Add above-512k pricing tier for MiniMax-M3 and correct its base rates (#30095)

* Add above-512k pricing tier support for MiniMax-M3

MiniMax-M3 doubles its per-token rates once a prompt exceeds 512k
input tokens. The tiered cost parser already handles arbitrary
thresholds, but get_model_info only copies whitelisted keys from
ModelInfoBase, which had no 512k variants, so above_512k keys were
silently dropped and long-context requests were priced at the flat
rate.

Add the input, output, and cache-read above_512k_tokens fields to
ModelInfoBase and pass them through in get_model_info. Update the
minimax/MiniMax-M3 entry with the tiered rates and correct the base
rates, which matched the above-512k tier instead of the published
base tier (https://platform.minimax.io/docs/guides/pricing-paygo).

Fixes #29663.

* Add above-512k keys to pricing schema, set MiniMax-M3 context to 1M

Register the three new above_512k_tokens cost keys in the INTENDED_SCHEMA
of test_aaamodel_prices_and_context_window_json_is_valid, declared the same
way as the existing above_200k/above_272k tier keys, so the schema check
accepts the MiniMax-M3 tiered pricing entry.

Also raise MiniMax-M3 max_input_tokens from 512000 to 1000000 in both
pricing JSONs. The MiniMax API docs
(https://platform.minimax.io/docs/guides/text-generation) state the model
supports a 1,000,000-token context window, and the pay-as-you-go pricing
page (https://platform.minimax.io/docs/guides/pricing-paygo) prices input
above 512k tokens, which only makes sense if inputs beyond 512k are
accepted. This makes the above-512k pricing tier reachable.

litellm/model_prices_and_context_window_backup.json

@@ -24392,9 +24392,12 @@
         "max_output_tokens": 8192
     },
     "minimax/MiniMax-M3": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.4e-06,
-        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_above_512k_tokens": 6e-07,
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_above_512k_tokens": 2.4e-06,
+        "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_above_512k_tokens": 1.2e-07,
         "litellm_provider": "minimax",
         "mode": "chat",
         "supports_function_calling": true,
@@ -24403,7 +24406,7 @@
         "supports_reasoning": true,
         "supports_system_messages": true,
         "supports_vision": true,
-        "max_input_tokens": 512000,
+        "max_input_tokens": 1000000,
         "max_output_tokens": 128000
     },
     "mistral.devstral-2-123b": {

litellm/types/utils.py

@@ -197,6 +197,7 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     ]  # OpenAI priority service tier pricing
     cache_read_input_token_cost_above_200k_tokens: Optional[float]
     cache_read_input_token_cost_above_272k_tokens: Optional[float]
+    cache_read_input_token_cost_above_512k_tokens: Optional[float]
     input_cost_per_character: Optional[float]  # only for vertex ai models
     input_cost_per_audio_token: Optional[float]
     input_cost_per_token_above_128k_tokens: Optional[float]  # only for vertex ai models
@@ -206,6 +207,9 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     input_cost_per_token_above_272k_tokens: Optional[
         float
     ]  # GPT-5.4/5.4-pro: prompts >272K priced at 2x input
+    input_cost_per_token_above_512k_tokens: Optional[
+        float
+    ]  # MiniMax-M3: prompts >512K priced at 2x input
     input_cost_per_character_above_128k_tokens: Optional[
         float
     ]  # only for vertex ai models
@@ -239,6 +243,9 @@ class ModelInfoBase(ProviderSpecificModelInfo, total=False):
     output_cost_per_token_above_272k_tokens: Optional[
         float
     ]  # GPT-5.4/5.4-pro: prompts >272K priced at 1.5x output
+    output_cost_per_token_above_512k_tokens: Optional[
+        float
+    ]  # MiniMax-M3: prompts >512K priced at 2x output
     output_cost_per_character_above_128k_tokens: Optional[
         float
     ]  # only for vertex ai models

litellm/utils.py

@@ -5941,6 +5941,9 @@ def _get_model_info_helper(  # noqa: PLR0915
                 cache_read_input_token_cost_above_272k_tokens=_model_info.get(
                     "cache_read_input_token_cost_above_272k_tokens", None
                 ),
+                cache_read_input_token_cost_above_512k_tokens=_model_info.get(
+                    "cache_read_input_token_cost_above_512k_tokens", None
+                ),
                 cache_read_input_token_cost_flex=_model_info.get(
                     "cache_read_input_token_cost_flex", None
                 ),
@@ -5962,6 +5965,9 @@ def _get_model_info_helper(  # noqa: PLR0915
                 input_cost_per_token_above_272k_tokens=_model_info.get(
                     "input_cost_per_token_above_272k_tokens", None
                 ),
+                input_cost_per_token_above_512k_tokens=_model_info.get(
+                    "input_cost_per_token_above_512k_tokens", None
+                ),
                 input_cost_per_query=_model_info.get("input_cost_per_query", None),
                 input_cost_per_second=_model_info.get("input_cost_per_second", None),
                 input_cost_per_audio_token=_model_info.get(
@@ -6017,6 +6023,9 @@ def _get_model_info_helper(  # noqa: PLR0915
                 output_cost_per_token_above_272k_tokens=_model_info.get(
                     "output_cost_per_token_above_272k_tokens", None
                 ),
+                output_cost_per_token_above_512k_tokens=_model_info.get(
+                    "output_cost_per_token_above_512k_tokens", None
+                ),
                 output_cost_per_second=_model_info.get("output_cost_per_second", None),
                 output_cost_per_second_1080p=_model_info.get(
                     "output_cost_per_second_1080p", None

