feat(gemini): add gemini-3.1-flash-lite model cost map (#28320)

* feat(gemini): add gemini-3.1-flash-lite model cost map entries

Co-authored-by: Cursor <cursoragent@cursor.com>

* Update model_prices_and_context_window.json

* Update source URL for model pricing information

* Sync source URL for gemini-3.1-flash-lite in backup JSON

* fix(model_cost_map): add mistral/ministral-8b-2512 entry

Mistral rotated the 'mistral/mistral-tiny' alias to return
'ministral-8b-2512' as the response model, which is not in the cost map.
This caused test_completion_mistral_api and
test_completion_mistral_api_modified_input to fail in
completion_cost lookup. Add the entry mirroring the existing
openrouter/mistralai/ministral-8b-2512 pricing.

* test(cost_calculator): assert output_cost_per_reasoning_token for gemini-3.1-flash-lite

* fix(tests): backfill local backup entries into runtime model_cost

litellm.model_cost is loaded from LITELLM_MODEL_COST_MAP_URL (pinned to
main) at import time, so any pricing entries added to the in-tree backup
on this branch aren't visible at test runtime until they also land on
main. The Mistral cassette currently returns model=ministral-8b-2512
and the cost-calculator lookup in test_completion_mistral_api /
test_completion_mistral_api_modified_input fails despite the entry
existing in the local backup. Backfill missing backup entries into
litellm.model_cost in the local_testing conftest so these lookups
succeed against the cassette state the branch is being tested with.

* fix(tests): guard conftest backfill against empty local cost map

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: mateo-berri <277851410+mateo-berri@users.noreply.github.com>

litellm/model_prices_and_context_window_backup.json

@@ -1448,6 +1448,35 @@
         "supports_native_structured_output": true,
         "supports_minimal_reasoning_effort": true
     },
+    "jp.anthropic.claude-sonnet-4-6": {
+        "cache_creation_input_token_cost": 4.125e-06,
+        "cache_read_input_token_cost": 3.3e-07,
+        "input_cost_per_token": 3.3e-06,
+        "litellm_provider": "bedrock_converse",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 64000,
+        "max_tokens": 64000,
+        "mode": "chat",
+        "output_cost_per_token": 1.65e-05,
+        "search_context_cost_per_query": {
+            "search_context_size_high": 0.01,
+            "search_context_size_low": 0.01,
+            "search_context_size_medium": 0.01
+        },
+        "supports_assistant_prefill": true,
+        "supports_computer_use": true,
+        "supports_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_max_reasoning_effort": true,
+        "supports_tool_choice": true,
+        "supports_vision": true,
+        "tool_use_system_prompt_tokens": 346,
+        "supports_native_structured_output": true,
+        "supports_minimal_reasoning_effort": true
+    },
     "anthropic.claude-sonnet-4-20250514-v1:0": {
         "cache_creation_input_token_cost": 3.75e-06,
         "cache_read_input_token_cost": 3e-07,
@@ -9602,6 +9631,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "supports_adaptive_thinking": true,
         "supports_assistant_prefill": true,
         "supports_computer_use": true,
         "supports_function_calling": true,
@@ -9795,6 +9825,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "supports_adaptive_thinking": true,
         "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
@@ -9828,6 +9859,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "supports_adaptive_thinking": true,
         "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
@@ -9861,6 +9893,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "supports_adaptive_thinking": true,
         "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
@@ -9895,6 +9928,7 @@
             "search_context_size_low": 0.01,
             "search_context_size_medium": 0.01
         },
+        "supports_adaptive_thinking": true,
         "supports_assistant_prefill": false,
         "supports_computer_use": true,
         "supports_function_calling": true,
@@ -14883,7 +14917,65 @@
         "mode": "chat",
         "output_cost_per_reasoning_token": 1.5e-06,
         "output_cost_per_token": 1.5e-06,
-        "source": "https://ai.google.dev/gemini-api/docs/models",
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_code_execution": true,
+        "supports_file_search": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_native_streaming": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014,
+            "search_context_size_high": 0.014
+        },
+        "web_search_billing_unit": "per_query",
+        "supports_service_tier": true
+    },
+    "gemini-3.1-flash-lite": {
+        "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_per_audio_token": 9e-08,
+        "input_cost_per_audio_token": 9e-07,
+        "input_cost_per_token": 4.5e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65536,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 2.7e-06,
+        "output_cost_per_token": 2.7e-06,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
         "supported_endpoints": [
             "/v1/chat/completions",
             "/v1/completions",
@@ -16987,6 +17079,66 @@
         "web_search_billing_unit": "per_query",
         "supports_service_tier": true
     },
+    "gemini/gemini-3.1-flash-lite": {
+        "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_per_audio_token": 9e-08,
+        "input_cost_per_audio_token": 9e-07,
+        "input_cost_per_token": 4.5e-07,
+        "litellm_provider": "gemini",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65536,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 2.7e-06,
+        "output_cost_per_token": 2.7e-06,
+        "rpm": 15,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_code_execution": true,
+        "supports_file_search": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_native_streaming": true,
+        "tpm": 250000,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014,
+            "search_context_size_high": 0.014
+        },
+        "web_search_billing_unit": "per_query",
+        "supports_service_tier": true
+    },
     "gemini/gemini-3-flash-preview": {
         "cache_read_input_token_cost": 5e-08,
         "input_cost_per_audio_token": 1e-06,
@@ -24285,6 +24437,21 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "mistral/ministral-8b-2512": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-07,
+        "source": "https://mistral.ai/pricing",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "mistral/mistral-tiny": {
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "mistral",
@@ -33605,6 +33772,64 @@
         },
         "web_search_billing_unit": "per_query"
     },
+    "vertex_ai/gemini-3.1-flash-lite": {
+        "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_per_audio_token": 9e-08,
+        "input_cost_per_audio_token": 9e-07,
+        "input_cost_per_token": 4.5e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65536,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 2.7e-06,
+        "output_cost_per_token": 2.7e-06,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_code_execution": true,
+        "supports_file_search": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_native_streaming": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014,
+            "search_context_size_high": 0.014
+        },
+        "web_search_billing_unit": "per_query",
+        "supports_service_tier": true
+    },
     "vertex_ai/deep-research-pro-preview-12-2025": {
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,

