From cfa16a320c9cb8de147088b10085a0e044e9e920 Mon Sep 17 00:00:00 2001 From: "devin-ai-integration[bot]" <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Sat, 31 Oct 2026 00:15:25 +0000 Subject: [PATCH 1/3] fix(databricks): mark audio and video input support on the Gemini 3.5 to 3.8 Flash rows --- ...odel_prices_and_context_window_backup.json | 30 ++++++++++++------- model_prices_and_context_window.json | 30 ++++++++++++------- 2 files changed, 40 insertions(+), 20 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index ce85f93f7f7..65b1bdf0a8e 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -22064,7 +22064,7 @@ }, "mode": "chat", "output_cost_per_token": 3.74997e-06, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22082,7 +22082,9 @@ "input_cost_per_token_priority": 1.35002e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.3503e-07, - "cache_creation_input_token_cost_priority": 1.35002e-06 + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-7-flash": { "cache_creation_input_token_cost": 7.4998e-07, @@ -22096,7 +22098,7 @@ }, "mode": "chat", "output_cost_per_token": 3.74997e-06, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22114,7 +22116,9 @@ "input_cost_per_token_priority": 1.35002e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.3503e-07, - "cache_creation_input_token_cost_priority": 1.35002e-06 + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-6-flash": { "cache_creation_input_token_cost": 7.4998e-07, @@ -22130,7 +22134,7 @@ "mode": "chat", "output_cost_per_token": 3.74997e-06, "output_dbu_cost_per_token": 5.3571e-05, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22149,7 +22153,9 @@ "input_cost_per_token_priority": 1.35002e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.3503e-07, - "cache_creation_input_token_cost_priority": 1.35002e-06 + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash": { "cache_creation_input_token_cost": 1.87502e-06, @@ -22165,7 +22171,7 @@ "mode": "chat", "output_cost_per_token": 1.124998e-05, "output_dbu_cost_per_token": 0.000160714, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22183,7 +22189,9 @@ "input_cost_per_token_priority": 3.37498e-06, "output_cost_per_token_priority": 2.025002e-05, "cache_read_input_token_cost_priority": 3.3747e-07, - "cache_creation_input_token_cost_priority": 3.37498e-06 + "cache_creation_input_token_cost_priority": 3.37498e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash-lite": { "cache_creation_input_token_cost": 3.7499e-07, @@ -22199,7 +22207,7 @@ "mode": "chat", "output_cost_per_token": 3.12501e-06, "output_dbu_cost_per_token": 4.4643e-05, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22219,7 +22227,9 @@ "input_cost_per_token_priority": 6.7501e-07, "output_cost_per_token_priority": 5.62499e-06, "cache_read_input_token_cost_priority": 6.748e-08, - "cache_creation_input_token_cost_priority": 6.7501e-07 + "cache_creation_input_token_cost_priority": 6.7501e-07, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index ce85f93f7f7..65b1bdf0a8e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -22064,7 +22064,7 @@ }, "mode": "chat", "output_cost_per_token": 3.74997e-06, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22082,7 +22082,9 @@ "input_cost_per_token_priority": 1.35002e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.3503e-07, - "cache_creation_input_token_cost_priority": 1.35002e-06 + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-7-flash": { "cache_creation_input_token_cost": 7.4998e-07, @@ -22096,7 +22098,7 @@ }, "mode": "chat", "output_cost_per_token": 3.74997e-06, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22114,7 +22116,9 @@ "input_cost_per_token_priority": 1.35002e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.3503e-07, - "cache_creation_input_token_cost_priority": 1.35002e-06 + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-6-flash": { "cache_creation_input_token_cost": 7.4998e-07, @@ -22130,7 +22134,7 @@ "mode": "chat", "output_cost_per_token": 3.74997e-06, "output_dbu_cost_per_token": 5.3571e-05, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22149,7 +22153,9 @@ "input_cost_per_token_priority": 1.35002e-06, "output_cost_per_token_priority": 6.75003e-06, "cache_read_input_token_cost_priority": 1.3503e-07, - "cache_creation_input_token_cost_priority": 1.35002e-06 + "cache_creation_input_token_cost_priority": 1.35002e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash": { "cache_creation_input_token_cost": 1.87502e-06, @@ -22165,7 +22171,7 @@ "mode": "chat", "output_cost_per_token": 1.124998e-05, "output_dbu_cost_per_token": 0.000160714, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22183,7 +22189,9 @@ "input_cost_per_token_priority": 3.37498e-06, "output_cost_per_token_priority": 2.025002e-05, "cache_read_input_token_cost_priority": 3.3747e-07, - "cache_creation_input_token_cost_priority": 3.37498e-06 + "cache_creation_input_token_cost_priority": 3.37498e-06, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemini-3-5-flash-lite": { "cache_creation_input_token_cost": 3.7499e-07, @@ -22199,7 +22207,7 @@ "mode": "chat", "output_cost_per_token": 3.12501e-06, "output_dbu_cost_per_token": 4.4643e-05, - "source": "https://www.databricks.com/product/pricing/proprietary-foundation-model-serving", + "source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models", "supported_modalities": [ "text", "image", @@ -22219,7 +22227,9 @@ "input_cost_per_token_priority": 6.7501e-07, "output_cost_per_token_priority": 5.62499e-06, "cache_read_input_token_cost_priority": 6.748e-08, - "cache_creation_input_token_cost_priority": 6.7501e-07 + "cache_creation_input_token_cost_priority": 6.7501e-07, + "supports_audio_input": true, + "supports_video_input": true }, "databricks/databricks-gemma-3-12b": { "cache_creation_input_token_cost": 