token": 7.5e-06,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_video_input": true,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "amazon.titan-text-express-v1": {
         "input_cost_per_token": 1.3e-06,
         "litellm_provider": "bedrock",
@@ -2876,7 +2895,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "apac.amazon.nova-micro-v1:0": {
         "input_cost_per_token": 3.7e-08,
@@ -2888,7 +2908,8 @@
         "output_cost_per_token": 1.48e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "apac.amazon.nova-pro-v1:0": {
         "input_cost_per_token": 8.4e-07,
@@ -2902,7 +2923,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "deprecation_date": "2026-07-30",
@@ -8064,7 +8086,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "deprecation_date": "2027-10-26"
     },
     "azure/us/gpt-5.5-2026-04-23": {
         "cache_read_input_token_cost": 5.5e-07,
@@ -8108,7 +8131,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "deprecation_date": "2027-10-26"
     },
     "azure/eu/gpt-5.5-2026-04-23": {
         "cache_read_input_token_cost": 5.5e-07,
@@ -8152,7 +8176,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "deprecation_date": "2027-10-26"
     },
     "azure/gpt-5.5-pro": {
         "cache_read_input_token_cost": 3e-06,
@@ -12317,7 +12342,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": {
         "input_cost_per_token": 1e-07,
@@ -12496,7 +12522,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "bedrock/us-gov-west-1/amazon.nova-micro-v1:0": {
         "input_cost_per_token": 4.2e-08,
@@ -12508,7 +12535,8 @@
         "output_cost_per_token": 1.68e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": {
         "input_cost_per_token": 9.6e-07,
@@ -12522,7 +12550,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": {
         "input_cost_per_token": 1e-07,
@@ -13973,7 +14002,8 @@
         "max_output_tokens": 3072,
         "max_tokens": 3072,
         "mode": "chat",
-        "output_cost_per_token": 1.923e-06
+        "output_cost_per_token": 1.923e-06,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-2-7b-chat-int8": {
         "input_cost_per_token": 1.923e-06,
@@ -13982,7 +14012,8 @@
         "max_output_tokens": 2048,
         "max_tokens": 2048,
         "mode": "chat",
-        "output_cost_per_token": 1.923e-06
+        "output_cost_per_token": 1.923e-06,
+        "rpm": 300
     },
     "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": {
         "input_cost_per_token": 1.923e-06,
@@ -13991,7 +14022,8 @@
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 1.923e-06
+        "output_cost_per_token": 1.923e-06,
+        "rpm": 300
     },
     "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": {
         "input_cost_per_token": 1.923e-06,
@@ -14000,7 +14032,8 @@
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 1.923e-06
+        "output_cost_per_token": 1.923e-06,
+        "rpm": 300
     },
     "cloudflare/@cf/openai/gpt-oss-120b": {
         "input_cost_per_token": 3.5e-07,
@@ -14010,6 +14043,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14020,7 +14054,8 @@
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-3.2-3b-instruct": {
         "input_cost_per_token": 5.09e-08,
@@ -14029,7 +14064,8 @@
         "max_output_tokens": 80000,
         "max_tokens": 80000,
         "mode": "chat",
-        "output_cost_per_token": 3.35e-07
+        "output_cost_per_token": 3.35e-07,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-guard-3-8b": {
         "input_cost_per_token": 4.84e-07,
@@ -14038,7 +14074,8 @@
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 3e-08
+        "output_cost_per_token": 3e-08,
+        "rpm": 300
     },
     "cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora": {
         "input_cost_per_token": 0.0,
@@ -14047,7 +14084,8 @@
         "max_output_tokens": 15000,
         "max_tokens": 15000,
         "mode": "chat",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "rpm": 300
     },
     "cloudflare/@cf/moonshotai/kimi-k2.7-code": {
         "cache_read_input_token_cost": 1.9e-07,
@@ -14058,6 +14096,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
+        "rpm": 20,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14069,6 +14108,7 @@
         "max_tokens": 80000,
         "mode": "chat",
         "output_cost_per_token": 4.881e-06,
+        "rpm": 300,
         "supports_reasoning": true
     },
     "cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8": {
@@ -14078,7 +14118,8 @@
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
-        "output_cost_per_token": 2.87e-07
+        "output_cost_per_token": 2.87e-07,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-3.2-1b-instruct": {
         "input_cost_per_token": 2.7e-08,
@@ -14087,7 +14128,8 @@
         "max_output_tokens": 60000,
         "max_tokens": 60000,
         "mode": "chat",
-        "output_cost_per_token": 2.01e-07
+        "output_cost_per_token": 2.01e-07,
+        "rpm": 300
     },
     "cloudflare/@cf/moonshotai/kimi-k2.6": {
         "cache_read_input_token_cost": 1.6e-07,
@@ -14098,6 +14140,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
+        "rpm": 20,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14109,6 +14152,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14119,7 +14163,8 @@
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
         "input_cost_per_token": 2.93e-07,
@@ -14129,6 +14174,7 @@
         "max_tokens": 24000,
         "mode": "chat",
         "output_cost_per_token": 2.253e-06,
+        "rpm": 300,
         "supports_function_calling": true
     },
     "cloudflare/@cf/ibm-granite/granite-4.0-h-micro": {
@@ -14139,6 +14185,7 @@
         "max_tokens": 131000,
         "mode": "chat",
         "output_cost_per_token": 1.12e-07,
+        "rpm": 300,
         "supports_function_calling": true
     },
     "cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct": {
@@ -14148,7 +14195,8 @@
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
-        "output_cost_per_token": 1e-06
+        "output_cost_per_token": 1e-06,
+        "rpm": 300
     },
     "cloudflare/@cf/zai-org/glm-5.2": {
         "cache_read_input_token_cost": 2.6e-07,
@@ -14159,6 +14207,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "rpm": 20,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14170,6 +14219,7 @@
         "max_tokens": 256000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14180,7 +14230,8 @@
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 5.55e-07
+        "output_cost_per_token": 5.55e-07,
+        "rpm": 300
     },
     "cloudflare/@cf/qwen/qwen3-30b-a3b-fp8": {
         "input_cost_per_token": 5.09e-08,
@@ -14190,6 +14241,7 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 3.35e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14200,7 +14252,8 @@
         "max_output_tokens": 3500,
         "max_tokens": 3500,
         "mode": "chat",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "rpm": 300
     },
     "cloudflare/@cf/google/gemma-4-26b-a4b-it": {
         "input_cost_per_token": 1e-07,
@@ -14210,6 +14263,7 @@
         "max_tokens": 256000,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14221,6 +14275,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5.55e-07,
+        "rpm": 300,
         "supports_function_calling": true
     },
     "cloudflare/@cf/meta/llama-3.2-11b-vision-instruct": {
@@ -14231,6 +14286,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 6.76e-07,
+        "rpm": 300,
         "supports_vision": true
     },
     "cloudflare/@cf/openai/gpt-oss-20b": {
@@ -14241,6 +14297,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14252,6 +14309,7 @@
         "max_tokens": 131000,
         "mode": "chat",
         "output_cost_per_token": 8.5e-07,
+        "rpm": 300,
         "supports_function_calling": true
     },
     "cloudflare/@cf/qwen/qwq-32b": {
@@ -14262,6 +14320,7 @@
         "max_tokens": 24000,
         "mode": "chat",
         "output_cost_per_token": 1e-06,
+        "rpm": 300,
         "supports_reasoning": true
     },
     "codestral/codestral-2405": {
@@ -14388,6 +14447,28 @@
         "output_vector_size": 1536,
         "supports_embedding_image_input": true
     },
+    "us.cohere.embed-v4:0": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1536,
+        "supports_embedding_image_input": true,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
+    "global.cohere.embed-v4:0": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1536,
+        "supports_embedding_image_input": true,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "cohere/embed-v4.0": {
         "input_cost_per_token": 1.2e-07,
         "litellm_provider": "cohere",
@@ -20959,7 +21040,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "eu.amazon.nova-micro-v1:0": {
         "input_cost_per_token": 4.6e-08,
@@ -20971,7 +21053,8 @@
         "output_cost_per_token": 1.84e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "eu.amazon.nova-pro-v1:0": {
         "input_cost_per_token": 1.05e-06,
@@ -20986,24 +21069,25 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "eu.anthropic.claude-3-5-haiku-20241022-v1:0": {
-        "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token": 8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 200000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token": 4e-06,
         "supports_assistant_prefill": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
-        "cache_read_input_token_cost": 2.5e-08,
-        "cache_creation_input_token_cost": 3.125e-07,
+        "cache_read_input_token_cost": 8e-08,
+        "cache_creation_input_token_cost": 1e-06,
         "prompt_cache_min_tokens": 2048
     },
     "eu.anthropic.claude-haiku-4-5-20251001-v1:0": {
@@ -24010,9 +24094,9 @@
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "vertex_ai-language-models",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
         "mode": "realtime",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_token": 2e-06,
@@ -24035,12 +24119,12 @@
         "supports_audio_output": true,
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_response_schema": true,
+        "supports_pdf_input": false,
+        "supports_prompt_caching": false,
+        "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_url_context": true,
+        "supports_url_context": false,
         "supports_vision": true,
         "supports_web_search": true,
         "search_context_cost_per_query": {
@@ -27832,6 +27916,70 @@
         "max_tokens": 8191,
         "mode": "embedding"
     },
+    "chatgpt/gpt-5.5": {
+        "litellm_provider": "chatgpt",
+        "source": "https://platform.openai.com/docs/models/gpt-5.5",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.6-luna": {
+        "litellm_provider": "chatgpt",
+        "source": "https://platform.openai.com/docs/models/gpt-5.6-luna",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.6-sol": {
+        "litellm_provider": "chatgpt",
+        "source": "https://platform.openai.com/docs/models/gpt-5.6-sol",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.6-terra": {
+        "litellm_provider": "chatgpt",
+        "source": "https://platform.openai.com/docs/models/gpt-5.6-terra",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
     "chatgpt/gpt-5.4": {
         "litellm_provider": "chatgpt",
         "max_input_tokens": 1050000,
@@ -28438,6 +28586,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -29262,7 +29411,12 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
+        }
     },
     "gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -29279,9 +29433,9 @@
         "output_cost_per_token_priority": 1e-06,
         "output_cost_per_token_batches": 3e-07,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.03,
+            "search_context_size_high": 0.025,
             "search_context_size_low": 0.025,
-            "search_context_size_medium": 0.0275
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29380,9 +29534,9 @@
         "output_cost_per_token": 6e-07,
         "output_cost_per_token_batches": 3e-07,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.03,
+            "search_context_size_high": 0.025,
             "search_context_size_low": 0.025,
-            "search_context_size_medium": 0.0275
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29407,9 +29561,9 @@
         "output_cost_per_token": 6e-07,
         "output_cost_per_token_batches": 3e-07,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.03,
+            "search_context_size_high": 0.025,
             "search_context_size_low": 0.025,
-            "search_context_size_medium": 0.0275
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29520,9 +29674,9 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_batches": 5e-06,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.05,
-            "search_context_size_low": 0.03,
-            "search_context_size_medium": 0.035
