From b9b715157bfdd7fc7eda91eb07169be3d6447f0f Mon Sep 17 00:00:00 2001 From: mubashir1osmani Date: Mon, 18 May 2026 23:27:52 -0400 Subject: [PATCH] gemini-3.1-flash-lite pricing (#27933) * feat(model_prices): add gemini-3.1-flash-lite pricing with standard/batch/flex/priority tiers * fix pricing * add service tier --------- Co-authored-by: shin-berri --- model_prices_and_context_window.json | 67 +++++++++++++++++++--------- 1 file changed, 47 insertions(+), 20 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 31a5993a240..2140493ec4a 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -15006,10 +15006,16 @@ "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, + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, @@ -15021,9 +15027,12 @@ "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", + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -17128,10 +17137,16 @@ "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, + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "gemini", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, @@ -17143,10 +17158,13 @@ "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, + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, "rpm": 15, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "supported_endpoints": [ "/v1/chat/completions", "/v1/completions", @@ -33932,10 +33950,16 @@ "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, + "cache_read_input_token_cost": 2.5e-08, + "cache_read_input_token_cost_batches": 1.25e-08, + "cache_read_input_token_cost_flex": 1.25e-08, + "cache_read_input_token_cost_per_audio_token": 5e-08, + "cache_read_input_token_cost_priority": 4.5e-08, + "input_cost_per_audio_token": 5e-07, + "input_cost_per_token": 2.5e-07, + "input_cost_per_token_batches": 1.25e-07, + "input_cost_per_token_flex": 1.25e-07, + "input_cost_per_token_priority": 4.5e-07, "litellm_provider": "vertex_ai-language-models", "max_audio_length_hours": 8.4, "max_audio_per_prompt": 1, @@ -33947,8 +33971,11 @@ "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, + "output_cost_per_reasoning_token": 1.5e-06, + "output_cost_per_token": 1.5e-06, + "output_cost_per_token_batches": 7.5e-07, + "output_cost_per_token_flex": 7.5e-07, + "output_cost_per_token_priority": 2.7e-06, "source": "https://cloud.google.com/vertex-ai/generative-ai/pricing#gemini-models", "supported_endpoints": [ "/v1/chat/completions",