From e5421bfe1ec29744dbfa86c6b2d77ca94d17ea01 Mon Sep 17 00:00:00 2001
From: mateo-berri <277851410+mateo-berri@users.noreply.github.com>
Date: Fri, 10 Jul 2026 23:16:09 +0000
Subject: [PATCH] fix(model_cost): add missing backup entries for gemini image
 models

gemini/gemini-3.1-flash-image, vertex_ai/gemini-3-pro-image, and
vertex_ai/gemini-3.1-flash-image existed in the root pricing JSON but not in
litellm/model_prices_and_context_window_backup.json, leaving deployments with
LITELLM_LOCAL_MODEL_COST_MAP=True unprotected. Copies the root entries into
the backup verbatim and extends the regression test to cover all ten gemini
image models, asserting each exists in the local cost map so a missing backup
entry fails the test instead of passing vacuously
---
 ...odel_prices_and_context_window_backup.json | 72 +++++++++++++++++++
 tests/test_litellm/test_utils.py              |  7 ++
 2 files changed, 79 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 9b1e60dff1a..2e21be86168 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -18782,6 +18782,48 @@
         },
         "web_search_billing_unit": "per_query"
     },
+    "gemini/gemini-3.1-flash-image": {
+        "input_cost_per_token": 2.5e-07,
+        "input_cost_per_token_batches": 1.25e-07,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 65536,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.045,
+        "output_cost_per_image_token": 6e-05,
+        "output_cost_per_token": 1.5e-06,
+        "output_cost_per_token_batches": 7.5e-07,
+        "rpm": 1000,
+        "tpm": 4000000,
+        "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-image",
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/completions",
+            "/v1/batch"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text",
+            "image"
+        ],
+        "supports_function_calling": false,
+        "supports_prompt_caching": true,
+        "supports_reasoning": false,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_vision": true,
+        "supports_web_search": 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"
+    },
     "gemini/gemini-3.1-flash-image-preview": {
         "input_cost_per_token": 2.5e-07,
         "input_cost_per_token_batches": 1.25e-07,
@@ -36781,6 +36823,22 @@
         "tpm": 8000000,
         "supports_image_size": false
     },
+    "vertex_ai/gemini-3-pro-image": {
+        "input_cost_per_image": 0.0011,
+        "input_cost_per_token": 2e-06,
+        "input_cost_per_token_batches": 1e-06,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 65536,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.134,
+        "output_cost_per_image_token": 0.00012,
+        "output_cost_per_token": 1.2e-05,
+        "output_cost_per_token_batches": 6e-06,
+        "supports_reasoning": false,
+        "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
+    },
     "vertex_ai/gemini-3-pro-image-preview": {
         "input_cost_per_image": 0.0011,
         "input_cost_per_token": 2e-06,
@@ -36797,6 +36855,20 @@
         "supports_reasoning": false,
         "source": "https://docs.cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/3-pro-image"
     },
+    "vertex_ai/gemini-3.1-flash-image": {
+        "input_cost_per_image": 0.00056,
+        "input_cost_per_token": 5e-07,
+        "litellm_provider": "vertex_ai-language-models",
+        "max_input_tokens": 65536,
+        "max_output_tokens": 32768,
+        "max_tokens": 32768,
+        "mode": "image_generation",
+        "output_cost_per_image": 0.0672,
+        "output_cost_per_image_token": 6e-05,
+        "output_cost_per_token": 3e-06,
+        "supports_reasoning": false,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models"
+    },
     "vertex_ai/gemini-3.1-flash-image-preview": {
         "input_cost_per_image": 0.00056,
         "input_cost_per_token": 5e-07,
diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py
index fddf1f4a0be..576f2f20242 100644
--- a/tests/test_litellm/test_utils.py
+++ b/tests/test_litellm/test_utils.py
@@ -4714,17 +4714,24 @@ class TestValidateEnvironmentTencent:
     "model",
     [
         "vertex_ai/gemini-2.5-flash-image",
+        "vertex_ai/gemini-3-pro-image",
         "vertex_ai/gemini-3-pro-image-preview",
+        "vertex_ai/gemini-3.1-flash-image",
         "vertex_ai/gemini-3.1-flash-image-preview",
         "gemini/gemini-2.5-flash-image",
         "gemini/gemini-3-pro-image",
         "gemini/gemini-3-pro-image-preview",
+        "gemini/gemini-3.1-flash-image",
         "gemini/gemini-3.1-flash-image-preview",
     ],
 )
 def test_gemini_image_models_do_not_support_reasoning(
     model: str, local_model_cost_map: None
 ) -> None:
+    assert model in litellm.model_cost, (
+        f"{model} is missing from the local model cost map. "
+        "Add its entry to litellm/model_prices_and_context_window_backup.json."
+    )
     assert litellm.supports_reasoning(model) is False, (
         f"{model} incorrectly classified as reasoning-capable. "
         "Add 'supports_reasoning: false' to its model_cost entry."