diff --git a/litellm/cost_calculator.py b/litellm/cost_calculator.py
index 7b02a5ede00..ae54b91c5a0 100644
--- a/litellm/cost_calculator.py
+++ b/litellm/cost_calculator.py
@@ -33,6 +33,7 @@ from litellm.litellm_core_utils.llm_cost_calc.utils import (
     _get_service_tier_cost_key,
     calculate_cost_component,
     generic_cost_per_token,
+    get_batch_cost_rates,
     get_billable_input_tokens,
     get_token_type_cost_breakdown,
     parse_prompt_tokens_details,
@@ -2557,35 +2558,14 @@ def batch_cost_calculator(
     if not model_info:
         return 0.0, 0.0
 
-    input_cost_per_token_batches: Final = model_info.get("input_cost_per_token_batches")
+    batch_rates: Final = get_batch_cost_rates(model_info, usage, custom_llm_provider)
     input_cost_per_token: Final = model_info.get("input_cost_per_token")
-    output_cost_per_token_batches: Final = model_info.get("output_cost_per_token_batches")
     output_cost_per_token: Final = model_info.get("output_cost_per_token")
     total_prompt_cost = 0.0
     total_completion_cost = 0.0
-    if input_cost_per_token_batches is not None:
-        batch_details: Final = parse_prompt_tokens_details(usage)
-        audio_tokens, image_tokens, video_tokens = (
-            batch_details["audio_tokens"],
-            batch_details["image_tokens"],
-            batch_details["video_tokens"],
-        )
-        modality_rates: Final = (
-            _batch_rate(model_info, "input_cost_per_audio_token_batches", input_cost_per_token_batches),
-            _batch_rate(model_info, "input_cost_per_image_token_batches", input_cost_per_token_batches),
-            _batch_rate(model_info, "input_cost_per_video_token_batches", input_cost_per_token_batches),
-        )
-        total_prompt_cost = sum(
-            tokens * rate
-            for tokens, rate in zip(
-                (
-                    max((usage.prompt_tokens or 0) - audio_tokens - image_tokens - video_tokens, 0),
-                    audio_tokens,
-                    image_tokens,
-                    video_tokens,
-                ),
-                (input_cost_per_token_batches, *modality_rates),
-            )
+    if batch_rates.input is not None:
+        total_prompt_cost = _batch_prompt_cost(
+            usage, model_info, batch_rates.input, batch_rates.cache_read, batch_rates.cache_creation
         )
     elif input_cost_per_token:
         details: Final = parse_prompt_tokens_details(usage)
@@ -2605,8 +2585,8 @@ def batch_cost_calculator(
 
         cache_creation_cost: Final = model_info.get("cache_creation_input_token_cost") or input_cost_per_token
         total_prompt_cost += cache_creation_tokens * cache_creation_cost / 2
-    if output_cost_per_token_batches is not None:
-        total_completion_cost = usage.completion_tokens * output_cost_per_token_batches
+    if batch_rates.output is not None:
+        total_completion_cost = usage.completion_tokens * batch_rates.output
     elif output_cost_per_token:
         total_completion_cost = (
             usage.completion_tokens * (output_cost_per_token) / 2
@@ -2620,6 +2600,34 @@ def batch_cost_calculator(
     return total_prompt_cost, total_completion_cost
 
 
+def _batch_prompt_cost(
+    usage: Usage,
+    model_info: ModelInfo,
+    input_rate: float,
+    cache_read_rate: float | None,
+    cache_creation_rate: float | None,
+) -> float:
+    details: Final = parse_prompt_tokens_details(usage)
+    cached_tokens: Final = details["cache_hit_tokens"] if cache_read_rate is not None else 0
+    written_tokens: Final = details["cache_creation_tokens"] if cache_creation_rate is not None else 0
+    audio_tokens, image_tokens, video_tokens = (
+        details["audio_tokens"],
+        details["image_tokens"],
+        details["video_tokens"],
+    )
+    text_tokens: Final = max(
+        (usage.prompt_tokens or 0) - audio_tokens - image_tokens - video_tokens - cached_tokens - written_tokens, 0
+    )
+    return (
+        text_tokens * input_rate
+        + audio_tokens * _batch_rate(model_info, "input_cost_per_audio_token_batches", input_rate)
+        + image_tokens * _batch_rate(model_info, "input_cost_per_image_token_batches", input_rate)
+        + video_tokens * _batch_rate(model_info, "input_cost_per_video_token_batches", input_rate)
+        + cached_tokens * (cache_read_rate or 0.0)
+        + written_tokens * (cache_creation_rate or 0.0)
+    )
+
+
 def _attribute_value(obj: object, name: str) -> object:
     return getattr(obj, name)
 
diff --git a/litellm/litellm_core_utils/litellm_logging.py b/litellm/litellm_core_utils/litellm_logging.py
index 306812cca0a..357ee51a44a 100644
--- a/litellm/litellm_core_utils/litellm_logging.py
+++ b/litellm/litellm_core_utils/litellm_logging.py
@@ -387,11 +387,40 @@ _DEPLOYMENT_PRICING_KEYS: Final = (
     "output_cost_per_token",
     "input_cost_per_token_batches",
     "output_cost_per_token_batches",
+    "input_cost_per_token_above_272k_tokens_batches",
+    "output_cost_per_token_above_272k_tokens_batches",
+    "cache_read_input_token_cost_batches",
+    "cache_read_input_token_cost_above_272k_tokens_batches",
+    "cache_creation_input_token_cost_batches",
+    "cache_creation_input_token_cost_above_272k_tokens_batches",
     "ocr_cost_per_page",
     "ocr_cost_per_page_batches",
     "annotation_cost_per_page",
     "annotation_cost_per_page_batches",
 )
+_INPUT_PRICING_KEY_PREFIXES: Final = (
+    "input_cost_per_token",
+    "cache_read_input_token_cost",
+    "cache_creation_input_token_cost",
+)
+_OUTPUT_PRICING_KEY_PREFIXES: Final = ("output_cost_per_token",)
+_BATCH_PRICING_KEY_SUFFIX: Final = "_batches"
+
+
+_NO_CARRIED_RATES: Final[Mapping[str, object]] = MappingProxyType({})
+
+
+def _published_direction(
+    published: ModelInfo, registered: Mapping[str, object], flat_key: str, prefixes: tuple[str, ...]
+) -> Mapping[str, object]:
+    return MappingProxyType(
+        {
+            key: value
+            for key, value in published.items()
+            if registered.get(key) is None
+            and (key == flat_key or (key.startswith(prefixes) and key.endswith(_BATCH_PRICING_KEY_SUFFIX)))
+        }
+    )
 
 
 def deployment_pricing_model_info(model_id: str | None, deployment_model: str | None) -> ModelInfo | None:
@@ -403,12 +432,15 @@ def deployment_pricing_model_info(model_id: str | None, deployment_model: str |
     get_model_info fills absent costs with 0, so asking it directly cannot
     tell "configured as free" apart from "no pricing configured". A deployment
     may declare only one side of its pricing, so the side it leaves out keeps
-    the model's published rates instead of billing as zero. Ownership is per
-    token direction: declaring either rate for a direction takes that whole
-    direction, so a published batch rate can never displace a standard rate
-    the deployment configured itself. OCR per-page rates count as declared
-    pricing too; they pass through as registered and ``ocr_batch_cost`` layers
-    the published rate under each per-page family the deployment leaves out.
+    the model's published standard rate and every published batch rate for
+    that direction (flat, long-context tier, cached, cache write) instead of
+    billing as zero. Ownership is per token direction: declaring the flat
+    standard or flat batch rate for a direction takes that whole direction, so
+    a published batch rate can never displace a standard rate the deployment
+    configured itself. A tier-only override keeps every published rate it left
+    out. OCR per-page rates count as declared pricing too; they pass through as
+    registered and ``ocr_batch_cost`` layers the published rate under each
+    per-page family the deployment leaves out.
     """
     if model_id is None:
         return None
@@ -429,13 +461,22 @@ def deployment_pricing_model_info(model_id: str | None, deployment_model: str |
         registered.get("output_cost_per_token") is not None
         or registered.get("output_cost_per_token_batches") is not None
     )
-    if not declares_input:
-        merged["input_cost_per_token"] = published.get("input_cost_per_token")
-        merged["input_cost_per_token_batches"] = published.get("input_cost_per_token_batches")
-    if not declares_output:
-        merged["output_cost_per_token"] = published.get("output_cost_per_token")
-        merged["output_cost_per_token_batches"] = published.get("output_cost_per_token_batches")
-    return merged
+    carried_input: Final = (
+        _NO_CARRIED_RATES
+        if declares_input
+        else _published_direction(published, registered, "input_cost_per_token", _INPUT_PRICING_KEY_PREFIXES)
+    )
+    carried_output: Final = (
+        _NO_CARRIED_RATES
+        if declares_output
+        else _published_direction(published, registered, "output_cost_per_token", _OUTPUT_PRICING_KEY_PREFIXES)
+    )
+    priced: Final[ModelInfo] = {  # pyright: ignore[reportAssignmentType]  # carried keys are ModelInfo rates
+        **merged,
+        **carried_input,
+        **carried_output,
+    }
+    return priced
 
 
 def _published_pricing(deployment_model: str | None) -> ModelInfo | None:
diff --git a/litellm/litellm_core_utils/llm_cost_calc/utils.py b/litellm/litellm_core_utils/llm_cost_calc/utils.py
index c60e3089816..3845f50af79 100644
--- a/litellm/litellm_core_utils/llm_cost_calc/utils.py
+++ b/litellm/litellm_core_utils/llm_cost_calc/utils.py
@@ -67,6 +67,15 @@ _SERVICE_TIER_TO_COST_KEY_SUFFIX: Final[Mapping[str, str]] = MappingProxyType(
 )
 
 _INCLUSIVE_THRESHOLD_PROVIDERS: Final = frozenset({"xai"})
+_BATCH_KEY_SUFFIX: Final = "_batches"
+_BATCH_RATE_PREFIXES: Final = (
+    "input_cost_per_token",
+    "output_cost_per_token",
+    "cache_read_input_token_cost",
+    "cache_creation_input_token_cost",
+)
+_BATCH_TIER_KEY: Final = re.compile(rf"^({'|'.join(_BATCH_RATE_PREFIXES)})_above_(\d+k?)_tokens{_BATCH_KEY_SUFFIX}$")
+_NON_STANDARD_THRESHOLD_SUFFIXES: Final = (*_SERVICE_TIER_SUFFIXES, _BATCH_KEY_SUFFIX)
 
 
 def _uses_inclusive_token_thresholds(custom_llm_provider: str | None) -> bool:
@@ -248,9 +257,80 @@ def _get_service_tier_cost_key(base_key: str, service_tier: str | None) -> str:
     return f"{base_key}_{suffix}"
 