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29547,9 +29701,9 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_batches": 5e-06,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.05,
-            "search_context_size_low": 0.03,
-            "search_context_size_medium": 0.035
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29631,6 +29785,66 @@
         "supports_vision": true,
         "supports_pdf_input": true
     },
+    "gpt-image-2.5-flare": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "input_cost_per_image_token": 8e-06,
+        "output_cost_per_image_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "gpt-image-2.5-flare-2026-09-08": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "input_cost_per_image_token": 8e-06,
+        "output_cost_per_image_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "gpt-image-2.5-sunburst": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "input_cost_per_image_token": 8e-06,
+        "output_cost_per_image_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "gpt-image-2.5-sunburst-2026-09-08": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "input_cost_per_image_token": 8e-06,
+        "output_cost_per_image_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
     "low/1024-x-1024/gpt-image-1.5": {
         "deprecation_date": "2026-12-01",
         "input_cost_per_image": 0.009,
@@ -41711,6 +41925,28 @@
         "mode": "rerank",
         "output_cost_per_token": 0.0
     },
+    "rerank-v4.0-fast": {
+        "input_cost_per_query": 0.002,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "cohere",
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cohere.com/pricing"
+    },
+    "rerank-v4.0-pro": {
+        "input_cost_per_query": 0.0025,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "cohere",
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cohere.com/pricing"
+    },
     "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": {
         "input_cost_per_query": 0.0,
         "input_cost_per_token": 0.0,
@@ -43671,7 +43907,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "us.amazon.nova-micro-v1:0": {
         "input_cost_per_token": 3.5e-08,
@@ -43683,7 +43920,8 @@
         "output_cost_per_token": 1.4e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "us.amazon.nova-premier-v1:0": {
         "deprecation_date": "2026-09-14",
@@ -43712,7 +43950,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "us.anthropic.claude-3-5-haiku-20241022-v1:0": {
         "cache_creation_input_token_cost": 1e-06,
@@ -45891,8 +46130,8 @@
         "input_cost_per_token": 1e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
         "max_input_tokens": 200000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 5e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
@@ -45916,8 +46155,8 @@
         "input_cost_per_token": 1e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
         "max_input_tokens": 200000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 5e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
@@ -47897,9 +48136,9 @@
         "cache_read_input_token_cost": 5e-08,
         "input_cost_per_token": 2e-07,
         "litellm_provider": "vertex_ai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
         "source": "https://docs.x.ai/developers/models",
@@ -47913,9 +48152,9 @@
         "cache_read_input_token_cost": 5e-08,
         "input_cost_per_token": 2e-07,
         "litellm_provider": "vertex_ai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
         "source": "https://docs.x.ai/developers/models",
@@ -47928,14 +48167,17 @@
     },
     "vertex_ai/xai/grok-4.20-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 2000000,
         "max_output_tokens": 2000000,
         "max_tokens": 2000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://docs.x.ai/developers/models",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -47944,14 +48186,17 @@
     },
     "vertex_ai/xai/grok-4.20-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 2000000,
         "max_output_tokens": 2000000,
         "max_tokens": 2000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://docs.x.ai/developers/models",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -47959,6 +48204,44 @@
         "supports_vision": true,
         "supports_web_search": true
     },
+    "vertex_ai/xai/grok-4.3": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 200000,
+        "max_tokens": 200000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "vertex_ai/xai/grok-4.6": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 524288,
+        "max_output_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": {
         "input_cost_per_token": 2.2e-07,
         "litellm_provider": "vertex_ai-qwen_models",
@@ -48217,6 +48500,16 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0
     },
+    "voyage/voyage-multilingual-2": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "voyage",
+        "max_input_tokens": 32000,
+        "max_tokens": 32000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1024,
+        "source": "https://docs.voyageai.com/docs/pricing"
+    },
     "voyage/voyage-3-large": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "voyage",
@@ -52290,7 +52583,8 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 8e-07,
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "deprecation_date": "2026-10-01"
     },
     "scaleway/openai/gpt-oss-120b": {
         "input_cost_per_token": 1.5e-07,
@@ -52329,7 +52623,8 @@
         "mode": "chat",
         "output_cost_per_token": 5e-07,
         "supports_function_calling": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "deprecation_date": "2026-08-01"
     },
     "scaleway/hcompany/holo2-30b-a3b": {
         "input_cost_per_token": 3e-07,
@@ -52340,7 +52635,8 @@
         "mode": "chat",
         "output_cost_per_token": 7e-07,
         "supports_reasoning": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "deprecation_date": "2026-08-09"
     },
     "scaleway/mistralai/mistral-medium-3.5-128b": {
         "input_cost_per_token": 1.5e-06,
@@ -52363,7 +52659,8 @@
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "deprecation_date": "2026-08-01"
     },
     "scaleway/mistralai/voxtral-small-24b-2507": {
         "input_cost_per_audio_token": 1.5e-07,
@@ -52374,7 +52671,8 @@
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3.5e-07,
-        "supports_audio_input": true
+        "supports_audio_input": true,
+        "deprecation_date": "2026-08-01"
     },
     "scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": {
         "input_cost_per_token": 1.5e-07,
@@ -52396,7 +52694,8 @@
         "mode": "chat",
         "output_cost_per_token": 2e-07,
         "supports_vision": true,
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "deprecation_date": "2026-10-01"
     },
     "scaleway/BAAI/bge-multilingual-gemma2": {
         "input_cost_per_token": 1e-07,
@@ -54846,7 +55145,7 @@
         "supports_tool_choice": true
     },
     "bedrock_mantle/openai.gpt-oss-20b": {
-        "input_cost_per_token": 7.5e-08,
+        "input_cost_per_token": 7e-08,
         "output_cost_per_token": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
@@ -54880,8 +55179,8 @@
         "supports_tool_choice": true
     },
     "bedrock_mantle/openai.gpt-oss-safeguard-20b": {
-        "input_cost_per_token": 7.5e-08,
-        "output_cost_per_token": 3e-07,
+        "input_cost_per_token": 7e-08,
+        "output_cost_per_token": 2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
         "max_output_tokens": 65536,
@@ -55001,6 +55300,39 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol": {
+        "input_cost_per_token": 5.5e-06,
+        "input_cost_per_token_above_272k_tokens": 1.1e-05,
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_read_input_token_cost": 5.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
+        "output_cost_per_token": 3.3e-05,
+        "output_cost_per_token_above_272k_tokens": 4.95e-05,
+        "litellm_provider": "bedrock_mantle",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "use_openai_responses_path": true,
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html"
+    },
     "bedrock_mantle/openai.gpt-5.6-luna": {
         "input_cost_per_token": 2.2e-07,
         "input_cost_per_token_above_272k_tokens": 4.4e-07,
@@ -55196,6 +55528,96 @@
         "supports_reasoning": true,
         "supports_vision": true
     },
+    "bedrock_mantle/openai.gpt-6-astra": {
+        "input_cost_per_token": 1.1e-05,
+        "input_cost_per_token_above_272k_tokens": 2.2e-05,
+        "cache_creation_input_token_cost": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
+        "cache_read_input_token_cost": 1.1e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
+        "output_cost_per_token": 5.5e-05,
+        "output_cost_per_token_above_272k_tokens": 8.25e-05,
+        "litellm_provider": "bedrock_mantle",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "use_openai_responses_path": true,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
+    },
+    "us.openai.gpt-6-astra": {
+        "input_cost_per_token": 1.1e-05,
+        "input_cost_per_token_above_272k_tokens": 2.2e-05,
+        "cache_creation_input_token_cost": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
+        "cache_read_input_token_cost": 1.1e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
+        "output_cost_per_token": 5.5e-05,
+        "output_cost_per_token_above_272k_tokens": 8.25e-05,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
+    },
+    "global.openai.gpt-6-astra": {
+        "input_cost_per_token": 1e-05,
+        "input_cost_per_token_above_272k_tokens": 2e-05,
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
+        "output_cost_per_token": 5e-05,
+        "output_cost_per_token_above_272k_tokens": 7.5e-05,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
+    },
     "bedrock_mantle/openai.gpt-5.5": {
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
@@ -56861,8 +57283,8 @@
         "rpm": 10
     },
     "vertex_ai/gemini-3.5-transcribe-preview": {
-        "input_cost_per_audio_token": 2.5e-06,
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_audio_token": 2e-06,
+        "input_cost_per_token": 2e-06,
         "litellm_provider": "vertex_ai",
         "mode": "audio_transcription",
         "output_cost_per_token": 1.2e-05,
@@ -56897,6 +57319,27 @@
         ],
         "supports_audio_input": true
     },
+    "vertex_ai/gemini-3.5-live-translate-preview": {
+        "input_cost_per_audio_token": 3.5e-06,
+        "input_cost_per_token": 3.5e-06,
+        "litellm_provider": "vertex_ai",
+        "mode": "realtime",
+        "output_cost_per_audio_token": 2.1e-05,
+        "output_cost_per_token": 2.1e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "audio",
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true
+    },
     "perplexity/pplx-embed-context-v1-0.6b": {
         "input_cost_per_token": 8e-09,
         "litellm_provider": "perplexity",
@@ -59588,6 +60031,77 @@
             "image"
         ]
     },
+    "xai/grok-imagine-video": {
+        "input_cost_per_image": 0.002,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.05,
+        "output_cost_per_second_480p": 0.05,
+        "output_cost_per_second_720p": 0.07,
+        "source": "https://docs.x.ai/docs/models/grok-imagine-video",
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
+    "xai/grok-imagine-video-1.5": {
+        "input_cost_per_image": 0.01,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_1080p": 0.25,
+        "output_cost_per_second_480p": 0.08,
+        "output_cost_per_second_720p": 0.14,
+        "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
+    "xai/grok-imagine-video-1.5-2026-05-30": {
+        "input_cost_per_image": 0.01,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_1080p": 0.25,
+        "output_cost_per_second_480p": 0.08,
+        "output_cost_per_second_720p": 0.14,
+        "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
+    "xai/grok-imagine-video-1.5-preview": {
+        "input_cost_per_image": 0.01,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_1080p": 0.25,
+        "output_cost_per_second_480p": 0.08,
+        "output_cost_per_second_720p": 0.14,
+        "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
     "low/1024-x-1024/grok-imagine-image-2.0": {
         "input_cost_per_image": 0.04,
         "litellm_provider": "xai",
@@ -60855,6 +61369,7 @@
         "litellm_provider": "cloudflare",
         "mode": "audio_transcription",
         "output_cost_per_second": 0.0,
+        "rpm": 720,
         "source": "https://developers.cloudflare.com/workers-ai/models/whisper/",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
@@ -60865,6 +61380,7 @@
         "litellm_provider": "cloudflare",
         "mode": "audio_transcription",
         "output_cost_per_second": 0.0,
