From 18e7eaaddbf7876145bc12709ac041e6a3cfb0b1 Mon Sep 17 00:00:00 2001 From: Seongbin Lim <58146755+sbinnee@users.noreply.github.com> Date: Fri, 31 Oct 2025 09:39:19 +0900 Subject: [PATCH] Add gemini/gemini-embedding-001 pricing entry for Google GenAI API (#16078) * Add gemini/gemini-embedding-001 pricing entry for Google GenAI API Add pricing and configuration entry for "gemini/gemini-embedding-001" model when called via Google GenAI API (google-genai provider). This mirrors the existing Vertex AI entry ("gemini-embedding-001") but uses the 'gemini' provider instead. Co-Authored-By: Claude * Update tpm and rpm for gemini/gemini-embedding-001 --------- Co-authored-by: Claude --- litellm/model_prices_and_context_window_backup.json | 12 ++++++++++++ model_prices_and_context_window.json | 12 ++++++++++++ 2 files changed, 24 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 5b3446721f..7103ffd457 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -10509,6 +10509,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "gemini/gemini-embedding-001": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", + "tpm": 10000000 + }, "gemini/gemini-1.5-flash": { "input_cost_per_token": 7.5e-08, "input_cost_per_token_above_128k_tokens": 1.5e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 5b3446721f..7103ffd457 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -10509,6 +10509,18 @@ "supports_tool_choice": true, "supports_vision": true }, + "gemini/gemini-embedding-001": { + "input_cost_per_token": 1.5e-07, + "litellm_provider": "gemini", + "max_input_tokens": 2048, + "max_tokens": 2048, + "mode": "embedding", + "output_cost_per_token": 0, + "output_vector_size": 3072, + "rpm": 10000, + "source": "https://ai.google.dev/gemini-api/docs/embeddings#model-versions", + "tpm": 10000000 + }, "gemini/gemini-1.5-flash": { "input_cost_per_token": 7.5e-08, "input_cost_per_token_above_128k_tokens": 1.5e-07,