 
+def _parse_token_threshold(threshold: str) -> float:
+    return float(threshold.replace("k", "")) * (1000 if "k" in threshold else 1)
+
+
 def _parse_above_token_threshold(key: str) -> float:
-    threshold_str: Final = key.split("_above_")[1].split("_tokens")[0]
-    return float(threshold_str.replace("k", "")) * (1000 if "k" in threshold_str else 1)
+    return _parse_token_threshold(key.split("_above_")[1].split("_tokens")[0])
+
+
+def _prompt_exceeds_threshold(prompt_tokens: int, threshold: float, inclusive: bool) -> bool:
+    return prompt_tokens > threshold or (inclusive and prompt_tokens == threshold)
+
+
+@dataclass(frozen=True, slots=True)
+class BatchCostRates:
+    input: float | None
+    output: float | None
+    cache_read: float | None
+    cache_creation: float | None
+
+
+def _batch_rate(model_info: ModelInfo, key: str) -> float | None:
+    value: Final = model_info.get(key)
+    if isinstance(value, (int, float)):
+        return float(value)
+    if not isinstance(value, str):
+        return None
+    try:
+        return float(value)
+    except ValueError:
+        return None
+
+
+def _batch_tier_rate(model_info: ModelInfo, tier_key: str, flat_key: str) -> float | None:
+    tier_rate: Final = _batch_rate(model_info, tier_key)
+    return _batch_rate(model_info, flat_key) if tier_rate is None else tier_rate
+
+
+def _batch_tier_thresholds(model_info: ModelInfo, prefix: str) -> frozenset[str]:
+    return frozenset(
+        tier.group(2)
+        for key, value in model_info.items()
+        if value is not None and (tier := _BATCH_TIER_KEY.match(key)) is not None and tier.group(1) == prefix
+    )
+
+
+def _crossed_batch_tier(model_info: ModelInfo, prefix: str, usage: Usage, inclusive: bool) -> str | None:
+    return next(
+        (
+            threshold
+            for threshold in sorted(
+                _batch_tier_thresholds(model_info, prefix), key=_parse_token_threshold, reverse=True
+            )
+            if _prompt_exceeds_threshold(usage.prompt_tokens, _parse_token_threshold(threshold), inclusive)
+        ),
+        None,
+    )
+
+
+def _batch_rate_for_prefix(model_info: ModelInfo, prefix: str, usage: Usage, inclusive: bool) -> float | None:
+    flat_key: Final = f"{prefix}{_BATCH_KEY_SUFFIX}"
+    threshold: Final = _crossed_batch_tier(model_info, prefix, usage, inclusive)
+    if threshold is None:
+        return _batch_rate(model_info, flat_key)
+    return _batch_tier_rate(model_info, f"{prefix}_above_{threshold}_tokens{_BATCH_KEY_SUFFIX}", flat_key)
+
+
+def get_batch_cost_rates(model_info: ModelInfo, usage: Usage, custom_llm_provider: str | None) -> BatchCostRates:
+    inclusive: Final = _uses_inclusive_token_thresholds(custom_llm_provider)
+    return BatchCostRates(
+        input=_batch_rate_for_prefix(model_info, "input_cost_per_token", usage, inclusive),
+        output=_batch_rate_for_prefix(model_info, "output_cost_per_token", usage, inclusive),
+        cache_read=_batch_rate_for_prefix(model_info, "cache_read_input_token_cost", usage, inclusive),
+        cache_creation=_batch_rate_for_prefix(model_info, "cache_creation_input_token_cost", usage, inclusive),
+    )
 
 
 def _select_priced_tier(model_info: ModelInfo, usage: Usage) -> dict | None:
@@ -576,7 +656,9 @@ def _get_token_base_cost(
     # so that the threshold detection loop only processes standard keys.  The
     # service_tier-specific above-threshold key is resolved later via _get_service_tier_cost_key.
     threshold_keys: Final = [
-        k for k in model_info if k.startswith("input_cost_per_token_above_") and not k.endswith(_SERVICE_TIER_SUFFIXES)
+        k
+        for k in model_info
+        if k.startswith("input_cost_per_token_above_") and not k.endswith(_NON_STANDARD_THRESHOLD_SUFFIXES)
     ]
 
     # Only sort the threshold keys (typically 1-2 keys instead of 66+)
@@ -588,7 +670,7 @@ def _get_token_base_cost(
                 # Handle both formats: _above_128k_tokens and _above_128_tokens
                 threshold_str = key.split("_above_")[1].split("_tokens")[0]
                 threshold = _parse_above_token_threshold(key)
-                if usage.prompt_tokens > threshold or (threshold_is_inclusive and usage.prompt_tokens == threshold):
+                if _prompt_exceeds_threshold(usage.prompt_tokens, threshold, threshold_is_inclusive):
                     # Prefer a service_tier-specific above-threshold key when available,
                     # e.g. input_cost_per_token_priority_above_200k_tokens for Gemini
                     # ON_DEMAND_PRIORITY.  Falls back to the standard key automatically
diff --git a/litellm/llms/azure/passthrough/transformation.py b/litellm/llms/azure/passthrough/transformation.py
index 1b5a4083ebe..c40cefecdd0 100644
--- a/litellm/llms/azure/passthrough/transformation.py
+++ b/litellm/llms/azure/passthrough/transformation.py
@@ -143,7 +143,7 @@ class AzurePassthroughConfig(BasePassthroughConfig):
     ) -> dict:
         return BaseAzureLLM._base_validate_azure_environment(
             headers=headers,
-            litellm_params=GenericLiteLLMParams(**{**litellm_params, "api_key": api_key}),
+            litellm_params=GenericLiteLLMParams.model_validate({**litellm_params, "api_key": api_key}),
         )
 