+        "rpm": 720,
         "source": "https://developers.cloudflare.com/workers-ai/models/whisper-large-v3-turbo/",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
@@ -60920,6 +61436,31 @@
         "supports_web_search": false,
         "output_cost_per_image": 0.08
     },
+    "gemini/lyria-3.5": {
+        "input_cost_per_token": 0,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "audio"
+        ],
+        "supports_audio_input": false,
+        "supports_audio_output": true,
+        "supports_function_calling": false,
+        "supports_prompt_caching": false,
+        "supports_response_schema": false,
+        "supports_system_messages": false,
+        "supports_vision": false,
+        "supports_web_search": false,
+        "output_cost_per_image": 0.08
+    },
     "perplexity/anthropic/claude-fable-5": {
         "litellm_provider": "perplexity",
         "mode": "responses",
diff --git a/litellm/types/router.py b/litellm/types/router.py
index 5c9eab30f3d..6b707a544a2 100644
--- a/litellm/types/router.py
+++ b/litellm/types/router.py
@@ -525,6 +525,7 @@ class LiteLLMParamsTypedDict(TypedDict, total=False):
     input_cost_per_second: float | None
     output_cost_per_second: float | None
     output_cost_per_second_480p: ReadOnly[float | None]
+    output_cost_per_second_720p: ReadOnly[float | None]
     output_cost_per_second_1080p: float | None
     output_cost_per_second_4k: ReadOnly[float | None]
     num_retries: int | None
diff --git a/litellm/types/utils.py b/litellm/types/utils.py
index d62f00f3676..ab0cc5f959c 100644
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@@ -318,6 +318,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
         float | None
     )  # video_generation tier: key output_cost_per_second_<resolution> (e.g. 1080p, 720p)
     output_cost_per_second_480p: ReadOnly[float | None]
+    output_cost_per_second_720p: ReadOnly[float | None]
     output_cost_per_second_4k: ReadOnly[float | None]
     ocr_cost_per_page: float | None  # for OCR models
     ocr_cost_per_credit: float | None  # for OCR models priced by credit
@@ -3522,6 +3523,7 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
     output_cost_per_second: float | None = None
     output_cost_per_second_1080p: float | None = None
     output_cost_per_second_480p: float | None = None
+    output_cost_per_second_720p: float | None = None
     output_cost_per_second_4k: float | None = None
     input_cost_per_pixel: float | None = None
     output_cost_per_pixel: float | None = None
diff --git a/litellm/utils.py b/litellm/utils.py
index 06ee3dd88af..eec843d087d 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -5913,6 +5913,7 @@ def _get_model_info_helper(
                 output_cost_per_second=_model_info.get("output_cost_per_second", None),
                 output_cost_per_second_1080p=_model_info.get("output_cost_per_second_1080p", None),
                 output_cost_per_second_480p=_model_info.get("output_cost_per_second_480p", None),
+                output_cost_per_second_720p=_model_info.get("output_cost_per_second_720p", None),
                 output_cost_per_second_4k=_model_info.get("output_cost_per_second_4k", None),
                 output_cost_per_video_per_second=_model_info.get("output_cost_per_video_per_second", None),
                 output_cost_per_image=_model_info.get("output_cost_per_image", None),
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 54ebdc85be9..0d2eda93323 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -364,7 +364,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "amazon.nova-2-lite-v1:0": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -380,6 +381,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -399,6 +401,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -416,6 +419,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -435,6 +439,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -452,6 +457,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -471,6 +477,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -488,6 +495,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -507,6 +515,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -537,7 +546,8 @@
         "output_cost_per_token": 1.4e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "amazon.nova-pro-v1:0": {
         "input_cost_per_token": 8e-07,
@@ -551,7 +561,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "amazon.nova-sonic-v1:0": {
         "deprecation_date": "2026-09-14",
@@ -756,6 +767,14 @@
         "mode": "chat",
         "supports_video_input": true
     },
+    "global.twelvelabs.pegasus-1-2-v1:0": {
+        "input_cost_per_video_per_second": 0.00049,
+        "output_cost_per_token": 7.5e-06,
+        "litellm_provider": "bedrock",
+        "mode": "chat",
+        "supports_video_input": true,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "amazon.titan-text-express-v1": {
         "input_cost_per_token": 1.3e-06,
         "litellm_provider": "bedrock",
@@ -2876,7 +2895,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "apac.amazon.nova-micro-v1:0": {
         "input_cost_per_token": 3.7e-08,
@@ -2888,7 +2908,8 @@
         "output_cost_per_token": 1.48e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "apac.amazon.nova-pro-v1:0": {
         "input_cost_per_token": 8.4e-07,
@@ -2902,7 +2923,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "apac.anthropic.claude-3-5-sonnet-20240620-v1:0": {
         "deprecation_date": "2026-07-30",
@@ -8064,7 +8086,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "deprecation_date": "2027-10-26"
     },
     "azure/us/gpt-5.5-2026-04-23": {
         "cache_read_input_token_cost": 5.5e-07,
@@ -8108,7 +8131,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "deprecation_date": "2027-10-26"
     },
     "azure/eu/gpt-5.5-2026-04-23": {
         "cache_read_input_token_cost": 5.5e-07,
@@ -8152,7 +8176,8 @@
         "supports_system_messages": true,
         "supports_tool_choice": true,
         "supports_vision": true,
-        "supports_web_search": true
+        "supports_web_search": true,
+        "deprecation_date": "2027-10-26"
     },
     "azure/gpt-5.5-pro": {
         "cache_read_input_token_cost": 3e-06,
@@ -12317,7 +12342,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "bedrock/us-gov-east-1/amazon.titan-embed-text-v1": {
         "input_cost_per_token": 1e-07,
@@ -12496,7 +12522,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "bedrock/us-gov-west-1/amazon.nova-micro-v1:0": {
         "input_cost_per_token": 4.2e-08,
@@ -12508,7 +12535,8 @@
         "output_cost_per_token": 1.68e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "bedrock/us-gov-west-1/amazon.nova-pro-v1:0": {
         "input_cost_per_token": 9.6e-07,
@@ -12522,7 +12550,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "bedrock/us-gov-west-1/amazon.titan-embed-text-v1": {
         "input_cost_per_token": 1e-07,
@@ -13973,7 +14002,8 @@
         "max_output_tokens": 3072,
         "max_tokens": 3072,
         "mode": "chat",
-        "output_cost_per_token": 1.923e-06
+        "output_cost_per_token": 1.923e-06,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-2-7b-chat-int8": {
         "input_cost_per_token": 1.923e-06,
@@ -13982,7 +14012,8 @@
         "max_output_tokens": 2048,
         "max_tokens": 2048,
         "mode": "chat",
-        "output_cost_per_token": 1.923e-06
+        "output_cost_per_token": 1.923e-06,
+        "rpm": 300
     },
     "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1": {
         "input_cost_per_token": 1.923e-06,
@@ -13991,7 +14022,8 @@
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 1.923e-06
+        "output_cost_per_token": 1.923e-06,
+        "rpm": 300
     },
     "cloudflare/@hf/thebloke/codellama-7b-instruct-awq": {
         "input_cost_per_token": 1.923e-06,
@@ -14000,7 +14032,8 @@
         "max_output_tokens": 4096,
         "max_tokens": 4096,
         "mode": "chat",
-        "output_cost_per_token": 1.923e-06
+        "output_cost_per_token": 1.923e-06,
+        "rpm": 300
     },
     "cloudflare/@cf/openai/gpt-oss-120b": {
         "input_cost_per_token": 3.5e-07,
@@ -14010,6 +14043,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 7.5e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14020,7 +14054,8 @@
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-3.2-3b-instruct": {
         "input_cost_per_token": 5.09e-08,
@@ -14029,7 +14064,8 @@
         "max_output_tokens": 80000,
         "max_tokens": 80000,
         "mode": "chat",
-        "output_cost_per_token": 3.35e-07
+        "output_cost_per_token": 3.35e-07,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-guard-3-8b": {
         "input_cost_per_token": 4.84e-07,
@@ -14038,7 +14074,8 @@
         "max_output_tokens": 131072,
         "max_tokens": 131072,
         "mode": "chat",
-        "output_cost_per_token": 3e-08
+        "output_cost_per_token": 3e-08,
+        "rpm": 300
     },
     "cloudflare/@cf/mistral/mistral-7b-instruct-v0.2-lora": {
         "input_cost_per_token": 0.0,
@@ -14047,7 +14084,8 @@
         "max_output_tokens": 15000,
         "max_tokens": 15000,
         "mode": "chat",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "rpm": 300
     },
     "cloudflare/@cf/moonshotai/kimi-k2.7-code": {
         "cache_read_input_token_cost": 1.9e-07,
@@ -14058,6 +14096,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
+        "rpm": 20,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14069,6 +14108,7 @@
         "max_tokens": 80000,
         "mode": "chat",
         "output_cost_per_token": 4.881e-06,
+        "rpm": 300,
         "supports_reasoning": true
     },
     "cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8": {
@@ -14078,7 +14118,8 @@
         "max_output_tokens": 32000,
         "max_tokens": 32000,
         "mode": "chat",
-        "output_cost_per_token": 2.87e-07
+        "output_cost_per_token": 2.87e-07,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-3.2-1b-instruct": {
         "input_cost_per_token": 2.7e-08,
@@ -14087,7 +14128,8 @@
         "max_output_tokens": 60000,
         "max_tokens": 60000,
         "mode": "chat",
-        "output_cost_per_token": 2.01e-07
+        "output_cost_per_token": 2.01e-07,
+        "rpm": 300
     },
     "cloudflare/@cf/moonshotai/kimi-k2.6": {
         "cache_read_input_token_cost": 1.6e-07,
@@ -14098,6 +14140,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 4e-06,
+        "rpm": 20,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14109,6 +14152,7 @@
         "max_tokens": 131072,
         "mode": "chat",
         "output_cost_per_token": 4e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14119,7 +14163,8 @@
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "rpm": 300
     },
     "cloudflare/@cf/meta/llama-3.3-70b-instruct-fp8-fast": {
         "input_cost_per_token": 2.93e-07,
@@ -14129,6 +14174,7 @@
         "max_tokens": 24000,
         "mode": "chat",
         "output_cost_per_token": 2.253e-06,
+        "rpm": 300,
         "supports_function_calling": true
     },
     "cloudflare/@cf/ibm-granite/granite-4.0-h-micro": {
@@ -14139,6 +14185,7 @@
         "max_tokens": 131000,
         "mode": "chat",
         "output_cost_per_token": 1.12e-07,
+        "rpm": 300,
         "supports_function_calling": true
     },
     "cloudflare/@cf/qwen/qwen2.5-coder-32b-instruct": {
@@ -14148,7 +14195,8 @@
         "max_output_tokens": 32768,
         "max_tokens": 32768,
         "mode": "chat",
-        "output_cost_per_token": 1e-06
+        "output_cost_per_token": 1e-06,
+        "rpm": 300
     },
     "cloudflare/@cf/zai-org/glm-5.2": {
         "cache_read_input_token_cost": 2.6e-07,
@@ -14159,6 +14207,7 @@
         "max_tokens": 262144,
         "mode": "chat",
         "output_cost_per_token": 4.4e-06,
+        "rpm": 20,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14170,6 +14219,7 @@
         "max_tokens": 256000,
         "mode": "chat",
         "output_cost_per_token": 1.5e-06,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14180,7 +14230,8 @@
         "max_output_tokens": 128000,
         "max_tokens": 128000,
         "mode": "chat",
-        "output_cost_per_token": 5.55e-07
+        "output_cost_per_token": 5.55e-07,
+        "rpm": 300
     },
     "cloudflare/@cf/qwen/qwen3-30b-a3b-fp8": {
         "input_cost_per_token": 5.09e-08,
@@ -14190,6 +14241,7 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 3.35e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14200,7 +14252,8 @@
         "max_output_tokens": 3500,
         "max_tokens": 3500,
         "mode": "chat",
-        "output_cost_per_token": 0.0
+        "output_cost_per_token": 0.0,
+        "rpm": 300
     },
     "cloudflare/@cf/google/gemma-4-26b-a4b-it": {
         "input_cost_per_token": 1e-07,
@@ -14210,6 +14263,7 @@
         "max_tokens": 256000,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14221,6 +14275,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5.55e-07,