model_prices_and_context_window.json

@@ -14957,6 +14957,64 @@
         "web_search_billing_unit": "per_query",
         "supports_service_tier": true
     },
+    "gemini-3.1-flash-lite": {
+        "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_per_audio_token": 9e-08,
+        "input_cost_per_audio_token": 9e-07,
+        "input_cost_per_token": 4.5e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65536,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 2.7e-06,
+        "output_cost_per_token": 2.7e-06,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_code_execution": true,
+        "supports_file_search": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_native_streaming": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014,
+            "search_context_size_high": 0.014
+        },
+        "web_search_billing_unit": "per_query",
+        "supports_service_tier": true
+    },
     "deep-research-pro-preview-12-2025": {
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
@@ -17021,6 +17079,66 @@
         "web_search_billing_unit": "per_query",
         "supports_service_tier": true
     },
+    "gemini/gemini-3.1-flash-lite": {
+        "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_per_audio_token": 9e-08,
+        "input_cost_per_audio_token": 9e-07,
+        "input_cost_per_token": 4.5e-07,
+        "litellm_provider": "gemini",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65536,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 2.7e-06,
+        "output_cost_per_token": 2.7e-06,
+        "rpm": 15,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_code_execution": true,
+        "supports_file_search": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_native_streaming": true,
+        "tpm": 250000,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014,
+            "search_context_size_high": 0.014
+        },
+        "web_search_billing_unit": "per_query",
+        "supports_service_tier": true
+    },
     "gemini/gemini-3-flash-preview": {
         "cache_read_input_token_cost": 5e-08,
         "input_cost_per_audio_token": 1e-06,
@@ -24319,6 +24437,21 @@
         "supports_tool_choice": true,
         "supports_vision": true
     },
+    "mistral/ministral-8b-2512": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "mistral",
+        "max_input_tokens": 262144,
+        "max_output_tokens": 262144,
+        "max_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 1.5e-07,
+        "source": "https://mistral.ai/pricing",
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "mistral/mistral-tiny": {
         "input_cost_per_token": 2.5e-07,
         "litellm_provider": "mistral",
@@ -33639,6 +33772,64 @@
         },
         "web_search_billing_unit": "per_query"
     },
+    "vertex_ai/gemini-3.1-flash-lite": {
+        "cache_read_input_token_cost": 4.5e-08,
+        "cache_read_input_token_cost_per_audio_token": 9e-08,
+        "input_cost_per_audio_token": 9e-07,
+        "input_cost_per_token": 4.5e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_audio_length_hours": 8.4,
+        "max_audio_per_prompt": 1,
+        "max_images_per_prompt": 3000,
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 65536,
+        "max_pdf_size_mb": 30,
+        "max_tokens": 65536,
+        "max_video_length": 1,
+        "max_videos_per_prompt": 10,
+        "mode": "chat",
+        "output_cost_per_reasoning_token": 2.7e-06,
+        "output_cost_per_token": 2.7e-06,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image",
+            "audio",
+            "video"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_audio_input": true,
+        "supports_audio_output": false,
+        "supports_code_execution": true,
+        "supports_file_search": true,
+        "supports_function_calling": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_url_context": true,
+        "supports_video_input": true,
+        "supports_vision": true,
+        "supports_web_search": true,
+        "supports_native_streaming": true,
+        "search_context_cost_per_query": {
+            "search_context_size_low": 0.014,
+            "search_context_size_medium": 0.014,
+            "search_context_size_high": 0.014
+        },
+        "web_search_billing_unit": "per_query",
+        "supports_service_tier": true
+    },
     "vertex_ai/deep-research-pro-preview-12-2025": {
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,