     @staticmethod
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 468d86d049d..7cde9a1162e 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -34129,6 +34129,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 2e-06,
         "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06,
         "cache_read_input_token_cost_above_272k_tokens_priority": 4e-06,
+        "cache_read_input_token_cost_batches": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 1e-06,
+        "cache_creation_input_token_cost_batches": 6.25e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05,
         "cache_read_input_token_cost_flex": 5e-07,
         "cache_read_input_token_cost_priority": 2e-06,
         "input_cost_per_token": 1e-05,
@@ -34136,6 +34140,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 4e-05,
         "input_cost_per_token_batches": 5e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 1e-05,
         "input_cost_per_token_flex": 5e-06,
         "input_cost_per_token_priority": 2e-05,
         "litellm_provider": "openai",
@@ -34148,6 +34153,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 3.75e-05,
         "output_cost_per_token_above_272k_tokens_priority": 0.00015,
         "output_cost_per_token_batches": 2.5e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 3.75e-05,
         "output_cost_per_token_flex": 2.5e-05,
         "output_cost_per_token_priority": 0.0001,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34199,6 +34205,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 8e-07,
         "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07,
         "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
+        "cache_read_input_token_cost_batches": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07,
+        "cache_creation_input_token_cost_batches": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 5e-06,
         "cache_read_input_token_cost_flex": 2e-07,
         "cache_read_input_token_cost_priority": 8e-07,
         "input_cost_per_token": 4e-06,
@@ -34206,6 +34216,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 4e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
         "input_cost_per_token_batches": 2e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 4e-06,
         "input_cost_per_token_flex": 2e-06,
         "input_cost_per_token_priority": 8e-06,
         "litellm_provider": "openai",
@@ -34218,6 +34229,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 1.5e-05,
         "output_cost_per_token_above_272k_tokens_priority": 6e-05,
         "output_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 1.5e-05,
         "output_cost_per_token_flex": 1e-05,
         "output_cost_per_token_priority": 4e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34266,6 +34278,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 8e-07,
         "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07,
         "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
+        "cache_read_input_token_cost_batches": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07,
+        "cache_creation_input_token_cost_batches": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 5e-06,
         "cache_read_input_token_cost_flex": 2e-07,
         "cache_read_input_token_cost_priority": 8e-07,
         "input_cost_per_token": 4e-06,
@@ -34273,6 +34289,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 4e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
         "input_cost_per_token_batches": 2e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 4e-06,
         "input_cost_per_token_flex": 2e-06,
         "input_cost_per_token_priority": 8e-06,
         "litellm_provider": "openai",
@@ -34285,6 +34302,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 1.5e-05,
         "output_cost_per_token_above_272k_tokens_priority": 6e-05,
         "output_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 1.5e-05,
         "output_cost_per_token_flex": 1e-05,
         "output_cost_per_token_priority": 4e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34335,6 +34353,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
         "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_batches": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 2e-07,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06,
         "cache_read_input_token_cost_flex": 1e-07,
         "cache_read_input_token_cost_priority": 4e-07,
         "input_cost_per_token": 2e-06,
@@ -34342,6 +34364,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 2e-06,
         "input_cost_per_token_above_272k_tokens_priority": 8e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 2e-06,
         "input_cost_per_token_flex": 1e-06,
         "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "openai",
@@ -34354,6 +34377,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 9e-06,
         "output_cost_per_token_above_272k_tokens_priority": 3.6e-05,
         "output_cost_per_token_batches": 6e-06,
+        "output_cost_per_token_above_272k_tokens_batches": 9e-06,
         "output_cost_per_token_flex": 6e-06,
         "output_cost_per_token_priority": 2.4e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34403,6 +34427,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 4e-08,
         "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08,
         "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
+        "cache_read_input_token_cost_batches": 1e-08,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 2e-08,
+        "cache_creation_input_token_cost_batches": 1.25e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-07,
         "cache_read_input_token_cost_flex": 1e-08,
         "cache_read_input_token_cost_priority": 4e-08,
         "input_cost_per_token": 2e-07,
@@ -34410,6 +34438,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 2e-07,
         "input_cost_per_token_above_272k_tokens_priority": 8e-07,
         "input_cost_per_token_batches": 1e-07,
+        "input_cost_per_token_above_272k_tokens_batches": 2e-07,
         "input_cost_per_token_flex": 1e-07,
         "input_cost_per_token_priority": 4e-07,
         "litellm_provider": "openai",
@@ -34422,6 +34451,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 9e-07,
         "output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
         "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_above_272k_tokens_batches": 9e-07,
         "output_cost_per_token_flex": 6e-07,
         "output_cost_per_token_priority": 2.4e-06,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34692,12 +34722,15 @@
     "gpt-5.5": {
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+        "cache_read_input_token_cost_batches": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
         "cache_read_input_token_cost_flex": 2.5e-07,
         "cache_read_input_token_cost_priority": 1.25e-06,
         "input_cost_per_token": 5e-06,
         "input_cost_per_token_above_272k_tokens": 1e-05,
         "input_cost_per_token_flex": 2.5e-06,
         "input_cost_per_token_batches": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 5e-06,
         "input_cost_per_token_priority": 1.25e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
@@ -34708,6 +34741,7 @@
         "output_cost_per_token_above_272k_tokens": 4.5e-05,
         "output_cost_per_token_flex": 1.5e-05,
         "output_cost_per_token_batches": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 2.25e-05,
         "output_cost_per_token_priority": 7.5e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
@@ -34750,12 +34784,15 @@
     "gpt-5.5-2026-04-23": {
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+        "cache_read_input_token_cost_batches": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
         "cache_read_input_token_cost_flex": 2.5e-07,
         "cache_read_input_token_cost_priority": 1.25e-06,
         "input_cost_per_token": 5e-06,
         "input_cost_per_token_above_272k_tokens": 1e-05,
         "input_cost_per_token_flex": 2.5e-06,
         "input_cost_per_token_batches": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 5e-06,
         "input_cost_per_token_priority": 1.25e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
@@ -34766,6 +34803,7 @@
         "output_cost_per_token_above_272k_tokens": 4.5e-05,
         "output_cost_per_token_flex": 1.5e-05,
         "output_cost_per_token_batches": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 2.25e-05,
         "output_cost_per_token_priority": 7.5e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
@@ -34810,6 +34848,7 @@
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_above_272k_tokens_batches": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -34819,6 +34858,7 @@
         "output_cost_per_token_above_272k_tokens": 0.00027,
         "output_cost_per_token_flex": 9e-05,
         "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 0.000135,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
@@ -34859,6 +34899,7 @@
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_above_272k_tokens_batches": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -34868,6 +34909,7 @@
         "output_cost_per_token_above_272k_tokens": 0.00027,
         "output_cost_per_token_flex": 9e-05,
         "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 0.000135,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
@@ -34906,12 +34948,15 @@
     "gpt-5.4": {
         "cache_read_input_token_cost": 2.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_batches": 1.25e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07,
         "cache_read_input_token_cost_flex": 1.3e-07,
         "cache_read_input_token_cost_priority": 5e-07,
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_above_272k_tokens": 5e-06,
         "input_cost_per_token_flex": 1.25e-06,
         "input_cost_per_token_batches": 1.25e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 2.5e-06,
         "input_cost_per_token_priority": 5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
@@ -34922,6 +34967,7 @@
         "output_cost_per_token_above_272k_tokens": 2.25e-05,
         "output_cost_per_token_flex": 7.5e-06,
         "output_cost_per_token_batches": 7.5e-06,
+        "output_cost_per_token_above_272k_tokens_batches": 1.125e-05,
         "output_cost_per_token_priority": 3e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
@@ -34959,12 +35005,15 @@
     "gpt-5.4-2026-03-05": {
         "cache_read_input_token_cost": 2.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_batches": 1.25e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07,
         "cache_read_input_token_cost_flex": 1.3e-07,
         "cache_read_input_token_cost_priority": 5e-07,
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_above_272k_tokens": 5e-06,
         "input_cost_per_token_flex": 1.25e-06,
         "input_cost_per_token_batches": 1.25e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 2.5e-06,
         "input_cost_per_token_priority": 5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
@@ -34975,6 +35024,7 @@
         "output_cost_per_token_above_272k_tokens": 2.25e-05,
         "output_cost_per_token_flex": 7.5e-06,
         "output_cost_per_token_batches": 7.5e-06,
+        "output_cost_per_token_above_272k_tokens_batches": 1.125e-05,
         "output_cost_per_token_priority": 3e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
@@ -35014,6 +35064,7 @@
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_above_272k_tokens_batches": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -35023,6 +35074,7 @@
         "output_cost_per_token_above_272k_tokens": 0.00027,
         "output_cost_per_token_flex": 9e-05,
         "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 0.000135,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
@@ -35064,6 +35116,7 @@
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_above_272k_tokens_batches": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -35073,6 +35126,7 @@
         "output_cost_per_token_above_272k_tokens": 0.00027,
         "output_cost_per_token_flex": 9e-05,
         "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 0.000135,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
diff --git a/litellm/types/utils.py b/litellm/types/utils.py
index bb0b3d2a687..f10f102d8ec 100644
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@@ -291,6 +291,10 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     cache_read_input_token_cost_above_272k_tokens_priority: float | None
     cache_read_input_token_cost_above_272k_tokens_flex: float | None
     cache_read_input_token_cost_above_512k_tokens: float | None
+    cache_read_input_token_cost_batches: ReadOnly[float | None]
+    cache_read_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None]
+    cache_creation_input_token_cost_batches: ReadOnly[float | None]
+    cache_creation_input_token_cost_above_272k_tokens_batches: ReadOnly[float | None]
     # Smallest prefix this model will actually cache, whatever caching mechanism its provider uses.
     # Absent means the provider-agnostic default applies; see MINIMUM_PROMPT_CACHE_TOKEN_COUNT.
     prompt_cache_min_tokens: int | None
@@ -316,7 +320,9 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     input_cost_per_second: float | None  # for OpenAI Speech models
     input_cost_per_token_batches: float | None
     input_cost_per_video_token_batches: ReadOnly[float | None]
+    input_cost_per_token_above_272k_tokens_batches: ReadOnly[float | None]
     output_cost_per_token_batches: float | None
+    output_cost_per_token_above_272k_tokens_batches: ReadOnly[float | None]
     output_cost_per_token: Required[float | None]
     output_cost_per_token_flex: float | None  # OpenAI flex service tier pricing
     output_cost_per_token_priority: float | None  # OpenAI priority service tier pricing
@@ -3718,6 +3724,10 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
     cache_read_input_token_cost_above_200k_tokens_priority: float | None = None
     cache_read_input_token_cost_above_272k_tokens_priority: float | None = None
     cache_read_input_token_cost_above_272k_tokens_flex: float | None = None
+    cache_read_input_token_cost_batches: float | None = None
+    cache_read_input_token_cost_above_272k_tokens_batches: float | None = None
+    cache_creation_input_token_cost_batches: float | None = None
+    cache_creation_input_token_cost_above_272k_tokens_batches: float | None = None
     cache_read_input_audio_token_cost: float | None = None
     cache_read_input_image_token_cost: float | None = None
     input_cost_per_character_above_128k_tokens: float | None = None
@@ -3728,6 +3738,7 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
     input_cost_per_token_above_200k_tokens_priority: float | None = None
     input_cost_per_token_above_272k_tokens_priority: float | None = None
     input_cost_per_token_above_272k_tokens_flex: float | None = None
+    input_cost_per_token_above_272k_tokens_batches: float | None = None
     input_cost_per_query: float | None = None
     input_cost_per_image: float | None = None
     input_cost_per_image_above_128k_tokens: float | None = None
@@ -3751,6 +3762,7 @@ class CustomPricingLiteLLMParams(MirroredPricingParams):
     output_cost_per_token_above_200k_tokens_priority: float | None = None
     output_cost_per_token_above_272k_tokens_priority: float | None = None
     output_cost_per_token_above_272k_tokens_flex: float | None = None
+    output_cost_per_token_above_272k_tokens_batches: float | None = None
     output_cost_per_character_above_128k_tokens: float | None = None
     output_cost_per_image: float | None = None
     output_cost_per_image_token: float | None = None
diff --git a/litellm/utils.py b/litellm/utils.py
index df2a6adbe1f..8ade6022e3e 100644
--- a/litellm/utils.py
+++ b/litellm/utils.py
@@ -6042,6 +6042,14 @@ def _get_model_info_helper(
                 cache_read_input_token_cost_flex=_model_info.get("cache_read_input_token_cost_flex", None),
                 cache_read_input_token_cost_priority=_model_info.get("cache_read_input_token_cost_priority", None),
                 cache_read_input_token_cost_ultrafast=_model_info.get("cache_read_input_token_cost_ultrafast", None),
+                cache_read_input_token_cost_batches=_model_info.get("cache_read_input_token_cost_batches"),
+                cache_read_input_token_cost_above_272k_tokens_batches=_model_info.get(
+                    "cache_read_input_token_cost_above_272k_tokens_batches"
+                ),
+                cache_creation_input_token_cost_batches=_model_info.get("cache_creation_input_token_cost_batches"),
+                cache_creation_input_token_cost_above_272k_tokens_batches=_model_info.get(
+                    "cache_creation_input_token_cost_above_272k_tokens_batches"
+                ),
                 cache_creation_input_token_cost_above_1hr=_model_info.get(