+        "rpm": 300,
         "supports_function_calling": true
     },
     "cloudflare/@cf/meta/llama-3.2-11b-vision-instruct": {
@@ -14231,6 +14286,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 6.76e-07,
+        "rpm": 300,
         "supports_vision": true
     },
     "cloudflare/@cf/openai/gpt-oss-20b": {
@@ -14241,6 +14297,7 @@
         "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 3e-07,
+        "rpm": 300,
         "supports_function_calling": true,
         "supports_reasoning": true
     },
@@ -14252,6 +14309,7 @@
         "max_tokens": 131000,
         "mode": "chat",
         "output_cost_per_token": 8.5e-07,
+        "rpm": 300,
         "supports_function_calling": true
     },
     "cloudflare/@cf/qwen/qwq-32b": {
@@ -14262,6 +14320,7 @@
         "max_tokens": 24000,
         "mode": "chat",
         "output_cost_per_token": 1e-06,
+        "rpm": 300,
         "supports_reasoning": true
     },
     "codestral/codestral-2405": {
@@ -14388,6 +14447,28 @@
         "output_vector_size": 1536,
         "supports_embedding_image_input": true
     },
+    "us.cohere.embed-v4:0": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1536,
+        "supports_embedding_image_input": true,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
+    "global.cohere.embed-v4:0": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "bedrock",
+        "max_input_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1536,
+        "supports_embedding_image_input": true,
+        "source": "https://aws.amazon.com/bedrock/pricing/"
+    },
     "cohere/embed-v4.0": {
         "input_cost_per_token": 1.2e-07,
         "litellm_provider": "cohere",
@@ -20959,7 +21040,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "eu.amazon.nova-micro-v1:0": {
         "input_cost_per_token": 4.6e-08,
@@ -20971,7 +21053,8 @@
         "output_cost_per_token": 1.84e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "eu.amazon.nova-pro-v1:0": {
         "input_cost_per_token": 1.05e-06,
@@ -20986,24 +21069,25 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "eu.anthropic.claude-3-5-haiku-20241022-v1:0": {
-        "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token": 8e-07,
         "litellm_provider": "bedrock",
         "max_input_tokens": 200000,
         "max_output_tokens": 8192,
         "max_tokens": 8192,
         "mode": "chat",
-        "output_cost_per_token": 1.25e-06,
+        "output_cost_per_token": 4e-06,
         "supports_assistant_prefill": true,
         "supports_function_calling": true,
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
-        "cache_read_input_token_cost": 2.5e-08,
-        "cache_creation_input_token_cost": 3.125e-07,
+        "cache_read_input_token_cost": 8e-08,
+        "cache_creation_input_token_cost": 1e-06,
         "prompt_cache_min_tokens": 2048
     },
     "eu.anthropic.claude-haiku-4-5-20251001-v1:0": {
@@ -24010,9 +24094,9 @@
         "input_cost_per_audio_token": 3e-06,
         "input_cost_per_token": 5e-07,
         "litellm_provider": "vertex_ai-language-models",
-        "max_input_tokens": 1048576,
-        "max_output_tokens": 65535,
-        "max_tokens": 65535,
+        "max_input_tokens": 131072,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
         "mode": "realtime",
         "output_cost_per_audio_token": 1.2e-05,
         "output_cost_per_token": 2e-06,
@@ -24035,12 +24119,12 @@
         "supports_audio_output": true,
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_pdf_input": true,
-        "supports_prompt_caching": true,
-        "supports_response_schema": true,
+        "supports_pdf_input": false,
+        "supports_prompt_caching": false,
+        "supports_response_schema": false,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_url_context": true,
+        "supports_url_context": false,
         "supports_vision": true,
         "supports_web_search": true,
         "search_context_cost_per_query": {
@@ -27832,6 +27916,70 @@
         "max_tokens": 8191,
         "mode": "embedding"
     },
+    "chatgpt/gpt-5.5": {
+        "litellm_provider": "chatgpt",
+        "source": "https://platform.openai.com/docs/models/gpt-5.5",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.6-luna": {
+        "litellm_provider": "chatgpt",
+        "source": "https://platform.openai.com/docs/models/gpt-5.6-luna",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.6-sol": {
+        "litellm_provider": "chatgpt",
+        "source": "https://platform.openai.com/docs/models/gpt-5.6-sol",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
+    "chatgpt/gpt-5.6-terra": {
+        "litellm_provider": "chatgpt",
+        "source": "https://platform.openai.com/docs/models/gpt-5.6-terra",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
+        "supports_vision": true
+    },
     "chatgpt/gpt-5.4": {
         "litellm_provider": "chatgpt",
         "max_input_tokens": 1050000,
@@ -28438,6 +28586,7 @@
         "supports_prompt_caching": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
+        "supports_tool_choice": true,
         "supports_video_input": true,
         "supports_vision": true
     },
@@ -29262,7 +29411,12 @@
         "supports_response_schema": true,
         "supports_system_messages": true,
         "supports_tool_choice": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
+        }
     },
     "gpt-4o-mini-2024-07-18": {
         "cache_read_input_token_cost": 7.5e-08,
@@ -29279,9 +29433,9 @@
         "output_cost_per_token_priority": 1e-06,
         "output_cost_per_token_batches": 3e-07,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.03,
+            "search_context_size_high": 0.025,
             "search_context_size_low": 0.025,
-            "search_context_size_medium": 0.0275
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29380,9 +29534,9 @@
         "output_cost_per_token": 6e-07,
         "output_cost_per_token_batches": 3e-07,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.03,
+            "search_context_size_high": 0.025,
             "search_context_size_low": 0.025,
-            "search_context_size_medium": 0.0275
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29407,9 +29561,9 @@
         "output_cost_per_token": 6e-07,
         "output_cost_per_token_batches": 3e-07,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.03,
+            "search_context_size_high": 0.025,
             "search_context_size_low": 0.025,
-            "search_context_size_medium": 0.0275
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29520,9 +29674,9 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_batches": 5e-06,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.05,
-            "search_context_size_low": 0.03,
-            "search_context_size_medium": 0.035
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29547,9 +29701,9 @@
         "output_cost_per_token": 1e-05,
         "output_cost_per_token_batches": 5e-06,
         "search_context_cost_per_query": {
-            "search_context_size_high": 0.05,
-            "search_context_size_low": 0.03,
-            "search_context_size_medium": 0.035
+            "search_context_size_high": 0.025,
+            "search_context_size_low": 0.025,
+            "search_context_size_medium": 0.025
         },
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
@@ -29631,6 +29785,66 @@
         "supports_vision": true,
         "supports_pdf_input": true
     },
+    "gpt-image-2.5-flare": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "input_cost_per_image_token": 8e-06,
+        "output_cost_per_image_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "gpt-image-2.5-flare-2026-09-08": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "input_cost_per_image_token": 8e-06,
+        "output_cost_per_image_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "gpt-image-2.5-sunburst": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "input_cost_per_image_token": 8e-06,
+        "output_cost_per_image_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
+    "gpt-image-2.5-sunburst-2026-09-08": {
+        "cache_read_input_token_cost": 1.25e-06,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "mode": "image_generation",
+        "input_cost_per_image_token": 8e-06,
+        "output_cost_per_image_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/images/generations",
+            "/v1/images/edits"
+        ],
+        "supports_vision": true,
+        "supports_pdf_input": true,
+        "source": "https://developers.openai.com/api/docs/pricing"
+    },
     "low/1024-x-1024/gpt-image-1.5": {
         "deprecation_date": "2026-12-01",
         "input_cost_per_image": 0.009,
@@ -41711,6 +41925,28 @@
         "mode": "rerank",
         "output_cost_per_token": 0.0
     },
+    "rerank-v4.0-fast": {
+        "input_cost_per_query": 0.002,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "cohere",
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cohere.com/pricing"
+    },
+    "rerank-v4.0-pro": {
+        "input_cost_per_query": 0.0025,
+        "input_cost_per_token": 0.0,
+        "litellm_provider": "cohere",
+        "max_input_tokens": 32768,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "rerank",
+        "output_cost_per_token": 0.0,
+        "source": "https://cohere.com/pricing"
+    },
     "nvidia_nim/nvidia/nv-rerankqa-mistral-4b-v3": {
         "input_cost_per_query": 0.0,
         "input_cost_per_token": 0.0,
@@ -43671,7 +43907,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "us.amazon.nova-micro-v1:0": {
         "input_cost_per_token": 3.5e-08,
@@ -43683,7 +43920,8 @@
         "output_cost_per_token": 1.4e-07,
         "supports_function_calling": true,
         "supports_prompt_caching": true,
-        "supports_response_schema": true
+        "supports_response_schema": true,
+        "supports_tool_choice": true
     },
     "us.amazon.nova-premier-v1:0": {
         "deprecation_date": "2026-09-14",
@@ -43712,7 +43950,8 @@
         "supports_pdf_input": true,
         "supports_prompt_caching": true,
         "supports_response_schema": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "supports_tool_choice": true
     },
     "us.anthropic.claude-3-5-haiku-20241022-v1:0": {
         "cache_creation_input_token_cost": 1e-06,
@@ -45891,8 +46130,8 @@
         "input_cost_per_token": 1e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
         "max_input_tokens": 200000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 5e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
@@ -45916,8 +46155,8 @@
         "input_cost_per_token": 1e-06,
         "litellm_provider": "vertex_ai-anthropic_models",
         "max_input_tokens": 200000,
-        "max_output_tokens": 8192,
-        "max_tokens": 8192,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
         "mode": "chat",
         "output_cost_per_token": 5e-06,
         "regional_endpoint_uplift_multiplier": 1.1,
@@ -47897,9 +48136,9 @@
         "cache_read_input_token_cost": 5e-08,
         "input_cost_per_token": 2e-07,
         "litellm_provider": "vertex_ai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
         "source": "https://docs.x.ai/developers/models",
@@ -47913,9 +48152,9 @@
         "cache_read_input_token_cost": 5e-08,
         "input_cost_per_token": 2e-07,
         "litellm_provider": "vertex_ai",
-        "max_input_tokens": 2000000,
-        "max_output_tokens": 2000000,
-        "max_tokens": 2000000,
+        "max_input_tokens": 128000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
         "mode": "chat",
         "output_cost_per_token": 5e-07,
         "source": "https://docs.x.ai/developers/models",
@@ -47928,14 +48167,17 @@
     },
     "vertex_ai/xai/grok-4.20-non-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 2000000,
         "max_output_tokens": 2000000,
         "max_tokens": 2000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://docs.x.ai/developers/models",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supports_function_calling": true,
         "supports_response_schema": true,
         "supports_tool_choice": true,
@@ -47944,14 +48186,17 @@
     },
     "vertex_ai/xai/grok-4.20-reasoning": {
         "cache_read_input_token_cost": 2e-07,
-        "input_cost_per_token": 2e-06,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
         "litellm_provider": "vertex_ai",
         "max_input_tokens": 2000000,
         "max_output_tokens": 2000000,
         "max_tokens": 2000000,
         "mode": "chat",
-        "output_cost_per_token": 6e-06,
-        "source": "https://docs.x.ai/developers/models",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
         "supports_function_calling": true,
         "supports_reasoning": true,
         "supports_response_schema": true,
@@ -47959,6 +48204,44 @@
