From 3b8d2a9a313d8a2b830f2ea4f1579c69ec146b24 Mon Sep 17 00:00:00 2001
From: Sameer Kankute <sameer@berri.ai>
Date: Wed, 11 Mar 2026 10:58:50 +0530
Subject: [PATCH] Add embedding model in model map

---
 ...odel_prices_and_context_window_backup.json | 39 +++++++++++++++++++
 model_prices_and_context_window.json          | 39 +++++++++++++++++++
 2 files changed, 78 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index 4704549e716..c1d097c62b3 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -14273,6 +14273,32 @@
         "output_vector_size": 3072,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
     },
+    "gemini-embedding-2-preview": {
+        "input_cost_per_audio_per_second": 0.00016,
+        "input_cost_per_image": 0.00012,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_video_per_second": 0.0237,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding",
+        "output_cost_per_token": 0,
+        "output_vector_size": 3072,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "uses_embed_content": true
+    },
+    "vertex_ai/gemini-embedding-2-preview": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding",
+        "output_cost_per_token": 0,
+        "output_vector_size": 3072,
+        "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
+        "supports_multimodal": true,
+        "uses_embed_content": true
+    },
     "gemini-flash-experimental": {
         "input_cost_per_character": 0,
         "input_cost_per_token": 0,
@@ -14350,6 +14376,19 @@
         "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions",
         "tpm": 10000000
     },
+    "gemini/gemini-embedding-2-preview": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding",
+        "output_cost_per_token": 0,
+        "output_vector_size": 3072,
+        "rpm": 10000,
+        "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
+        "supports_multimodal": true,
+        "tpm": 10000000
+    },
     "gemini/gemini-1.5-flash": {
         "deprecation_date": "2025-09-29",
         "input_cost_per_token": 7.5e-08,
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index 4704549e716..c1d097c62b3 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -14273,6 +14273,32 @@
         "output_vector_size": 3072,
         "source": "https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models"
     },
+    "gemini-embedding-2-preview": {
+        "input_cost_per_audio_per_second": 0.00016,
+        "input_cost_per_image": 0.00012,
+        "input_cost_per_token": 2e-07,
+        "input_cost_per_video_per_second": 0.0237,
+        "litellm_provider": "vertex_ai-embedding-models",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding",
+        "output_cost_per_token": 0,
+        "output_vector_size": 3072,
+        "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing",
+        "uses_embed_content": true
+    },
+    "vertex_ai/gemini-embedding-2-preview": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "vertex_ai",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding",
+        "output_cost_per_token": 0,
+        "output_vector_size": 3072,
+        "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
+        "supports_multimodal": true,
+        "uses_embed_content": true
+    },
     "gemini-flash-experimental": {
         "input_cost_per_character": 0,
         "input_cost_per_token": 0,
@@ -14350,6 +14376,19 @@
         "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions",
         "tpm": 10000000
     },
+    "gemini/gemini-embedding-2-preview": {
+        "input_cost_per_token": 1.5e-07,
+        "litellm_provider": "gemini",
+        "max_input_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "embedding",
+        "output_cost_per_token": 0,
+        "output_vector_size": 3072,
+        "rpm": 10000,
+        "source": "https://ai.google.dev/gemini-api/docs/embeddings#multimodal",
+        "supports_multimodal": true,
+        "tpm": 10000000
+    },
     "gemini/gemini-1.5-flash": {
         "deprecation_date": "2025-09-29",
         "input_cost_per_token": 7.5e-08,