                     "cache_creation_input_token_cost_above_1hr", None
                 ),
@@ -6072,7 +6080,13 @@ def _get_model_info_helper(
                 input_cost_per_video_per_second=_model_info.get("input_cost_per_video_per_second", None),
                 input_cost_per_token_batches=_model_info.get("input_cost_per_token_batches"),
                 input_cost_per_video_token_batches=_model_info.get("input_cost_per_video_token_batches", None),
+                input_cost_per_token_above_272k_tokens_batches=_model_info.get(
+                    "input_cost_per_token_above_272k_tokens_batches"
+                ),
                 output_cost_per_token_batches=_model_info.get("output_cost_per_token_batches"),
+                output_cost_per_token_above_272k_tokens_batches=_model_info.get(
+                    "output_cost_per_token_above_272k_tokens_batches"
+                ),
                 output_cost_per_token=_output_cost_per_token,
                 output_cost_per_token_flex=_model_info.get("output_cost_per_token_flex", None),
                 output_cost_per_token_priority=_model_info.get("output_cost_per_token_priority", None),
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 468d86d049d..7cde9a1162e 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -34129,6 +34129,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 2e-06,
         "cache_read_input_token_cost_above_272k_tokens_flex": 1e-06,
         "cache_read_input_token_cost_above_272k_tokens_priority": 4e-06,
+        "cache_read_input_token_cost_batches": 5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 1e-06,
+        "cache_creation_input_token_cost_batches": 6.25e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 1.25e-05,
         "cache_read_input_token_cost_flex": 5e-07,
         "cache_read_input_token_cost_priority": 2e-06,
         "input_cost_per_token": 1e-05,
@@ -34136,6 +34140,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 1e-05,
         "input_cost_per_token_above_272k_tokens_priority": 4e-05,
         "input_cost_per_token_batches": 5e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 1e-05,
         "input_cost_per_token_flex": 5e-06,
         "input_cost_per_token_priority": 2e-05,
         "litellm_provider": "openai",
@@ -34148,6 +34153,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 3.75e-05,
         "output_cost_per_token_above_272k_tokens_priority": 0.00015,
         "output_cost_per_token_batches": 2.5e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 3.75e-05,
         "output_cost_per_token_flex": 2.5e-05,
         "output_cost_per_token_priority": 0.0001,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34199,6 +34205,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 8e-07,
         "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07,
         "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
+        "cache_read_input_token_cost_batches": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07,
+        "cache_creation_input_token_cost_batches": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 5e-06,
         "cache_read_input_token_cost_flex": 2e-07,
         "cache_read_input_token_cost_priority": 8e-07,
         "input_cost_per_token": 4e-06,
@@ -34206,6 +34216,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 4e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
         "input_cost_per_token_batches": 2e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 4e-06,
         "input_cost_per_token_flex": 2e-06,
         "input_cost_per_token_priority": 8e-06,
         "litellm_provider": "openai",
@@ -34218,6 +34229,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 1.5e-05,
         "output_cost_per_token_above_272k_tokens_priority": 6e-05,
         "output_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 1.5e-05,
         "output_cost_per_token_flex": 1e-05,
         "output_cost_per_token_priority": 4e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34266,6 +34278,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 8e-07,
         "cache_read_input_token_cost_above_272k_tokens_flex": 4e-07,
         "cache_read_input_token_cost_above_272k_tokens_priority": 1.6e-06,
+        "cache_read_input_token_cost_batches": 2e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 4e-07,
+        "cache_creation_input_token_cost_batches": 2.5e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 5e-06,
         "cache_read_input_token_cost_flex": 2e-07,
         "cache_read_input_token_cost_priority": 8e-07,
         "input_cost_per_token": 4e-06,
@@ -34273,6 +34289,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 4e-06,
         "input_cost_per_token_above_272k_tokens_priority": 1.6e-05,
         "input_cost_per_token_batches": 2e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 4e-06,
         "input_cost_per_token_flex": 2e-06,
         "input_cost_per_token_priority": 8e-06,
         "litellm_provider": "openai",
@@ -34285,6 +34302,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 1.5e-05,
         "output_cost_per_token_above_272k_tokens_priority": 6e-05,
         "output_cost_per_token_batches": 1e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 1.5e-05,
         "output_cost_per_token_flex": 1e-05,
         "output_cost_per_token_priority": 4e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34335,6 +34353,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 4e-07,
         "cache_read_input_token_cost_above_272k_tokens_flex": 2e-07,
         "cache_read_input_token_cost_above_272k_tokens_priority": 8e-07,
+        "cache_read_input_token_cost_batches": 1e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 2e-07,
+        "cache_creation_input_token_cost_batches": 1.25e-06,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-06,
         "cache_read_input_token_cost_flex": 1e-07,
         "cache_read_input_token_cost_priority": 4e-07,
         "input_cost_per_token": 2e-06,
@@ -34342,6 +34364,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 2e-06,
         "input_cost_per_token_above_272k_tokens_priority": 8e-06,
         "input_cost_per_token_batches": 1e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 2e-06,
         "input_cost_per_token_flex": 1e-06,
         "input_cost_per_token_priority": 4e-06,
         "litellm_provider": "openai",
@@ -34354,6 +34377,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 9e-06,
         "output_cost_per_token_above_272k_tokens_priority": 3.6e-05,
         "output_cost_per_token_batches": 6e-06,
+        "output_cost_per_token_above_272k_tokens_batches": 9e-06,
         "output_cost_per_token_flex": 6e-06,
         "output_cost_per_token_priority": 2.4e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34403,6 +34427,10 @@
         "cache_read_input_token_cost_above_272k_tokens": 4e-08,
         "cache_read_input_token_cost_above_272k_tokens_flex": 2e-08,
         "cache_read_input_token_cost_above_272k_tokens_priority": 8e-08,
+        "cache_read_input_token_cost_batches": 1e-08,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 2e-08,
+        "cache_creation_input_token_cost_batches": 1.25e-07,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 2.5e-07,
         "cache_read_input_token_cost_flex": 1e-08,
         "cache_read_input_token_cost_priority": 4e-08,
         "input_cost_per_token": 2e-07,
@@ -34410,6 +34438,7 @@
         "input_cost_per_token_above_272k_tokens_flex": 2e-07,
         "input_cost_per_token_above_272k_tokens_priority": 8e-07,
         "input_cost_per_token_batches": 1e-07,
+        "input_cost_per_token_above_272k_tokens_batches": 2e-07,
         "input_cost_per_token_flex": 1e-07,
         "input_cost_per_token_priority": 4e-07,
         "litellm_provider": "openai",
@@ -34422,6 +34451,7 @@
         "output_cost_per_token_above_272k_tokens_flex": 9e-07,
         "output_cost_per_token_above_272k_tokens_priority": 3.6e-06,
         "output_cost_per_token_batches": 6e-07,
+        "output_cost_per_token_above_272k_tokens_batches": 9e-07,
         "output_cost_per_token_flex": 6e-07,
         "output_cost_per_token_priority": 2.4e-06,
         "regional_processing_uplift_multiplier_eu": 1.1,
@@ -34692,12 +34722,15 @@
     "gpt-5.5": {
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+        "cache_read_input_token_cost_batches": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
         "cache_read_input_token_cost_flex": 2.5e-07,
         "cache_read_input_token_cost_priority": 1.25e-06,
         "input_cost_per_token": 5e-06,
         "input_cost_per_token_above_272k_tokens": 1e-05,
         "input_cost_per_token_flex": 2.5e-06,
         "input_cost_per_token_batches": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 5e-06,
         "input_cost_per_token_priority": 1.25e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
@@ -34708,6 +34741,7 @@
         "output_cost_per_token_above_272k_tokens": 4.5e-05,
         "output_cost_per_token_flex": 1.5e-05,
         "output_cost_per_token_batches": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 2.25e-05,
         "output_cost_per_token_priority": 7.5e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
@@ -34750,12 +34784,15 @@
     "gpt-5.5-2026-04-23": {
         "cache_read_input_token_cost": 5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 1e-06,
+        "cache_read_input_token_cost_batches": 2.5e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 5e-07,
         "cache_read_input_token_cost_flex": 2.5e-07,
         "cache_read_input_token_cost_priority": 1.25e-06,
         "input_cost_per_token": 5e-06,
         "input_cost_per_token_above_272k_tokens": 1e-05,
         "input_cost_per_token_flex": 2.5e-06,
         "input_cost_per_token_batches": 2.5e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 5e-06,
         "input_cost_per_token_priority": 1.25e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
@@ -34766,6 +34803,7 @@
         "output_cost_per_token_above_272k_tokens": 4.5e-05,
         "output_cost_per_token_flex": 1.5e-05,
         "output_cost_per_token_batches": 1.5e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 2.25e-05,
         "output_cost_per_token_priority": 7.5e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
@@ -34810,6 +34848,7 @@
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_above_272k_tokens_batches": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -34819,6 +34858,7 @@
         "output_cost_per_token_above_272k_tokens": 0.00027,
         "output_cost_per_token_flex": 9e-05,
         "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 0.000135,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
@@ -34859,6 +34899,7 @@
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_above_272k_tokens_batches": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -34868,6 +34909,7 @@
         "output_cost_per_token_above_272k_tokens": 0.00027,
         "output_cost_per_token_flex": 9e-05,
         "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 0.000135,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
@@ -34906,12 +34948,15 @@
     "gpt-5.4": {
         "cache_read_input_token_cost": 2.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_batches": 1.25e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07,
         "cache_read_input_token_cost_flex": 1.3e-07,
         "cache_read_input_token_cost_priority": 5e-07,
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_above_272k_tokens": 5e-06,
         "input_cost_per_token_flex": 1.25e-06,
         "input_cost_per_token_batches": 1.25e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 2.5e-06,
         "input_cost_per_token_priority": 5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
@@ -34922,6 +34967,7 @@
         "output_cost_per_token_above_272k_tokens": 2.25e-05,
         "output_cost_per_token_flex": 7.5e-06,
         "output_cost_per_token_batches": 7.5e-06,
+        "output_cost_per_token_above_272k_tokens_batches": 1.125e-05,
         "output_cost_per_token_priority": 3e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
@@ -34959,12 +35005,15 @@
     "gpt-5.4-2026-03-05": {
         "cache_read_input_token_cost": 2.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 5e-07,
+        "cache_read_input_token_cost_batches": 1.25e-07,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 2.5e-07,
         "cache_read_input_token_cost_flex": 1.3e-07,
         "cache_read_input_token_cost_priority": 5e-07,
         "input_cost_per_token": 2.5e-06,
         "input_cost_per_token_above_272k_tokens": 5e-06,
         "input_cost_per_token_flex": 1.25e-06,
         "input_cost_per_token_batches": 1.25e-06,
+        "input_cost_per_token_above_272k_tokens_batches": 2.5e-06,
         "input_cost_per_token_priority": 5e-06,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
@@ -34975,6 +35024,7 @@
         "output_cost_per_token_above_272k_tokens": 2.25e-05,
         "output_cost_per_token_flex": 7.5e-06,
         "output_cost_per_token_batches": 7.5e-06,
+        "output_cost_per_token_above_272k_tokens_batches": 1.125e-05,
         "output_cost_per_token_priority": 3e-05,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
@@ -35014,6 +35064,7 @@
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_above_272k_tokens_batches": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -35023,6 +35074,7 @@
         "output_cost_per_token_above_272k_tokens": 0.00027,
         "output_cost_per_token_flex": 9e-05,
         "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 0.000135,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
@@ -35064,6 +35116,7 @@
         "input_cost_per_token_above_272k_tokens": 6e-05,
         "input_cost_per_token_flex": 1.5e-05,
         "input_cost_per_token_batches": 1.5e-05,
+        "input_cost_per_token_above_272k_tokens_batches": 3e-05,
         "litellm_provider": "openai",
         "max_input_tokens": 1050000,
         "max_output_tokens": 128000,
@@ -35073,6 +35126,7 @@
         "output_cost_per_token_above_272k_tokens": 0.00027,
         "output_cost_per_token_flex": 9e-05,
         "output_cost_per_token_batches": 9e-05,
+        "output_cost_per_token_above_272k_tokens_batches": 0.000135,
         "regional_processing_uplift_multiplier_eu": 1.1,
         "regional_processing_uplift_multiplier_us": 1.1,
         "search_context_cost_per_query": {
diff --git a/model_prices_and_context_window.schema.json b/model_prices_and_context_window.schema.json
index 16b762f7803..737a9b7fa60 100644
--- a/model_prices_and_context_window.schema.json
+++ b/model_prices_and_context_window.schema.json
@@ -113,6 +113,11 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "cache_creation_input_token_cost_above_272k_tokens_batches": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "cache_creation_input_token_cost_above_272k_tokens_flex": {
           "type": "number",
           "minimum": 0,
@@ -123,6 +128,10 @@
           "minimum": 0,
           "description": "Priority service-tier rate for the same-named base field."
         },
+        "cache_creation_input_token_cost_batches": {
+          "type": "number",
+          "minimum": 0
+        },
         "cache_creation_input_token_cost_flex": {
           "type": "number",
           "minimum": 0,
@@ -171,6 +180,11 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "cache_read_input_token_cost_above_272k_tokens_batches": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "cache_read_input_token_cost_above_272k_tokens_flex": {
           "type": "number",
           "minimum": 0,
@@ -186,6 +200,10 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "cache_read_input_token_cost_batches": {
+          "type": "number",
+          "minimum": 0
+        },
         "cache_read_input_token_cost_flex": {
           "type": "number",
           "minimum": 0,
@@ -338,6 +356,11 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "input_cost_per_token_above_272k_tokens_batches": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "input_cost_per_token_above_272k_tokens_flex": {
           "type": "number",
           "minimum": 0,
@@ -669,6 +692,11 @@
           "minimum": 0,
           "description": "Rate applied once the prompt exceeds the token threshold in the field name."
         },
+        "output_cost_per_token_above_272k_tokens_batches": {
+          "type": "number",
+          "minimum": 0,
+          "description": "Rate applied once the prompt exceeds the token threshold in the field name."
+        },
         "output_cost_per_token_above_272k_tokens_flex": {
           "type": "number",
           "minimum": 0,
diff --git a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
index 4fe3d410ef8..4b25c87d70f 100644
--- a/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
+++ b/tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py
@@ -1,5 +1,6 @@
 from collections.abc import Mapping
 from datetime import datetime, timezone
+from typing import cast
 