         "supports_vision": true,
         "supports_web_search": true
     },
+    "vertex_ai/xai/grok-4.3": {
+        "cache_read_input_token_cost": 2e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 4e-07,
+        "input_cost_per_token": 1.25e-06,
+        "input_cost_per_token_above_200k_tokens": 2.5e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 200000,
+        "max_output_tokens": 200000,
+        "max_tokens": 200000,
+        "mode": "chat",
+        "output_cost_per_token": 2.5e-06,
+        "output_cost_per_token_above_200k_tokens": 5e-06,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
+    "vertex_ai/xai/grok-4.6": {
+        "cache_read_input_token_cost": 5e-07,
+        "cache_read_input_token_cost_above_200k_tokens": 1e-06,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_above_200k_tokens": 4e-06,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 524288,
+        "max_output_tokens": 524288,
+        "max_tokens": 524288,
+        "mode": "chat",
+        "output_cost_per_token": 6e-06,
+        "output_cost_per_token_above_200k_tokens": 1.2e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maas": {
         "input_cost_per_token": 2.2e-07,
         "litellm_provider": "vertex_ai-qwen_models",
@@ -48217,6 +48500,16 @@
         "mode": "embedding",
         "output_cost_per_token": 0.0
     },
+    "voyage/voyage-multilingual-2": {
+        "input_cost_per_token": 1.2e-07,
+        "litellm_provider": "voyage",
+        "max_input_tokens": 32000,
+        "max_tokens": 32000,
+        "mode": "embedding",
+        "output_cost_per_token": 0.0,
+        "output_vector_size": 1024,
+        "source": "https://docs.voyageai.com/docs/pricing"
+    },
     "voyage/voyage-3-large": {
         "input_cost_per_token": 1.8e-07,
         "litellm_provider": "voyage",
@@ -52290,7 +52583,8 @@
         "max_tokens": 32768,
         "mode": "chat",
         "output_cost_per_token": 8e-07,
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "deprecation_date": "2026-10-01"
     },
     "scaleway/openai/gpt-oss-120b": {
         "input_cost_per_token": 1.5e-07,
@@ -52329,7 +52623,8 @@
         "mode": "chat",
         "output_cost_per_token": 5e-07,
         "supports_function_calling": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "deprecation_date": "2026-08-01"
     },
     "scaleway/hcompany/holo2-30b-a3b": {
         "input_cost_per_token": 3e-07,
@@ -52340,7 +52635,8 @@
         "mode": "chat",
         "output_cost_per_token": 7e-07,
         "supports_reasoning": true,
-        "supports_vision": true
+        "supports_vision": true,
+        "deprecation_date": "2026-08-09"
     },
     "scaleway/mistralai/mistral-medium-3.5-128b": {
         "input_cost_per_token": 1.5e-06,
@@ -52363,7 +52659,8 @@
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 2e-06,
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "deprecation_date": "2026-08-01"
     },
     "scaleway/mistralai/voxtral-small-24b-2507": {
         "input_cost_per_audio_token": 1.5e-07,
@@ -52374,7 +52671,8 @@
         "max_tokens": 16384,
         "mode": "chat",
         "output_cost_per_token": 3.5e-07,
-        "supports_audio_input": true
+        "supports_audio_input": true,
+        "deprecation_date": "2026-08-01"
     },
     "scaleway/mistralai/mistral-small-3.2-24b-instruct-2506": {
         "input_cost_per_token": 1.5e-07,
@@ -52396,7 +52694,8 @@
         "mode": "chat",
         "output_cost_per_token": 2e-07,
         "supports_vision": true,
-        "supports_function_calling": true
+        "supports_function_calling": true,
+        "deprecation_date": "2026-10-01"
     },
     "scaleway/BAAI/bge-multilingual-gemma2": {
         "input_cost_per_token": 1e-07,
@@ -54846,7 +55145,7 @@
         "supports_tool_choice": true
     },
     "bedrock_mantle/openai.gpt-oss-20b": {
-        "input_cost_per_token": 7.5e-08,
+        "input_cost_per_token": 7e-08,
         "output_cost_per_token": 3e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
@@ -54880,8 +55179,8 @@
         "supports_tool_choice": true
     },
     "bedrock_mantle/openai.gpt-oss-safeguard-20b": {
-        "input_cost_per_token": 7.5e-08,
-        "output_cost_per_token": 3e-07,
+        "input_cost_per_token": 7e-08,
+        "output_cost_per_token": 2e-07,
         "litellm_provider": "bedrock_mantle",
         "max_input_tokens": 131072,
         "max_output_tokens": 65536,
@@ -55001,6 +55300,39 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "bedrock_mantle/openai.gpt-daybreak-blue-5.6-sol": {
+        "input_cost_per_token": 5.5e-06,
+        "input_cost_per_token_above_272k_tokens": 1.1e-05,
+        "cache_creation_input_token_cost": 6.875e-06,
+        "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05,
+        "cache_read_input_token_cost": 5.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens": 1.1e-06,
+        "output_cost_per_token": 3.3e-05,
+        "output_cost_per_token_above_272k_tokens": 4.95e-05,
+        "litellm_provider": "bedrock_mantle",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "use_openai_responses_path": true,
+        "supported_endpoints": [
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-daybreak-blue-56-sol.html"
+    },
     "bedrock_mantle/openai.gpt-5.6-luna": {
         "input_cost_per_token": 2.2e-07,
         "input_cost_per_token_above_272k_tokens": 4.4e-07,
@@ -55196,6 +55528,96 @@
         "supports_reasoning": true,
         "supports_vision": true
     },
+    "bedrock_mantle/openai.gpt-6-astra": {
+        "input_cost_per_token": 1.1e-05,
+        "input_cost_per_token_above_272k_tokens": 2.2e-05,
+        "cache_creation_input_token_cost": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
+        "cache_read_input_token_cost": 1.1e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
+        "output_cost_per_token": 5.5e-05,
+        "output_cost_per_token_above_272k_tokens": 8.25e-05,
+        "litellm_provider": "bedrock_mantle",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "responses",
+        "use_openai_responses_path": true,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
+    },
+    "us.openai.gpt-6-astra": {
+        "input_cost_per_token": 1.1e-05,
+        "input_cost_per_token_above_272k_tokens": 2.2e-05,
+        "cache_creation_input_token_cost": 1.375e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.75e-05,
+        "cache_read_input_token_cost": 1.1e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2.2e-06,
+        "output_cost_per_token": 5.5e-05,
+        "output_cost_per_token_above_272k_tokens": 8.25e-05,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
+    },
+    "global.openai.gpt-6-astra": {
+        "input_cost_per_token": 1e-05,
+        "input_cost_per_token_above_272k_tokens": 2e-05,
+        "cache_creation_input_token_cost": 1.25e-05,
+        "cache_creation_input_token_cost_above_272k_tokens": 2.5e-05,
+        "cache_read_input_token_cost": 1e-06,
+        "cache_read_input_token_cost_above_272k_tokens": 2e-06,
+        "output_cost_per_token": 5e-05,
+        "output_cost_per_token_above_272k_tokens": 7.5e-05,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1050000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_tool_choice": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_vision": true,
+        "source": "https://docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html"
+    },
     "bedrock_mantle/openai.gpt-5.5": {
         "input_cost_per_token": 5.5e-06,
         "input_cost_per_token_above_272k_tokens": 1.1e-05,
@@ -56861,8 +57283,8 @@
         "rpm": 10
     },
     "vertex_ai/gemini-3.5-transcribe-preview": {
-        "input_cost_per_audio_token": 2.5e-06,
-        "input_cost_per_token": 2.5e-06,
+        "input_cost_per_audio_token": 2e-06,
+        "input_cost_per_token": 2e-06,
         "litellm_provider": "vertex_ai",
         "mode": "audio_transcription",
         "output_cost_per_token": 1.2e-05,
@@ -56897,6 +57319,27 @@
         ],
         "supports_audio_input": true
     },
+    "vertex_ai/gemini-3.5-live-translate-preview": {
+        "input_cost_per_audio_token": 3.5e-06,
+        "input_cost_per_token": 3.5e-06,
+        "litellm_provider": "vertex_ai",
+        "mode": "realtime",
+        "output_cost_per_audio_token": 2.1e-05,
+        "output_cost_per_token": 2.1e-05,
+        "source": "https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing",
+        "supported_endpoints": [
+            "/v1/realtime"
+        ],
+        "supported_modalities": [
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "audio",
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": true
+    },
     "perplexity/pplx-embed-context-v1-0.6b": {
         "input_cost_per_token": 8e-09,
         "litellm_provider": "perplexity",
@@ -59588,6 +60031,77 @@
             "image"
         ]
     },
+    "xai/grok-imagine-video": {
+        "input_cost_per_image": 0.002,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.05,
+        "output_cost_per_second_480p": 0.05,
+        "output_cost_per_second_720p": 0.07,
+        "source": "https://docs.x.ai/docs/models/grok-imagine-video",
+        "supported_modalities": [
+            "text",
+            "image",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
+    "xai/grok-imagine-video-1.5": {
+        "input_cost_per_image": 0.01,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_1080p": 0.25,
+        "output_cost_per_second_480p": 0.08,
+        "output_cost_per_second_720p": 0.14,
+        "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
+    "xai/grok-imagine-video-1.5-2026-05-30": {
+        "input_cost_per_image": 0.01,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_1080p": 0.25,
+        "output_cost_per_second_480p": 0.08,
+        "output_cost_per_second_720p": 0.14,
+        "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
+    "xai/grok-imagine-video-1.5-preview": {
+        "input_cost_per_image": 0.01,
+        "litellm_provider": "xai",
+        "mode": "video_generation",
+        "output_cost_per_second": 0.08,
+        "output_cost_per_second_1080p": 0.25,
+        "output_cost_per_second_480p": 0.08,
+        "output_cost_per_second_720p": 0.14,
+        "source": "https://docs.x.ai/docs/models/grok-imagine-video-1.5",
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio"
+        ],
+        "supported_output_modalities": [
+            "video"
+        ]
+    },
     "low/1024-x-1024/grok-imagine-image-2.0": {
         "input_cost_per_image": 0.04,
         "litellm_provider": "xai",
@@ -60855,6 +61369,7 @@
         "litellm_provider": "cloudflare",
         "mode": "audio_transcription",
         "output_cost_per_second": 0.0,
+        "rpm": 720,
         "source": "https://developers.cloudflare.com/workers-ai/models/whisper/",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
@@ -60865,6 +61380,7 @@
         "litellm_provider": "cloudflare",
         "mode": "audio_transcription",
         "output_cost_per_second": 0.0,
+        "rpm": 720,
         "source": "https://developers.cloudflare.com/workers-ai/models/whisper-large-v3-turbo/",
         "supported_endpoints": [
             "/v1/audio/transcriptions"
@@ -60920,6 +61436,31 @@
         "supports_web_search": false,
         "output_cost_per_image": 0.08
     },
+    "gemini/lyria-3.5": {
+        "input_cost_per_token": 0,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_tokens": 65536,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_modalities": [
+            "text"
+        ],
+        "supported_output_modalities": [
+            "audio"
+        ],
+        "supports_audio_input": false,
+        "supports_audio_output": true,
+        "supports_function_calling": false,
+        "supports_prompt_caching": false,
+        "supports_response_schema": false,
+        "supports_system_messages": false,
+        "supports_vision": false,
+        "supports_web_search": false,
+        "output_cost_per_image": 0.08
+    },
     "perplexity/anthropic/claude-fable-5": {
         "litellm_provider": "perplexity",
         "mode": "responses",
diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json
index 47a1934a703..7ed1e7e568b 100644
--- a/model_prices_and_context_window.schema.json
+++ b/model_prices_and_context_window.schema.json
@@ -478,6 +478,10 @@
           "type": "number",
           "minimum": 0
         },
+        "output_cost_per_second_720p": {
+          "type": "number",
+          "minimum": 0
+        },
         "output_cost_per_token": {
           "type": "number",
           "minimum": 0,
diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py
index 6cc3dcceebc..bbb7b5f9c35 100644
--- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py
+++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py
@@ -1,5 +1,6 @@
-import os
+import json
 from collections.abc import Mapping, Sequence
+from pathlib import Path
 