model_prices_and_context_window.json

@@ -24392,9 +24392,12 @@
         "max_output_tokens": 8192
     },
     "minimax/MiniMax-M3": {
-        "input_cost_per_token": 6e-07,
-        "output_cost_per_token": 2.4e-06,
-        "cache_read_input_token_cost": 1.2e-07,
+        "input_cost_per_token": 3e-07,
+        "input_cost_per_token_above_512k_tokens": 6e-07,
+        "output_cost_per_token": 1.2e-06,
+        "output_cost_per_token_above_512k_tokens": 2.4e-06,
+        "cache_read_input_token_cost": 6e-08,
+        "cache_read_input_token_cost_above_512k_tokens": 1.2e-07,
         "litellm_provider": "minimax",
         "mode": "chat",
         "supports_function_calling": true,
@@ -24403,7 +24406,7 @@
         "supports_reasoning": true,
         "supports_system_messages": true,
         "supports_vision": true,
-        "max_input_tokens": 512000,
+        "max_input_tokens": 1000000,
         "max_output_tokens": 128000
     },
     "mistral.devstral-2-123b": {

tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py

@@ -328,6 +328,41 @@ def test_generic_cost_per_token_gpt54_above_272k_tokens():
     assert round(completion_cost, 10) == round(expected_completion, 10)
 
 
+def test_generic_cost_per_token_minimax_m3_above_512k_tokens():
+    """MiniMax-M3: prompts >512K input tokens priced at 2x input, output, and cache read."""
+    model = "minimax/MiniMax-M3"
+    custom_llm_provider = "minimax"
+    os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+
+    model_cost_map = litellm.model_cost[model]
+    prompt_tokens = 600000
+    cached_tokens = 100000
+    completion_tokens = 1000
+    usage = Usage(
+        prompt_tokens=prompt_tokens,
+        completion_tokens=completion_tokens,
+        total_tokens=prompt_tokens + completion_tokens,
+        prompt_tokens_details=PromptTokensDetailsWrapper(cached_tokens=cached_tokens),
+    )
+    prompt_cost, completion_cost = generic_cost_per_token(
+        model=model,
+        usage=usage,
+        custom_llm_provider=custom_llm_provider,
+    )
+    expected_prompt = (
+        model_cost_map["input_cost_per_token_above_512k_tokens"]
+        * (prompt_tokens - cached_tokens)
+        + model_cost_map["cache_read_input_token_cost_above_512k_tokens"]
+        * cached_tokens
+    )
+    expected_completion = (
+        model_cost_map["output_cost_per_token_above_512k_tokens"] * completion_tokens
+    )
+    assert round(prompt_cost, 10) == round(expected_prompt, 10)
+    assert round(completion_cost, 10) == round(expected_completion, 10)
+
+
 def test_generic_cost_per_token_gpt55():
     """gpt-5.5: base pricing — $5/1M input, $30/1M output, $0.50/1M cached input."""
     model = "gpt-5.5"

tests/test_litellm/test_utils.py

@@ -700,6 +700,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "cache_read_input_token_cost": {"type": "number"},
                 "cache_read_input_token_cost_above_200k_tokens": {"type": "number"},
                 "cache_read_input_token_cost_above_272k_tokens": {"type": "number"},
+                "cache_read_input_token_cost_above_512k_tokens": {"type": "number"},
                 "cache_read_input_token_cost_batches": {"type": "number"},
                 "cache_creation_input_token_cost_above_1hr_above_200k_tokens": {
                     "type": "number"
@@ -721,6 +722,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "input_cost_per_token_above_200k_tokens": {"type": "number"},
                 "input_cost_per_token_above_256k_tokens": {"type": "number"},
                 "input_cost_per_token_above_272k_tokens": {"type": "number"},
+                "input_cost_per_token_above_512k_tokens": {"type": "number"},
                 "cache_read_input_token_cost_flex": {"type": "number"},
                 "cache_read_input_token_cost_priority": {"type": "number"},
                 "cache_read_input_token_cost_above_200k_tokens_priority": {
@@ -811,6 +813,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid():
                 "output_cost_per_token_above_200k_tokens": {"type": "number"},
                 "output_cost_per_token_above_256k_tokens": {"type": "number"},
                 "output_cost_per_token_above_272k_tokens": {"type": "number"},
+                "output_cost_per_token_above_512k_tokens": {"type": "number"},
                 "output_cost_per_image_above_1024_and_1024_pixels": {"type": "number"},
                 "output_cost_per_image_above_1024_and_1024_pixels_and_premium_image": {
                     "type": "number"