 import pytest
 
@@ -3634,3 +3635,147 @@ def test_get_token_base_cost_resolves_missing_cache_write_rates_like_the_tiered_
 
     assert creation == pytest.approx(expected_creation)
     assert creation_1h == pytest.approx(expected_creation_1h)
+
+
+def _batch_rates_model_info(**rates: object) -> ModelInfo:
+    return cast(ModelInfo, dict(rates))
+
+
+def test_get_batch_cost_rates_parses_string_rates():
+    from litellm.litellm_core_utils.llm_cost_calc.utils import get_batch_cost_rates
+
+    rates = get_batch_cost_rates(
+        _batch_rates_model_info(
+            input_cost_per_token_batches="1e-06",
+            output_cost_per_token_batches="4e-06",
+            cache_read_input_token_cost_batches="1e-07",
+            input_cost_per_token_above_272k_tokens_batches="2e-06",
+            output_cost_per_token_above_272k_tokens_batches="6e-06",
+            cache_read_input_token_cost_above_272k_tokens_batches="2e-07",
+        ),
+        Usage(prompt_tokens=300_000, completion_tokens=1, total_tokens=300_001),
+        "openai",
+    )
+
+    assert (rates.input, rates.output, rates.cache_read) == (2e-6, 6e-6, 2e-7)
+
+
+def test_get_batch_cost_rates_falls_back_to_the_flat_rates_when_tier_rates_are_unparsable():
+    from litellm.litellm_core_utils.llm_cost_calc.utils import get_batch_cost_rates
+
+    rates = get_batch_cost_rates(
+        _batch_rates_model_info(
+            input_cost_per_token_batches=1e-6,
+            output_cost_per_token_batches=4e-6,
+            cache_read_input_token_cost_batches=1e-7,
+            input_cost_per_token_above_272k_tokens_batches="two",
+            output_cost_per_token_above_272k_tokens_batches="six",
+            cache_read_input_token_cost_above_272k_tokens_batches="none",
+            cache_creation_input_token_cost_batches=1.25e-7,
+            cache_creation_input_token_cost_above_272k_tokens_batches="nope",
+        ),
+        Usage(prompt_tokens=300_000, completion_tokens=1, total_tokens=300_001),
+        "openai",
+    )
+
+    assert (rates.input, rates.output, rates.cache_read, rates.cache_creation) == (1e-6, 4e-6, 1e-7, 1.25e-7)
+
+
+def test_get_batch_cost_rates_has_no_cached_rate_without_a_cached_batch_key():
+    from litellm.litellm_core_utils.llm_cost_calc.utils import get_batch_cost_rates
+
+    rates = get_batch_cost_rates(
+        _batch_rates_model_info(
+            input_cost_per_token_batches=1e-6,
+            output_cost_per_token_batches=4e-6,
+            cache_read_input_token_cost=2e-7,
+            input_cost_per_token_above_272k_tokens_batches=2e-6,
+        ),
+        Usage(prompt_tokens=300_000, completion_tokens=1, total_tokens=300_001),
+        "openai",
+    )
+
+    assert (rates.input, rates.output, rates.cache_read) == (2e-6, 4e-6, None)
+
+
+@pytest.mark.parametrize(("prompt_tokens", "expected"), [(1_000, 1.25e-7), (272_000, 1.25e-7), (300_000, 2.5e-7)])
+def test_get_batch_cost_rates_reads_the_batch_cache_write_rate_for_the_crossed_tier(prompt_tokens, expected):
+    from litellm.litellm_core_utils.llm_cost_calc.utils import get_batch_cost_rates
+
+    rates = get_batch_cost_rates(
+        _batch_rates_model_info(
+            input_cost_per_token_batches=1e-7,
+            input_cost_per_token_above_272k_tokens_batches=2e-7,
+            cache_creation_input_token_cost_batches=1.25e-7,
+            cache_creation_input_token_cost_above_272k_tokens_batches=2.5e-7,
+        ),
+        Usage(prompt_tokens=prompt_tokens, completion_tokens=1, total_tokens=prompt_tokens + 1),
+        "openai",
+    )
+
+    assert rates.cache_creation == expected
+
+
+@pytest.mark.parametrize(
+    ("tier_key", "attribute"),
+    [
+        ("output_cost_per_token_above_272k_tokens_batches", "output"),
+        ("cache_read_input_token_cost_above_272k_tokens_batches", "cache_read"),
+        ("cache_creation_input_token_cost_above_272k_tokens_batches", "cache_creation"),
+    ],
+)
+def test_get_batch_cost_rates_crosses_a_tier_declared_without_an_input_tier_key(tier_key, attribute):
+    from litellm.litellm_core_utils.llm_cost_calc.utils import get_batch_cost_rates
+
+    rates = get_batch_cost_rates(
+        _batch_rates_model_info(
+            input_cost_per_token_batches=1e-6,
+            output_cost_per_token_batches=4e-6,
+            cache_read_input_token_cost_batches=1e-7,
+            cache_creation_input_token_cost_batches=1.25e-7,
+            **{tier_key: 9e-6},
+        ),
+        Usage(prompt_tokens=300_000, completion_tokens=1, total_tokens=300_001),
+        "openai",
+    )
+
+    assert getattr(rates, attribute) == 9e-6
+    assert rates.input == 1e-6
+
+
+@pytest.mark.parametrize(
+    ("prompt_tokens", "expected_input", "expected_output"),
+    [(200_000, 1e-6, 4e-6), (250_000, 1e-6, 5e-6), (300_000, 2e-6, 5e-6)],
+)
+def test_get_batch_cost_rates_crosses_each_components_own_tier(prompt_tokens, expected_input, expected_output):
+    from litellm.litellm_core_utils.llm_cost_calc.utils import get_batch_cost_rates
+
+    rates = get_batch_cost_rates(
+        _batch_rates_model_info(
+            input_cost_per_token_batches=1e-6,
+            input_cost_per_token_above_272k_tokens_batches=2e-6,
+            output_cost_per_token_batches=4e-6,
+            output_cost_per_token_above_200k_tokens_batches=5e-6,
+        ),
+        Usage(prompt_tokens=prompt_tokens, completion_tokens=1, total_tokens=prompt_tokens + 1),
+        "openai",
+    )
+
+    assert (rates.input, rates.output) == (expected_input, expected_output)
+
+
+def test_get_batch_cost_rates_has_no_cache_write_rate_without_a_cache_write_batch_key():
+    from litellm.litellm_core_utils.llm_cost_calc.utils import get_batch_cost_rates
+
+    rates = get_batch_cost_rates(
+        _batch_rates_model_info(
+            input_cost_per_token_batches=1e-7,
+            input_cost_per_token_above_272k_tokens_batches=2e-7,
+            cache_creation_input_token_cost=2.5e-7,
+            cache_creation_input_token_cost_above_272k_tokens=5e-7,
+        ),
+        Usage(prompt_tokens=300_000, completion_tokens=1, total_tokens=300_001),
+        "openai",
+    )
+
+    assert rates.cache_creation is None
diff --git a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py
index 52eed9c9f95..b0fc725b50a 100644
--- a/tests/test_litellm/litellm_core_utils/test_litellm_logging.py
+++ b/tests/test_litellm/litellm_core_utils/test_litellm_logging.py
@@ -6,6 +6,7 @@ import logging
 import os
 import sys
 from collections.abc import Callable, Iterator, Mapping
+from types import MappingProxyType
 from typing import Final, Literal
 from unittest.mock import AsyncMock, MagicMock, patch
 
@@ -7478,6 +7479,141 @@ def test_passthrough_embeddings_result_swapped_for_callbacks():
     assert swapped_result.data[0]["embedding"] == [0.1, 0.2, 0.3]
 