 import pytest
 
@@ -11,8 +12,6 @@ from litellm.types.llms.openai import FileSearchTool, ResponsesAPIResponse, WebS
 from litellm.types.utils import ModelResponse, StandardBuiltInToolsParams
 
 
-
-
 def test_web_search_cost_low():
     web_search_options = WebSearchOptions(search_context_size="low")
     model_info = litellm.get_model_info("gpt-4o-search-preview")
@@ -683,12 +682,13 @@ def test_web_search_provider_prefix_fallback_does_not_misprice_non_gemini_model(
 
 
 def _openai_responses_with_web_search_calls(model, num_calls):
-    from litellm.types.llms.openai import ResponsesAPIResponse
     from openai.types.responses.response_function_web_search import (
         ActionSearch,
         ResponseFunctionWebSearch,
     )
 
+    from litellm.types.llms.openai import ResponsesAPIResponse
+
     output = [
         ResponseFunctionWebSearch(
             id=f"ws_{i}",
@@ -859,11 +859,62 @@ def test_dated_search_preview_entries_carry_search_pricing(local_model_cost_map)
         custom_llm_provider="openai",
         standard_built_in_tools_params=None,
     )
-    assert cost == pytest.approx(0.035), (
-        f"dated search-preview id must bill the $0.035 search fee, got ${cost}"
+    assert cost == pytest.approx(0.025), (
+        f"dated search-preview id must bill the $0.025 search fee, got ${cost}"
     )
 
