From 89cc395a887468a86ba78c3ba6a8c6b82467cb46 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Thu, 5 Nov 2026 18:42:29 +0000 Subject: [PATCH] feat(gemini): add Omni 1.2 Flash pricing and update video model successors (#50229) --- ...odel_prices_and_context_window_backup.json | 55 +++++++++++++++---- model_prices_and_context_window.json | 55 +++++++++++++++---- tests/unit/test_utils.py | 1 + 3 files changed, 91 insertions(+), 20 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index aba1957f03c..a5b9a5cb457 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -32813,7 +32813,7 @@ "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1beta/interactions" ], @@ -32835,7 +32835,7 @@ "tpm": 800000, "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", - "successor_model": "gemini/gemini-omni-1.1-flash" + "successor_model": "gemini/gemini-omni-1.2-flash" }, "gemini/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -33619,14 +33619,14 @@ "gemini/veo-3.1-fast-generate-preview": { "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", - "successor_model": "gemini/gemini-omni-1.1-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -33637,13 +33637,13 @@ "gemini/veo-3.1-generate-preview": { "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", - "successor_model": "gemini/gemini-omni-1.1-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -33654,13 +33654,13 @@ "gemini/veo-3.1-lite-generate-preview": { "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", - "successor_model": "gemini/gemini-omni-1.1-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, - "source": "https://ai.google.dev/gemini-api/docs/video", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -67660,17 +67660,20 @@ "source": "https://deepinfra.com/pricing" }, "gemini/gemini-omni-1.1-flash": { + "deprecation_date": "2026-12-03", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "supported_endpoints": [ "/v1beta/interactions" ], @@ -86348,5 +86351,37 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": false + }, + "gemini/gemini-omni-1.2-flash": { + "input_cost_per_image_token": 1.5e-06, + "input_cost_per_token": 1.5e-06, + "input_cost_per_video_token": 1.5e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.2e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video", + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_reasoning": true, + "supports_system_messages": false, + "supports_video_input": true, + "supports_vision": true } } diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index aba1957f03c..a5b9a5cb457 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -32813,7 +32813,7 @@ "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_endpoints": [ "/v1beta/interactions" ], @@ -32835,7 +32835,7 @@ "tpm": 800000, "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", - "successor_model": "gemini/gemini-omni-1.1-flash" + "successor_model": "gemini/gemini-omni-1.2-flash" }, "gemini/gemini-3.1-pro-preview": { "prompt_cache_min_tokens": 4096, @@ -33619,14 +33619,14 @@ "gemini/veo-3.1-fast-generate-preview": { "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", - "successor_model": "gemini/gemini-omni-1.1-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.1, "output_cost_per_second_1080p": 0.12, "output_cost_per_second_4k": 0.3, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -33637,13 +33637,13 @@ "gemini/veo-3.1-generate-preview": { "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", - "successor_model": "gemini/gemini-omni-1.1-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.4, "output_cost_per_second_4k": 0.6, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -33654,13 +33654,13 @@ "gemini/veo-3.1-lite-generate-preview": { "deprecation_date": "2026-10-22", "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", - "successor_model": "gemini/gemini-omni-1.1-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "litellm_provider": "gemini", "max_input_tokens": 1024, "mode": "video_generation", "output_cost_per_second": 0.05, "output_cost_per_second_1080p": 0.08, - "source": "https://ai.google.dev/gemini-api/docs/video", + "source": "https://ai.google.dev/gemini-api/docs/deprecations", "supported_modalities": [ "text" ], @@ -67660,17 +67660,20 @@ "source": "https://deepinfra.com/pricing" }, "gemini/gemini-omni-1.1-flash": { + "deprecation_date": "2026-12-03", + "deprecation_source": "https://ai.google.dev/gemini-api/docs/deprecations", "input_cost_per_audio_token": 1.5e-06, "input_cost_per_token": 1.5e-06, "litellm_provider": "gemini", - "max_input_tokens": 1048576, + "max_input_tokens": 131072, "max_output_tokens": 65536, "mode": "chat", "output_cost_per_reasoning_token": 9e-06, "output_cost_per_token": 9e-06, "output_cost_per_video_token": 1.75e-05, "rpm": 2000, - "source": "https://ai.google.dev/gemini-api/docs/pricing", + "source": "https://ai.google.dev/gemini-api/docs/models/gemini-omni-flash", + "successor_model": "gemini/gemini-omni-1.2-flash", "supported_endpoints": [ "/v1beta/interactions" ], @@ -86348,5 +86351,37 @@ "supports_video_input": true, "supports_vision": true, "supports_web_search": false + }, + "gemini/gemini-omni-1.2-flash": { + "input_cost_per_image_token": 1.5e-06, + "input_cost_per_token": 1.5e-06, + "input_cost_per_video_token": 1.5e-06, + "litellm_provider": "gemini", + "max_input_tokens": 131072, + "max_output_tokens": 65536, + "mode": "chat", + "output_cost_per_reasoning_token": 9e-06, + "output_cost_per_token": 9e-06, + "output_cost_per_video_token": 1.2e-05, + "source": "https://ai.google.dev/gemini-api/docs/pricing", + "supported_endpoints": [ + "/v1beta/interactions" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text", + "video", + "audio" + ], + "supports_audio_input": false, + "supports_audio_output": true, + "supports_reasoning": true, + "supports_system_messages": false, + "supports_video_input": true, + "supports_vision": true } } diff --git a/tests/unit/test_utils.py b/tests/unit/test_utils.py index e24499db071..924c3738638 100644 --- a/tests/unit/test_utils.py +++ b/tests/unit/test_utils.py @@ -8393,6 +8393,7 @@ def test_get_model_info_gemini(monkeypatch): and "veo" not in model and "lyria" not in model and "robotics" not in model + and "omni" not in model and "3.8-flash-tts" not in model and "3.8-flash-lite-tts" not in model ):