 
+_PUBLISHED_BATCH_MODEL: Final = "lit-published-batch-tier-model"
+_PUBLISHED_BATCH_DEPLOYMENT: Final = f"openai/{_PUBLISHED_BATCH_MODEL}"
+_PUBLISHED_BATCH_RATES: Final = MappingProxyType(
+    {
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "input_cost_per_token": 2e-6,
+        "output_cost_per_token": 8e-6,
+        "input_cost_per_token_batches": 1.1e-6,
+        "output_cost_per_token_batches": 4.1e-6,
+        "cache_read_input_token_cost_batches": 1.2e-7,
+        "cache_creation_input_token_cost_batches": 1.3e-6,
+        "input_cost_per_token_above_272k_tokens_batches": 3.1e-6,
+        "output_cost_per_token_above_272k_tokens_batches": 7.1e-6,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 3.2e-7,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 3.3e-6,
+    }
+)
+_PUBLISHED_INPUT_BATCH_KEYS: Final = (
+    "input_cost_per_token_batches",
+    "input_cost_per_token_above_272k_tokens_batches",
+    "cache_read_input_token_cost_batches",
+    "cache_read_input_token_cost_above_272k_tokens_batches",
+    "cache_creation_input_token_cost_batches",
+    "cache_creation_input_token_cost_above_272k_tokens_batches",
+)
+_PUBLISHED_OUTPUT_BATCH_KEYS: Final = (
+    "output_cost_per_token_batches",
+    "output_cost_per_token_above_272k_tokens_batches",
+)
+
+
+@pytest.fixture
+def _published_batch_model(monkeypatch: pytest.MonkeyPatch) -> None:
+    monkeypatch.setenv("LITELLM_LOCAL_MODEL_COST_MAP", "True")
+    monkeypatch.setattr(litellm, "model_cost", litellm.get_model_cost_map(url=""))
+    litellm.register_model(
+        model_cost={_PUBLISHED_BATCH_MODEL: {**_PUBLISHED_BATCH_RATES}}, persist_across_reloads=False
+    )
+
+
+def _batch_deployment_id(custom_pricing: dict[str, float]) -> str:
+    from litellm import Router
+
+    router: Final = Router(
+        model_list=[
+            {
+                "model_name": "published-batch",
+                "litellm_params": {"model": _PUBLISHED_BATCH_DEPLOYMENT, "api_key": "sk-test", **custom_pricing},
+            }
+        ]
+    )
+    return router.model_list[0]["model_info"]["id"]
+
+
+def test_deployment_pricing_model_info_carries_every_published_input_batch_rate_when_only_output_is_declared(
+    _published_batch_model: None,
+) -> None:
+    from litellm.litellm_core_utils.litellm_logging import deployment_pricing_model_info
+
+    info: Final = deployment_pricing_model_info(
+        _batch_deployment_id({"output_cost_per_token_batches": 4e-6}), _PUBLISHED_BATCH_DEPLOYMENT
+    )
+
+    assert info is not None
+    assert {key: info[key] for key in _PUBLISHED_INPUT_BATCH_KEYS} == {
+        key: _PUBLISHED_BATCH_RATES[key] for key in _PUBLISHED_INPUT_BATCH_KEYS
+    }
+    assert info["output_cost_per_token_batches"] == 4e-6
+    assert info["output_cost_per_token_above_272k_tokens_batches"] is None
+
+
+def test_deployment_pricing_model_info_carries_the_published_output_batch_tier_when_only_input_is_declared(
+    _published_batch_model: None,
+) -> None:
+    from litellm.litellm_core_utils.litellm_logging import deployment_pricing_model_info
+
+    info: Final = deployment_pricing_model_info(
+        _batch_deployment_id({"input_cost_per_token_batches": 1e-6}), _PUBLISHED_BATCH_DEPLOYMENT
+    )
+
+    assert info is not None
+    assert {key: info[key] for key in _PUBLISHED_OUTPUT_BATCH_KEYS} == {
+        key: _PUBLISHED_BATCH_RATES[key] for key in _PUBLISHED_OUTPUT_BATCH_KEYS
+    }
+    assert info["input_cost_per_token_batches"] == 1e-6
+    assert info["input_cost_per_token_above_272k_tokens_batches"] is None
+    assert info["cache_read_input_token_cost_batches"] is None
+    assert info["cache_creation_input_token_cost_batches"] is None
+
+
+def test_batch_cost_calculator_bills_the_carried_output_tier_when_the_deployment_declares_its_own_input_rate(
+    _published_batch_model: None,
+) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+    from litellm.litellm_core_utils.litellm_logging import deployment_pricing_model_info
+    from litellm.types.utils import Usage
+
+    info: Final = deployment_pricing_model_info(
+        _batch_deployment_id({"input_cost_per_token": 5e-6}), _PUBLISHED_BATCH_DEPLOYMENT
+    )
+    assert info is not None
+
+    prompt_cost, completion_cost = batch_cost_calculator(
+        usage=Usage(prompt_tokens=300_000, completion_tokens=10, total_tokens=300_010),
+        model=_PUBLISHED_BATCH_DEPLOYMENT,
+        custom_llm_provider="openai",
+        model_info=info,
+    )
+
+    assert prompt_cost == pytest.approx(300_000 * 5e-6 / 2)
+    assert completion_cost == pytest.approx(
+        10 * _PUBLISHED_BATCH_RATES["output_cost_per_token_above_272k_tokens_batches"]
+    )
+
+
+def test_deployment_pricing_model_info_honors_a_tier_only_batch_override_over_the_published_flat_rates(
+    _published_batch_model: None,
+) -> None:
+    from litellm.litellm_core_utils.litellm_logging import deployment_pricing_model_info
+
+    info: Final = deployment_pricing_model_info(
+        _batch_deployment_id({"input_cost_per_token_above_272k_tokens_batches": 1e-3}), _PUBLISHED_BATCH_DEPLOYMENT
+    )
+    carried_keys: Final = tuple(
+        key
+        for key in (*_PUBLISHED_INPUT_BATCH_KEYS, *_PUBLISHED_OUTPUT_BATCH_KEYS)
+        if key != "input_cost_per_token_above_272k_tokens_batches"
+    )
+
+    assert info is not None
+    assert info["input_cost_per_token_above_272k_tokens_batches"] == 1e-3
+    assert {key: info[key] for key in carried_keys} == {key: _PUBLISHED_BATCH_RATES[key] for key in carried_keys}
+
+
 def test_get_status_fields_ranks_guardrail_flagged_between_success_and_intervened():
     """LIT-6894: a non-blocking flagged verdict must outrank success in the
     request-level guardrail_status but never mask an intervention."""
diff --git a/tests/test_litellm/test_cost_calculator.py b/tests/test_litellm/test_cost_calculator.py
index bdeedb5f38c..a33701cd1bf 100644
--- a/tests/test_litellm/test_cost_calculator.py
+++ b/tests/test_litellm/test_cost_calculator.py
@@ -1,6 +1,7 @@
 import datetime
 import time
-from typing import Final
+from types import MappingProxyType
+from typing import Final, cast
 
 import pytest
 from pydantic import BaseModel
@@ -4464,6 +4465,273 @@ def test_completion_cost_prices_responses_websocket_turns_per_service_tier():
     assert ws_cost != pytest.approx(_http_cost(160, 50, "priority"))
 