 
+@pytest.mark.parametrize(
+    "web_search_options",
+    [
+        None,
+        WebSearchOptions(search_context_size="low"),
+        WebSearchOptions(search_context_size="medium"),
+        WebSearchOptions(search_context_size="high"),
+    ],
+)
+def test_gpt_4o_mini_snapshot_bills_web_search_like_its_alias(
+    web_search_options: WebSearchOptions | None, local_model_cost_map: None
+) -> None:
+    alias_info = litellm.get_model_info("gpt-4o-mini")
+    snapshot_info = litellm.get_model_info("gpt-4o-mini-2024-07-18")
+
+    assert not snapshot_info["supports_web_search"]
+    assert not alias_info["supports_web_search"]
+
+    snapshot_cost = StandardBuiltInToolCostTracking.get_cost_for_web_search(
+        web_search_options=web_search_options, model_info=snapshot_info
+    )
+    alias_cost = StandardBuiltInToolCostTracking.get_cost_for_web_search(
+        web_search_options=web_search_options, model_info=alias_info
+    )
+
+    assert snapshot_cost == alias_cost == 0.025
+
+
+def test_gpt_4o_mini_web_search_price_matches_in_both_cost_maps():
+    repo_root = Path(__file__).parents[4]
+    cost_maps = tuple(
+        json.loads((repo_root / path).read_text(encoding="utf-8"))
+        for path in (
+            "model_prices_and_context_window.json",
+            "litellm/model_prices_and_context_window_backup.json",
+        )
+    )
+    canonical, backup = cost_maps
+    expected_search_price = {
+        "search_context_size_low": 0.025,
+        "search_context_size_medium": 0.025,
+        "search_context_size_high": 0.025,
+    }
+    for model_name in ("gpt-4o-mini", "gpt-4o-mini-2024-07-18"):
+        canonical_entry = canonical[model_name]
+        backup_entry = backup[model_name]
+        assert canonical_entry["search_context_cost_per_query"] == expected_search_price
+        assert backup_entry["search_context_cost_per_query"] == expected_search_price
+        assert canonical_entry == backup_entry
+
+
 # Note: File search integration test removed due to complex annotation detection logic
 # The unit tests in test_azure_assistant_cost_tracking.py provide comprehensive coverage
 
diff --git a/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py b/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py
index c2c448cd7e2..96a2fa6ec67 100644
--- a/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py
+++ b/tests/test_litellm/llms/bedrock/chat/invoke_transformations/test_base_invoke_transformation.py
@@ -1,5 +1,7 @@
 import json
+from unittest.mock import MagicMock
 
+import httpx
 import pytest
 
 
@@ -190,3 +192,45 @@ def test_get_error_class_preserves_provider_headers():
     assert isinstance(error, BedrockError)
     assert error.headers == {"x-amzn-RequestId": "req-invoke-500"}
     assert error.response.headers["x-amzn-requestid"] == "req-invoke-500"
+
+
+def test_transform_response_hands_json_mode_to_nova():
+    """The invoke dispatcher forwards its json_mode argument to Nova instead of dropping it."""
+    from litellm.types.utils import ModelResponse
+
+    response_json = {
+        "output": {
+            "message": {
+                "role": "assistant",
+                "content": [
+                    {
+                        "toolUse": {
+                            "toolUseId": "tooluse_nova_json",
+                            "name": "json_tool_call",
+                            "input": {"city": "Paris", "temperature": 21},
+                        }
+                    }
+                ],
+            }
+        },
+        "stopReason": "tool_use",
+        "usage": {"inputTokens": 5, "outputTokens": 4, "totalTokens": 9},
+    }
+    raw_response = httpx.Response(200, json=response_json, request=httpx.Request("POST", "https://bedrock"))
+
+    result = AmazonInvokeConfig().transform_response(
+        model="invoke/amazon.nova-lite-v1:0",
+        raw_response=raw_response,
+        model_response=ModelResponse(),
+        logging_obj=MagicMock(),
+        request_data={},
+        messages=[{"role": "user", "content": "weather"}],
+        optional_params={},
+        litellm_params={},
+        encoding=None,
+        api_key=None,
+        json_mode=True,
+    )
+
+    assert result.choices[0].message.tool_calls is None
+    assert json.loads(result.choices[0].message.content) == {"city": "Paris", "temperature": 21}
diff --git a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py
index f0e361ceb88..51c0cd261e8 100644
--- a/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py
+++ b/tests/test_litellm/llms/bedrock/chat/test_converse_transformation.py
@@ -382,6 +382,8 @@ def test_reasoning_with_forced_tool_choice_switches_to_auto():
         "us.openai.gpt-5.6-sol",
         "global.openai.gpt-5.6-terra",
         "bedrock/converse/us.openai.gpt-5.6-luna",
+        "us.openai.gpt-6-astra",
+        "bedrock/converse/global.openai.gpt-6-astra",
     ],
 )
 def test_reasoning_effort_maps_to_reasoning_effort_for_openai_gpt5_converse(model, local_model_cost_map):
@@ -412,6 +414,7 @@ def test_reasoning_effort_maps_to_reasoning_effort_for_openai_gpt5_converse(mode
     [
         "us.openai.gpt-5.6-sol",
         "bedrock/converse/global.openai.gpt-5.6-luna",
+        "us.openai.gpt-6-astra",
     ],
 )
 def test_openai_gpt5_converse_never_forwards_thinking(model, local_model_cost_map):
@@ -6727,3 +6730,41 @@ def test_forced_tool_choice_forwarded_on_converse_models_that_support_it(
     )
 
     assert result == {"any": {}}
+
+
+def test_transform_response_honors_json_mode_kwarg_when_optional_params_lack_it():
+    response_json = {
+        "metrics": {"latencyMs": 900},
+        "output": {
+            "message": {
+                "content": [
+                    {
+                        "toolUse": {
+                            "input": {"city": "Paris", "population": 2100000},
+                            "name": "json_tool_call",
+                            "toolUseId": "tooluse_invoke_nova_json",
+                        }
+                    }
+                ],
+                "role": "assistant",
+            }
+        },
+        "stopReason": "tool_use",
+        "usage": {"inputTokens": 40, "outputTokens": 20, "totalTokens": 60},
+    }
+    raw_response = httpx.Response(200, json=response_json, request=httpx.Request("POST", "https://bedrock.test"))
+    logging_obj = MagicMock()
+    result = AmazonConverseConfig().transform_response(
+        model="bedrock/invoke/us.amazon.nova-micro-v1:0",
+        raw_response=raw_response,
+        model_response=ModelResponse(),
+        logging_obj=logging_obj,
+        request_data={},
+        messages=[],
+        optional_params={"tools": [{"type": "function", "function": {"name": "json_tool_call", "parameters": {}}}]},
+        litellm_params={},
+        encoding=None,
+        json_mode=True,
+    )
+    assert result.choices[0].message.tool_calls is None
+    assert json.loads(result.choices[0].message.content) == {"city": "Paris", "population": 2100000}
diff --git a/tests/test_litellm/llms/chatgpt/responses/test_chatgpt_responses_transformation.py b/tests/test_litellm/llms/chatgpt/responses/test_chatgpt_responses_transformation.py
index 8e0415d50de..a7520bd5955 100644
--- a/tests/test_litellm/llms/chatgpt/responses/test_chatgpt_responses_transformation.py
+++ b/tests/test_litellm/llms/chatgpt/responses/test_chatgpt_responses_transformation.py
@@ -10,18 +10,23 @@ from unittest.mock import MagicMock, patch
 import httpx
 import pytest
 
-
+import litellm
+from litellm.llms.chatgpt.responses.transformation import ChatGPTResponsesAPIConfig
 from litellm.llms.openai.common_utils import OpenAIError
+from litellm.main import responses_api_bridge_check
 from litellm.types.router import GenericLiteLLMParams
 from litellm.types.utils import LlmProviders
 from litellm.utils import ProviderConfigManager
-from litellm.llms.chatgpt.responses.transformation import ChatGPTResponsesAPIConfig
 
 
 class TestChatGPTResponsesAPITransformation:
     @pytest.mark.parametrize(
         "model_name",
         [
+            "chatgpt/gpt-5.5",
+            "chatgpt/gpt-5.6-luna",
+            "chatgpt/gpt-5.6-sol",
+            "chatgpt/gpt-5.6-terra",
             "chatgpt/gpt-5.4",
             "chatgpt/gpt-5.4-pro",
             "chatgpt/gpt-5.3-chat-latest",
@@ -40,6 +45,52 @@ class TestChatGPTResponsesAPITransformation:
         assert isinstance(config, ChatGPTResponsesAPIConfig)
         assert config.custom_llm_provider == LlmProviders.CHATGPT
 
+    @pytest.mark.parametrize(
+        "model_name",
+        [
+            "chatgpt/gpt-5.5",
+            "chatgpt/gpt-5.6-luna",
+            "chatgpt/gpt-5.6-sol",
+            "chatgpt/gpt-5.6-terra",
+        ],
+    )
+    def test_chatgpt_responses_model_metadata(self, model_name: str, local_model_cost_map: None) -> None:
+        model_info = litellm.get_model_info(model_name)
+
+        assert model_info["litellm_provider"] == "chatgpt"
+        assert model_info["mode"] == "responses"
+        assert model_info["supported_endpoints"] == [
+            "/v1/chat/completions",
+            "/v1/responses",
+        ]
+        assert model_info["max_input_tokens"] == 1050000
+        assert model_info["max_output_tokens"] == 128000
+
+    @pytest.mark.parametrize(
+        "model_name",
+        [
+            "gpt-5.5",
+            "gpt-5.6-luna",
+            "gpt-5.6-sol",
+            "gpt-5.6-terra",
+        ],
+    )
+    def test_chatgpt_models_bridge_chat_completions_to_responses(
+        self, model_name: str, local_model_cost_map: None
+    ) -> None:
+        """A chat completions request for these models must take the Responses bridge.
+
+        `gpt-5.6-*` also exists as an openai chat model, so an unregistered
+        chatgpt model resolves to mode "chat" here and never reaches the bridge.
+        """
+        model_info, resolved_model = responses_api_bridge_check(
+            model=model_name,
+            custom_llm_provider="chatgpt",
+        )
+
+        assert model_info["mode"] == "responses"
+        assert resolved_model == model_name
+
     @patch("litellm.llms.chatgpt.responses.transformation.Authenticator")
     def test_chatgpt_responses_endpoint_url(self, mock_authenticator_class):
         mock_auth_instance = MagicMock()
diff --git a/tests/test_litellm/llms/vertex_ai/audio_transcription/test_vertex_ai_gemini_transcribe_transformation.py b/tests/test_litellm/llms/vertex_ai/audio_transcription/test_vertex_ai_gemini_transcribe_transformation.py
index eadd87d9c92..08e46b1ffac 100644
--- a/tests/test_litellm/llms/vertex_ai/audio_transcription/test_vertex_ai_gemini_transcribe_transformation.py
+++ b/tests/test_litellm/llms/vertex_ai/audio_transcription/test_vertex_ai_gemini_transcribe_transformation.py
@@ -322,8 +322,8 @@ class TestModelCostEntry:
             entry = json.load(f)["vertex_ai/gemini-3.5-transcribe-preview"]
         assert entry["mode"] == "audio_transcription"
         assert entry["litellm_provider"] == "vertex_ai"
-        assert entry["input_cost_per_audio_token"] == pytest.approx(2.5e-06)
-        assert entry["input_cost_per_token"] == pytest.approx(2.5e-06)
+        assert entry["input_cost_per_audio_token"] == pytest.approx(2e-06)
+        assert entry["input_cost_per_token"] == pytest.approx(2e-06)
         assert entry["output_cost_per_token"] == pytest.approx(1.2e-05)
         assert entry["supported_endpoints"] == ["/v1/audio/transcriptions"]
 