tests/local_testing/conftest.py

@@ -22,6 +22,20 @@ sys.path.insert(
 )  # Adds the parent directory to the system path
 import litellm
 
+# ``litellm.model_cost`` is loaded at import time from the URL pinned to
+# ``main`` (``LITELLM_MODEL_COST_MAP_URL``).  The in-tree backup ships with
+# this branch and can include pricing entries that main has not yet picked
+# up (e.g. an upstream provider rotates a model id and the test cassette
+# records the new name).  Backfill any entries that are missing from the
+# remote-fetched map so cost-calculator lookups in tests succeed against
+# the cassette state the branch is being tested with.
+from litellm.litellm_core_utils.get_model_cost_map import GetModelCostMap
+
+_local_cost_map = GetModelCostMap.load_local_model_cost_map()
+for _k, _v in _local_cost_map.items():
+    litellm.model_cost.setdefault(_k, _v)
+del _local_cost_map
+
 from tests._vcr_conftest_common import (  # noqa: E402,F401
     VerboseReporterState,
     _pin_multipart_boundary,

tests/test_litellm/test_cost_calculator.py

@@ -2059,6 +2059,25 @@ def test_openrouter_gemini_3_1_flash_lite_preview_pricing():
     assert model_info["max_output_tokens"] == 65536
 
 
+def test_gemini_3_1_flash_lite_pricing():
+    os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+
+    for model_name in (
+        "gemini-3.1-flash-lite",
+        "gemini/gemini-3.1-flash-lite",
+        "vertex_ai/gemini-3.1-flash-lite",
+    ):
+        model_info = litellm.model_cost.get(model_name)
+        assert model_info is not None, f"Missing model pricing entry: {model_name}"
+        assert model_info["input_cost_per_token"] == 4.5e-07
+        assert model_info["input_cost_per_audio_token"] == 9e-07
+        assert model_info["output_cost_per_token"] == 2.7e-06
+        assert model_info["output_cost_per_reasoning_token"] == 2.7e-06
+        assert model_info["cache_read_input_token_cost"] == 4.5e-08
+        assert model_info["max_input_tokens"] == 1048576
+
+
 def test_custom_pricing_applies_cache_read_input_cost():
     """
     Bug 1 reproduction: custom_cost_per_token with cache_read_input_token_cost