 
+_TIERED_BATCH_MODEL: Final = "lit-tiered-batch-model"
+_FLAT_CACHE_BATCH_MODEL: Final = "lit-tiered-batch-model-without-cache-batch-rates"
+_TIERED_BATCH_ENTRY: Final = MappingProxyType(
+    {
+        "litellm_provider": "openai",
+        "mode": "chat",
+        "input_cost_per_token": 2e-6,
+        "output_cost_per_token": 8e-6,
+        "cache_read_input_token_cost": 2e-7,
+        "cache_creation_input_token_cost": 2.5e-6,
+        "input_cost_per_token_above_272k_tokens": 4e-6,
+        "output_cost_per_token_above_272k_tokens": 1.2e-5,
+        "input_cost_per_token_batches": 1e-6,
+        "output_cost_per_token_batches": 4e-6,
+        "cache_read_input_token_cost_batches": 1e-7,
+        "cache_creation_input_token_cost_batches": 1.25e-6,
+        "input_cost_per_token_above_272k_tokens_batches": 3e-6,
+        "output_cost_per_token_above_272k_tokens_batches": 7e-6,
+        "cache_read_input_token_cost_above_272k_tokens_batches": 3e-7,
+        "cache_creation_input_token_cost_above_272k_tokens_batches": 3.75e-6,
+    }
+)
+_BATCH_RATE_PREFIXES: Final = (
+    "input_cost_per_token",
+    "output_cost_per_token",
+    "cache_read_input_token_cost",
+    "cache_creation_input_token_cost",
+)
+
+
+@pytest.fixture
+def _tiered_batch_models(_local_model_cost_map: None) -> None:
+    litellm.register_model(
+        model_cost={
+            _TIERED_BATCH_MODEL: {**_TIERED_BATCH_ENTRY},
+            _FLAT_CACHE_BATCH_MODEL: {
+                key: rate
+                for key, rate in _TIERED_BATCH_ENTRY.items()
+                if not (key.startswith("cache_") and key.endswith("_batches"))
+            },
+        },
+        persist_across_reloads=False,
+    )
+
+
+def test_batch_cost_calculator_bills_the_long_context_batch_tier_above_272k(_tiered_batch_models: None) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    usage: Final = Usage(prompt_tokens=300_035, completion_tokens=64, total_tokens=300_099)
+
+    prompt_cost, completion_cost_value = batch_cost_calculator(
+        usage=usage, model=_TIERED_BATCH_MODEL, custom_llm_provider="openai"
+    )
+
+    assert prompt_cost == pytest.approx(300_035 * 3e-6)
+    assert completion_cost_value == pytest.approx(64 * 7e-6)
+
+
+@pytest.mark.parametrize("prompt_tokens", [272_000, 1_000])
+def test_batch_cost_calculator_bills_the_flat_batch_rate_at_or_below_272k(
+    _tiered_batch_models: None, prompt_tokens: int
+) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    usage: Final = Usage(prompt_tokens=prompt_tokens, completion_tokens=64, total_tokens=prompt_tokens + 64)
+
+    prompt_cost, completion_cost_value = batch_cost_calculator(
+        usage=usage, model=_TIERED_BATCH_MODEL, custom_llm_provider="openai"
+    )
+
+    assert prompt_cost == pytest.approx(prompt_tokens * 1e-6)
+    assert completion_cost_value == pytest.approx(64 * 4e-6)
+
+
+def test_get_model_info_exposes_every_registered_batch_rate(_tiered_batch_models: None) -> None:
+    info: Final = litellm.get_model_info(_TIERED_BATCH_MODEL, custom_llm_provider="openai")
+    batch_keys: Final = tuple(key for key in _TIERED_BATCH_ENTRY if key.endswith("_batches"))
+
+    assert len(batch_keys) == 8
+    assert {key: info[key] for key in batch_keys} == {key: _TIERED_BATCH_ENTRY[key] for key in batch_keys}
+
+
+def test_regular_path_never_bills_the_batch_tier_keys(_local_model_cost_map, monkeypatch):
+    monkeypatch.setitem(
+        litellm.model_cost,
+        "lit-batch-tier-guard",
+        {
+            "litellm_provider": "openai",
+            "mode": "chat",
+            "input_cost_per_token": 2e-6,
+            "output_cost_per_token": 8e-6,
+            "input_cost_per_token_batches": 1e-6,
+            "output_cost_per_token_batches": 4e-6,
+            "input_cost_per_token_above_272k_tokens_batches": 5e-6,
+            "output_cost_per_token_above_272k_tokens_batches": 9e-6,
+        },
+    )
+
+    prompt_cost, completion_cost = litellm.cost_per_token(
+        model="lit-batch-tier-guard", custom_llm_provider="openai", prompt_tokens=300_035, completion_tokens=64
+    )
+
+    assert prompt_cost == pytest.approx(300_035 * 2e-6)
+    assert completion_cost == pytest.approx(64 * 8e-6)
+
+
+@pytest.mark.parametrize("prefix", _BATCH_RATE_PREFIXES)
+def test_every_openai_entry_with_a_long_context_rate_and_a_batch_rate_declares_the_batch_tier(
+    _local_model_cost_map: None, prefix: str
+) -> None:
+    undeclared: Final = [
+        name
+        for name, entry in litellm.model_cost.items()
+        if isinstance(entry, dict)
+        and entry.get("litellm_provider") == "openai"
+        and entry.get(f"{prefix}_above_272k_tokens") is not None
+        and entry.get(f"{prefix}_batches") is not None
+        and entry.get(f"{prefix}_above_272k_tokens_batches") is None
+    ]
+
+    assert undeclared == []
+
+
+def test_batch_cost_calculator_ignores_malformed_batch_tier_keys():
+    from litellm.cost_calculator import batch_cost_calculator
+
+    usage = Usage(prompt_tokens=300_035, completion_tokens=64, total_tokens=300_099)
+    model_info = cast(
+        ModelInfo,
+        {
+            "input_cost_per_token": 2e-6,
+            "output_cost_per_token": 8e-6,
+            "input_cost_per_token_batches": 1e-6,
+            "output_cost_per_token_batches": 4e-6,
+            "input_cost_per_token_above_272k_tokens_batches": 2e-6,
+            "output_cost_per_token_above_272k_tokens_batches": 6e-6,
+            "input_cost_per_token_above_lots_tokens_batches": 1.0,
+        },
+    )
+
+    prompt_cost, completion_cost = batch_cost_calculator(
+        usage=usage, model=_TIERED_BATCH_MODEL, custom_llm_provider="openai", model_info=model_info
+    )
+
+    assert prompt_cost == pytest.approx(300_035 * 2e-6)
+    assert completion_cost == pytest.approx(64 * 6e-6)
+
+
+def _cached_usage(prompt_tokens: int, cached_tokens: int, completion_tokens: int) -> Usage:
+    return Usage(
+        prompt_tokens=prompt_tokens,
+        completion_tokens=completion_tokens,
+        total_tokens=prompt_tokens + completion_tokens,
+        prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens),
+    )
+
+
+def test_batch_cost_calculator_bills_cached_tokens_at_the_long_context_batch_cached_rate(
+    _tiered_batch_models: None,
+) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    prompt_cost, completion_cost_value = batch_cost_calculator(
+        usage=_cached_usage(300_048, 300_045, 11), model=_TIERED_BATCH_MODEL, custom_llm_provider="openai"
+    )
+
+    assert prompt_cost == pytest.approx(3 * 3e-6 + 300_045 * 3e-7)
+    assert completion_cost_value == pytest.approx(11 * 7e-6)
+
+
+def test_batch_cost_calculator_bills_cached_tokens_at_the_flat_batch_cached_rate_at_or_below_272k(
+    _tiered_batch_models: None,
+) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    prompt_cost, _ = batch_cost_calculator(
+        usage=_cached_usage(1_000, 900, 4), model=_TIERED_BATCH_MODEL, custom_llm_provider="openai"
+    )
+
+    assert prompt_cost == pytest.approx(100 * 1e-6 + 900 * 1e-7)
+
+
+def test_batch_cost_calculator_bills_cached_tokens_at_the_batch_input_rate_without_a_cached_batch_rate(
+    _tiered_batch_models: None,
+) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    prompt_cost, _ = batch_cost_calculator(
+        usage=_cached_usage(300_048, 300_045, 11), model=_FLAT_CACHE_BATCH_MODEL, custom_llm_provider="openai"
+    )
+
+    assert prompt_cost == pytest.approx(300_048 * 3e-6)
+
+
+def _cache_write_usage(prompt_tokens: int, cache_write_tokens: int, completion_tokens: int) -> Usage:
+    return Usage(
+        prompt_tokens=prompt_tokens,
+        completion_tokens=completion_tokens,
+        total_tokens=prompt_tokens + completion_tokens,
+        prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=0, cache_write_tokens=cache_write_tokens),
+    )
+
+
+def test_batch_cost_calculator_bills_cache_write_tokens_at_the_long_context_batch_cache_write_rate(
+    _tiered_batch_models: None,
+) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    prompt_cost, completion_cost_value = batch_cost_calculator(
+        usage=_cache_write_usage(300_048, 300_045, 4), model=_TIERED_BATCH_MODEL, custom_llm_provider="openai"
+    )
+
+    assert prompt_cost == pytest.approx(3 * 3e-6 + 300_045 * 3.75e-6)
+    assert completion_cost_value == pytest.approx(4 * 7e-6)
+
+
+def test_batch_cost_calculator_bills_cache_write_tokens_at_the_flat_batch_cache_write_rate_at_or_below_272k(
+    _tiered_batch_models: None,
+) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    prompt_cost, _ = batch_cost_calculator(
+        usage=_cache_write_usage(1_000, 900, 4), model=_TIERED_BATCH_MODEL, custom_llm_provider="openai"
+    )
+
+    assert prompt_cost == pytest.approx(100 * 1e-6 + 900 * 1.25e-6)
+
+
+def test_batch_cost_calculator_bills_cache_write_tokens_at_the_batch_input_rate_without_a_cache_write_batch_rate(
+    _tiered_batch_models: None,
+) -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    prompt_cost, _ = batch_cost_calculator(
+        usage=_cache_write_usage(300_048, 300_045, 4), model=_FLAT_CACHE_BATCH_MODEL, custom_llm_provider="openai"
+    )
+
+    assert prompt_cost == pytest.approx(300_048 * 3e-6)
+
+
+def test_batch_cost_calculator_prices_modalities_and_cached_tokens_together_in_the_crossed_tier() -> None:
+    from litellm.cost_calculator import batch_cost_calculator
+
+    model_info: Final = cast(
+        ModelInfo,
+        {
+            "input_cost_per_token_batches": 1e-6,
+            "input_cost_per_token_above_272k_tokens_batches": 3e-6,
+            "input_cost_per_audio_token_batches": 5e-6,
+            "cache_read_input_token_cost_batches": 1e-7,
+            "cache_read_input_token_cost_above_272k_tokens_batches": 3e-7,
+        },
+    )
+    usage: Final = Usage(
+        prompt_tokens=300_000,
+        completion_tokens=0,
+        total_tokens=300_000,
+        prompt_tokens_details=PromptTokensDetailsWrapper(audio_tokens=64, image_tokens=10, cached_tokens=1_000),
+    )
+
+    prompt_cost, _ = batch_cost_calculator(
+        usage=usage, model=_TIERED_BATCH_MODEL, custom_llm_provider="openai", model_info=model_info
+    )
+
+    assert prompt_cost == pytest.approx(298_926 * 3e-6 + 64 * 5e-6 + 10 * 3e-6 + 1_000 * 3e-7)
+
+
 QWEN3_NEXT_REGIONS: Final = ("ap-northeast-1", "ap-south-1", "ap-southeast-2", "eu-west-1", "eu-west-2", "sa-east-1")
 
 
diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py
index 38aad3ace1c..96c420299e7 100644
--- a/tests/test_litellm/test_utils.py
+++ b/tests/test_litellm/test_utils.py
@@ -740,6 +740,8 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "cache_creation_input_token_cost_above_272k_tokens": {"type": "number"},
                 "cache_creation_input_token_cost_above_272k_tokens_flex": {"type": "number"},
                 "cache_creation_input_token_cost_above_272k_tokens_priority": {"type": "number"},
+                "cache_creation_input_token_cost_above_272k_tokens_batches": {"type": "number"},
+                "cache_creation_input_token_cost_batches": {"type": "number"},
                 "cache_creation_input_token_cost_flex": {"type": "number"},
                 "cache_creation_input_token_cost_priority": {"type": "number"},
                 "cache_read_input_token_cost": {"type": "number"},
@@ -749,6 +751,8 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "cache_read_input_token_cost_above_272k_tokens": {"type": "number"},
                 "cache_read_input_token_cost_above_272k_tokens_flex": {"type": "number"},
                 "cache_read_input_token_cost_above_512k_tokens": {"type": "number"},
+                "cache_read_input_token_cost_batches": {"type": "number"},
+                "cache_read_input_token_cost_above_272k_tokens_batches": {"type": "number"},
                 "cache_creation_input_token_cost_above_1hr_above_200k_tokens": {"type": "number"},
                 "cache_read_input_audio_token_cost": {"type": "number"},
                 "cache_read_input_image_token_cost": {"type": "number"},
@@ -776,12 +780,14 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "input_cost_per_token_priority": {"type": "number"},
                 "input_cost_per_token_above_200k_tokens_priority": {"type": "number"},
                 "input_cost_per_token_above_272k_tokens_priority": {"type": "number"},
+                "input_cost_per_token_above_272k_tokens_batches": {"type": "number"},
                 "input_cost_per_token_above_272k_tokens_flex": {"type": "number"},
                 "input_cost_per_audio_token_priority": {"type": "number"},
                 "output_cost_per_token_flex": {"type": "number"},
                 "output_cost_per_token_priority": {"type": "number"},
                 "output_cost_per_token_above_200k_tokens_priority": {"type": "number"},
                 "output_cost_per_token_above_272k_tokens_priority": {"type": "number"},
+                "output_cost_per_token_above_272k_tokens_batches": {"type": "number"},
                 "output_cost_per_token_above_272k_tokens_flex": {"type": "number"},
                 "regional_endpoint_uplift_multiplier": {"type": "number"},
                 "regional_processing_uplift_multiplier_eu": {"type": "number"},
diff --git a/tests/unit/batches/test_batch_utils.py b/tests/unit/batches/test_batch_utils.py
index 708c472939e..a4de8eee23c 100644
--- a/tests/unit/batches/test_batch_utils.py
+++ b/tests/unit/batches/test_batch_utils.py
@@ -26,7 +26,7 @@ from openai.types.batch import BatchRequestCounts
 
 import litellm
 import litellm.batches.batch_utils as bu
-from litellm.types.utils import LiteLLMBatch, Usage
+from litellm.types.utils import LiteLLMBatch, ModelInfo, Usage
 