diff --git a/tests/test_litellm/proxy/management_endpoints/policy_endpoints/test_ai_policy_suggester.py b/tests/test_litellm/proxy/management_endpoints/policy_endpoints/test_ai_policy_suggester.py
index 93dc429168f..bb71d67f24e 100644
--- a/tests/test_litellm/proxy/management_endpoints/policy_endpoints/test_ai_policy_suggester.py
+++ b/tests/test_litellm/proxy/management_endpoints/policy_endpoints/test_ai_policy_suggester.py
@@ -265,7 +265,7 @@ class TestSuggesterRejectsModelsWithoutToolCalling:
 
     def test_a_model_without_forced_tool_choice_support_remains_eligible(self, local_model_cost_map):
         supported_params = litellm.get_supported_openai_params(
-            model="amazon.nova-pro-v1:0",
+            model="meta.llama4-scout-17b-instruct-v1:0",
             custom_llm_provider="bedrock",
         )
 
diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py
index e42608c9904..8b186be43e5 100644
--- a/tests/test_litellm/test_utils.py
+++ b/tests/test_litellm/test_utils.py
@@ -56,6 +56,12 @@ from litellm.utils import (
 # Adds the parent directory to the system path
 
 
+def test_cloudflare_model_info_includes_rpm(local_model_cost_map: None) -> None:
+    assert litellm.get_model_info("cloudflare/@cf/meta/llama-3.1-8b-instruct-fp8")["rpm"] == 300
+    assert litellm.get_model_info("cloudflare/@cf/moonshotai/kimi-k2.6")["rpm"] == 20
+    assert litellm.get_model_info("cloudflare/@cf/openai/whisper-large-v3-turbo")["rpm"] == 720
+
+
 def test_get_utc_datetime_returns_current_aware_utc_time() -> None:
     before: Final = datetime.now(timezone.utc)
     result: Final = litellm.utils.get_utc_datetime()
@@ -810,6 +816,7 @@ def validate_model_cost_values(model_data, exceptions=None):
         "input_cost_per_second",
         "output_cost_per_second",
         "output_cost_per_second_480p",
+        "output_cost_per_second_720p",
         "output_cost_per_second_1080p",
         "output_cost_per_second_4k",
         "input_cost_per_query",
@@ -1033,6 +1040,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "output_cost_per_pixel": {"type": "number"},
                 "output_cost_per_second": {"type": "number"},
                 "output_cost_per_second_480p": {"type": "number"},
+                "output_cost_per_second_720p": {"type": "number"},
                 "output_cost_per_second_1080p": {"type": "number"},
                 "output_cost_per_second_4k": {"type": "number"},
                 "output_cost_per_token": {"type": "number"},
@@ -1405,23 +1413,35 @@ def test_supports_tool_choice_simple_tests():
         is True
     )
 
-    assert (
-        litellm.utils.supports_tool_choice(model="us.amazon.nova-micro-v1:0") is False
-    )
-    assert (
-        litellm.utils.supports_tool_choice(model="bedrock/us.amazon.nova-micro-v1:0")
-        is False
-    )
-    assert (
-        litellm.utils.supports_tool_choice(
-            model="us.amazon.nova-micro-v1:0", custom_llm_provider="bedrock_converse"
-        )
-        is False
-    )
-
     assert litellm.utils.supports_tool_choice(model="perplexity/sonar") is False
 
 
+@pytest.mark.usefixtures("local_model_cost_map")
+@pytest.mark.parametrize(
+    "model",
+    [
+        "amazon.nova-lite-v1:0",
+        "amazon.nova-micro-v1:0",
+        "amazon.nova-pro-v1:0",
+        "apac.amazon.nova-lite-v1:0",
+        "apac.amazon.nova-micro-v1:0",
+        "apac.amazon.nova-pro-v1:0",
+        "bedrock/us-gov-east-1/amazon.nova-pro-v1:0",
+        "bedrock/us-gov-west-1/amazon.nova-lite-v1:0",
+        "bedrock/us-gov-west-1/amazon.nova-micro-v1:0",
+        "bedrock/us-gov-west-1/amazon.nova-pro-v1:0",
+        "eu.amazon.nova-lite-v1:0",
+        "eu.amazon.nova-micro-v1:0",
+        "eu.amazon.nova-pro-v1:0",
+        "us.amazon.nova-lite-v1:0",
+        "us.amazon.nova-micro-v1:0",
+        "us.amazon.nova-pro-v1:0",
+    ],
+)
+def test_amazon_nova_v1_understanding_models_support_tool_choice(model: str) -> None:
+    assert litellm.utils.supports_tool_choice(model=model) is True
+
+
 def test_check_provider_match():
     """
     Test the _check_provider_match function for various provider scenarios
diff --git a/tests/test_litellm/test_video_generation.py b/tests/test_litellm/test_video_generation.py
index 2a60ff9c4b5..f3cd4618078 100644
--- a/tests/test_litellm/test_video_generation.py
+++ b/tests/test_litellm/test_video_generation.py
@@ -532,6 +532,32 @@ class TestVideoGeneration:
         assert abs(cost_for("runwayml/seedance2_5", "480p", 8.0) - 1.6) < 0.001
         assert abs(cost_for("runwayml/gen4.5", None, 8.0) - 0.96) < 0.001
 
+    def test_completion_cost_xai_imagine_video_720p_tier_from_cost_map(self, monkeypatch):
+        """720p xAI Imagine Video requests bill the published 720p rate, not the 480p base rate."""
+        from litellm.cost_calculator import completion_cost
+
+        local_map_path = os.path.join(
+            os.path.dirname(__file__), "..", "..", "model_prices_and_context_window.json"
+        )
+        with open(local_map_path, "r") as f:
+            monkeypatch.setattr(litellm, "model_cost", json.load(f))
+
+        def cost_for(model: str, resolution: str, duration: float) -> float:
+            mock_response = MagicMock()
+            mock_response.usage = {"duration_seconds": duration, "video_resolution": resolution}
+            type(mock_response)._hidden_params = {}
+            return completion_cost(
+                completion_response=mock_response,
+                model=model,
+                call_type="create_video",
+                custom_llm_provider="xai",
+            )
+
+        assert abs(cost_for("xai/grok-imagine-video", "720p", 10.0) - 0.7) < 0.001
+        assert abs(cost_for("xai/grok-imagine-video-1.5", "720p", 10.0) - 1.4) < 0.001
+        assert abs(cost_for("xai/grok-imagine-video-1.5", "480p", 10.0) - 0.8) < 0.001
+        assert abs(cost_for("xai/grok-imagine-video-1.5", "1080p", 10.0) - 2.5) < 0.001
+
     def test_completion_cost_veo_31_tiers_pin_published_rates(self, monkeypatch):
         """The gemini and vertex_ai veo 3.1 entries bill Google's published per-second tier rates."""
         from litellm.cost_calculator import completion_cost
diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts
index adbdb2f46d9..6d62ce2b675 100644
--- a/ui/litellm-dashboard/src/lib/http/schema.d.ts
+++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts
@@ -29741,6 +29741,8 @@ export interface components {
             output_cost_per_second_480p?: number | null;
             /** Output Cost Per Second 4K */
             output_cost_per_second_4k?: number | null;
+            /** Output Cost Per Second 720P */
+            output_cost_per_second_720p?: number | null;
             /** Output Cost Per Token */
             output_cost_per_token?: number | null;
             /** Output Cost Per Token Above 128K Tokens */
@@ -39932,6 +39934,8 @@ export interface components {
             output_cost_per_second_480p?: number | null;
             /** Output Cost Per Second 4K */
             output_cost_per_second_4k?: number | null;
+            /** Output Cost Per Second 720P */
+            output_cost_per_second_720p?: number | null;
             /** Output Cost Per Token */
             output_cost_per_token?: number | null;
             /** Output Cost Per Token Above 128K Tokens */
diff --git a/whitelisted_bedrock_models.txt b/whitelisted_bedrock_models.txt
index 578edddec8d..6124cb41044 100644
--- a/whitelisted_bedrock_models.txt
+++ b/whitelisted_bedrock_models.txt
@@ -6,6 +6,7 @@ ai21.jamba-instruct-v1:0
 twelvelabs.pegasus-1-2-v1:0
 us.twelvelabs.pegasus-1-2-v1:0
 eu.twelvelabs.pegasus-1-2-v1:0
+global.twelvelabs.pegasus-1-2-v1:0
 amazon.titan-text-express-v1
 amazon.titan-text-lite-v1
 amazon.titan-text-premier-v1:0