 # --------------------------------------------------------------------------- #
 # Builders for batch OUTPUT file rows.
@@ -437,6 +437,33 @@ def test_total_usage_and_cost_normalize_mixed_responses_and_chat():
     assert result.cost == pytest.approx((30 * 0.00125) + (12 * 0.005))
 
 
+def test_total_cost_applies_the_long_context_batch_tier_per_line():
+    long_row = _success_row(usage=_usage(300_000, 10))
+    short_row = _success_row(usage=_usage(100, 10))
+
+    result = bu._aggregate_batch_cost_usage_models(
+        entries=[long_row, short_row],
+        custom_llm_provider="openai",
+        model_info=ModelInfo(
+            key="lit-batch-tier",
+            max_tokens=None,
+            max_input_tokens=None,
+            max_output_tokens=None,
+            input_cost_per_token=2e-6,
+            output_cost_per_token=8e-6,
+            litellm_provider="openai",
+            mode="chat",
+            supported_openai_params=None,
+            input_cost_per_token_batches=1e-6,
+            output_cost_per_token_batches=4e-6,
+            input_cost_per_token_above_272k_tokens_batches=2e-6,
+            output_cost_per_token_above_272k_tokens_batches=6e-6,
+        ),
+    )
+
+    assert result.cost == pytest.approx((300_000 * 2e-6) + (10 * 6e-6) + (100 * 1e-6) + (10 * 4e-6))
+
+
 def test_total_usage_empty_is_zero():
     result = bu._aggregate_batch_cost_usage_models(entries=[], custom_llm_provider="openai")
     assert result.cost == 0.0
@@ -1824,6 +1851,45 @@ def test_unparsable_bedrock_batch_usage_warns(caplog):
     assert "inputTextTokenCount" in caplog.text
 
 
+def test_total_cost_bills_cached_tokens_per_line_at_the_batch_cached_rate():
+    responses_row = _success_row(
+        usage={
+            "input_tokens": 300_000,
+            "output_tokens": 10,
+            "total_tokens": 300_010,
+            "input_tokens_details": {"cached_tokens": 299_000},
+        }
+    )
+    chat_row = _success_row(usage={**_usage(100, 10), "prompt_tokens_details": {"cached_tokens": 60}})
+
+    result = bu._aggregate_batch_cost_usage_models(
+        entries=[responses_row, chat_row],
+        custom_llm_provider="openai",
+        model_info=ModelInfo(
+            key="lit-batch-cached-tier",
+            max_tokens=None,
+            max_input_tokens=None,
+            max_output_tokens=None,
+            input_cost_per_token=2e-6,
+            output_cost_per_token=8e-6,
+            cache_read_input_token_cost=1e-6,
+            litellm_provider="openai",
+            mode="chat",
+            supported_openai_params=None,
+            input_cost_per_token_batches=1e-6,
+            output_cost_per_token_batches=4e-6,
+            cache_read_input_token_cost_batches=5e-7,
+            input_cost_per_token_above_272k_tokens_batches=2e-6,
+            output_cost_per_token_above_272k_tokens_batches=6e-6,
+            cache_read_input_token_cost_above_272k_tokens_batches=1e-6,
+        ),
+    )
+
+    long_line = 1_000 * 2e-6 + 299_000 * 1e-6 + 10 * 6e-6
+    short_line = 40 * 1e-6 + 60 * 5e-7 + 10 * 4e-6
+    assert result.cost == pytest.approx(long_line + short_line)
+
+
 # --------------------------------------------------------------------------- #
 # batch_cost_is_final
 # --------------------------------------------------------------------------- #
diff --git a/ui/litellm-dashboard/src/lib/http/schema.d.ts b/ui/litellm-dashboard/src/lib/http/schema.d.ts
index 38cfdc9666b..38f8ac365ff 100644
--- a/ui/litellm-dashboard/src/lib/http/schema.d.ts
+++ b/ui/litellm-dashboard/src/lib/http/schema.d.ts
@@ -31186,10 +31186,14 @@ export interface components {
             cache_creation_input_token_cost_above_200k_tokens?: number | null;
             /** Cache Creation Input Token Cost Above 272K Tokens */
             cache_creation_input_token_cost_above_272k_tokens?: number | null;
+            /** Cache Creation Input Token Cost Above 272K Tokens Batches */
+            cache_creation_input_token_cost_above_272k_tokens_batches?: number | null;
             /** Cache Creation Input Token Cost Above 272K Tokens Flex */
             cache_creation_input_token_cost_above_272k_tokens_flex?: number | null;
             /** Cache Creation Input Token Cost Above 272K Tokens Priority */
             cache_creation_input_token_cost_above_272k_tokens_priority?: number | null;
+            /** Cache Creation Input Token Cost Batches */
+            cache_creation_input_token_cost_batches?: number | null;
             /** Cache Creation Input Token Cost Flex */
             cache_creation_input_token_cost_flex?: number | null;
             /** Cache Creation Input Token Cost Priority */
@@ -31208,12 +31212,16 @@ export interface components {
             cache_read_input_token_cost_above_200k_tokens_priority?: number | null;
             /** Cache Read Input Token Cost Above 272K Tokens */
             cache_read_input_token_cost_above_272k_tokens?: number | null;
+            /** Cache Read Input Token Cost Above 272K Tokens Batches */
+            cache_read_input_token_cost_above_272k_tokens_batches?: number | null;
             /** Cache Read Input Token Cost Above 272K Tokens Flex */
             cache_read_input_token_cost_above_272k_tokens_flex?: number | null;
             /** Cache Read Input Token Cost Above 272K Tokens Priority */
             cache_read_input_token_cost_above_272k_tokens_priority?: number | null;
             /** Cache Read Input Token Cost Above 512K Tokens */
             cache_read_input_token_cost_above_512k_tokens?: number | null;
+            /** Cache Read Input Token Cost Batches */
+            cache_read_input_token_cost_batches?: number | null;
             /** Cache Read Input Token Cost Flex */
             cache_read_input_token_cost_flex?: number | null;
             /** Cache Read Input Token Cost Priority */
@@ -31282,6 +31290,8 @@ export interface components {
             input_cost_per_token_above_200k_tokens_priority?: number | null;
             /** Input Cost Per Token Above 272K Tokens */
             input_cost_per_token_above_272k_tokens?: number | null;
+            /** Input Cost Per Token Above 272K Tokens Batches */
+            input_cost_per_token_above_272k_tokens_batches?: number | null;
             /** Input Cost Per Token Above 272K Tokens Flex */
             input_cost_per_token_above_272k_tokens_flex?: number | null;
             /** Input Cost Per Token Above 272K Tokens Priority */
@@ -31403,6 +31413,8 @@ export interface components {
             output_cost_per_token_above_200k_tokens_priority?: number | null;
             /** Output Cost Per Token Above 272K Tokens */
             output_cost_per_token_above_272k_tokens?: number | null;
+            /** Output Cost Per Token Above 272K Tokens Batches */
+            output_cost_per_token_above_272k_tokens_batches?: number | null;
             /** Output Cost Per Token Above 272K Tokens Flex */
             output_cost_per_token_above_272k_tokens_flex?: number | null;
             /** Output Cost Per Token Above 272K Tokens Priority */
@@ -42026,10 +42038,14 @@ export interface components {
             cache_creation_input_token_cost_above_200k_tokens?: number | null;
             /** Cache Creation Input Token Cost Above 272K Tokens */
             cache_creation_input_token_cost_above_272k_tokens?: number | null;
+            /** Cache Creation Input Token Cost Above 272K Tokens Batches */
+            cache_creation_input_token_cost_above_272k_tokens_batches?: number | null;
             /** Cache Creation Input Token Cost Above 272K Tokens Flex */
             cache_creation_input_token_cost_above_272k_tokens_flex?: number | null;
             /** Cache Creation Input Token Cost Above 272K Tokens Priority */
             cache_creation_input_token_cost_above_272k_tokens_priority?: number | null;
+            /** Cache Creation Input Token Cost Batches */
+            cache_creation_input_token_cost_batches?: number | null;
             /** Cache Creation Input Token Cost Flex */
             cache_creation_input_token_cost_flex?: number | null;
             /** Cache Creation Input Token Cost Priority */
@@ -42048,12 +42064,16 @@ export interface components {
             cache_read_input_token_cost_above_200k_tokens_priority?: number | null;
             /** Cache Read Input Token Cost Above 272K Tokens */
             cache_read_input_token_cost_above_272k_tokens?: number | null;
+            /** Cache Read Input Token Cost Above 272K Tokens Batches */
+            cache_read_input_token_cost_above_272k_tokens_batches?: number | null;
             /** Cache Read Input Token Cost Above 272K Tokens Flex */
             cache_read_input_token_cost_above_272k_tokens_flex?: number | null;
             /** Cache Read Input Token Cost Above 272K Tokens Priority */
             cache_read_input_token_cost_above_272k_tokens_priority?: number | null;
             /** Cache Read Input Token Cost Above 512K Tokens */
             cache_read_input_token_cost_above_512k_tokens?: number | null;
+            /** Cache Read Input Token Cost Batches */
+            cache_read_input_token_cost_batches?: number | null;
             /** Cache Read Input Token Cost Flex */
             cache_read_input_token_cost_flex?: number | null;
             /** Cache Read Input Token Cost Priority */
@@ -42122,6 +42142,8 @@ export interface components {
             input_cost_per_token_above_200k_tokens_priority?: number | null;
             /** Input Cost Per Token Above 272K Tokens */
             input_cost_per_token_above_272k_tokens?: number | null;
+            /** Input Cost Per Token Above 272K Tokens Batches */
+            input_cost_per_token_above_272k_tokens_batches?: number | null;
             /** Input Cost Per Token Above 272K Tokens Flex */
             input_cost_per_token_above_272k_tokens_flex?: number | null;
             /** Input Cost Per Token Above 272K Tokens Priority */
@@ -42243,6 +42265,8 @@ export interface components {
             output_cost_per_token_above_200k_tokens_priority?: number | null;
             /** Output Cost Per Token Above 272K Tokens */
             output_cost_per_token_above_272k_tokens?: number | null;
+            /** Output Cost Per Token Above 272K Tokens Batches */
+            output_cost_per_token_above_272k_tokens_batches?: number | null;
             /** Output Cost Per Token Above 272K Tokens Flex */
             output_cost_per_token_above_272k_tokens_flex?: number | null;
             /** Output Cost Per Token Above 272K Tokens Priority */