1.5001e-07, From e6e8dc516a543633ba1bcbc925b2c0ef17cdf4f1 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Sat, 31 Oct 2026 13:11:00 +0000 Subject: [PATCH 2/3] fix(model_prices): add Vertex AI and Together AI retirement dates Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- litellm/model_prices_and_context_window_backup.json | 7 +++++++ model_prices_and_context_window.json | 7 +++++++ 2 files changed, 14 insertions(+) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 38b9f3b86a5..be235a18929 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -29429,6 +29429,7 @@ "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { + "deprecation_date": "2027-06-28", "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, @@ -30428,6 +30429,7 @@ "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.8-flash": { + "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, @@ -30534,6 +30536,7 @@ "supports_native_streaming": true }, "vertex_ai/gemini-3.8-live": { + "deprecation_date": "2027-09-25", "gemini_audio_only_live": true, "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, @@ -32706,6 +32709,7 @@ "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.8-flash": { + "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, @@ -48964,6 +48968,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { + "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", @@ -52683,6 +52688,7 @@ }, "vertex_ai/gemini-3.1-flash-lite-image": { + "deprecation_date": "2027-06-28", "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, @@ -76783,6 +76789,7 @@ "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-4-argon": { + "deprecation_date": "2027-10-13", "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_flex": 5e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 38b9f3b86a5..be235a18929 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -29429,6 +29429,7 @@ "web_search_billing_unit": "per_query" }, "gemini-3.1-flash-lite-image": { + "deprecation_date": "2027-06-28", "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, @@ -30428,6 +30429,7 @@ "google_maps_grounding_cost_per_query": 0.014 }, "vertex_ai/gemini-3.8-flash": { + "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, @@ -30534,6 +30536,7 @@ "supports_native_streaming": true }, "vertex_ai/gemini-3.8-live": { + "deprecation_date": "2027-09-25", "gemini_audio_only_live": true, "input_cost_per_audio_token": 3e-06, "input_cost_per_image_token": 1e-06, @@ -32706,6 +32709,7 @@ "google_maps_grounding_cost_per_query": 0.014 }, "gemini-3.8-flash": { + "deprecation_date": "2027-09-02", "cache_read_input_token_cost": 7.5e-08, "cache_read_input_token_cost_batches": 3.75e-08, "cache_read_input_token_cost_flex": 3.75e-08, @@ -48964,6 +48968,7 @@ "source": "https://api.together.ai/v1/models" }, "together_ai/Qwen/Qwen3.8-2.4T-A95B": { + "deprecation_date": "2026-11-04", "cache_read_input_token_cost": 2.5e-07, "input_cost_per_token": 2e-06, "litellm_provider": "together_ai", @@ -52683,6 +52688,7 @@ }, "vertex_ai/gemini-3.1-flash-lite-image": { + "deprecation_date": "2027-06-28", "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, @@ -76783,6 +76789,7 @@ "web_search_billing_unit": "per_query" }, "vertex_ai/gemini-4-argon": { + "deprecation_date": "2027-10-13", "cache_read_input_token_cost": 1e-07, "cache_read_input_token_cost_batches": 5e-08, "cache_read_input_token_cost_flex": 5e-08, From 0b71cc8e0ce47d7de3d079022f230374f19bb87d Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Sat, 31 Oct 2026 19:16:58 +0000 Subject: [PATCH 3/3] fix(model_prices): correct perplexity agent api pricing and add gemini-4-argon, nemotron-3.5-super Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- ...odel_prices_and_context_window_backup.json | 24 ++++++++++++++++++- model_prices_and_context_window.json | 24 ++++++++++++++++++- 2 files changed, 46 insertions(+), 2 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index fd396219dcd..47c4617a479 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -69560,6 +69560,14 @@ "cache_read_input_token_cost": 3e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/google/gemini-4-argon": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/google/gemini-3.6-flash": { "litellm_provider": "perplexity", "mode": "responses", @@ -69687,6 +69695,14 @@ "cache_read_input_token_cost": 1.15e-09, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/perplexity/nemotron-3.5-super-120b-a12b": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/perplexity/nemotron-3-ultra-550b-a55b": { "litellm_provider": "perplexity", "mode": "responses", @@ -74795,7 +74811,7 @@ "supports_function_calling": true, "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-fable-5-1": { @@ -74843,6 +74859,9 @@ "output_cost_per_token": 5e-05, "cache_read_input_token_cost": 1e-06, "cache_creation_input_token_cost": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-6-luna": { @@ -76308,6 +76327,9 @@ "input_cost_per_token": 1e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "us-gov.anthropic.claude-haiku-5-5": { diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index fd396219dcd..47c4617a479 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -69560,6 +69560,14 @@ "cache_read_input_token_cost": 3e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/google/gemini-4-argon": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-06, + "output_cost_per_token": 1e-05, + "cache_read_input_token_cost": 1e-07, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/google/gemini-3.6-flash": { "litellm_provider": "perplexity", "mode": "responses", @@ -69687,6 +69695,14 @@ "cache_read_input_token_cost": 1.15e-09, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, + "perplexity/perplexity/nemotron-3.5-super-120b-a12b": { + "litellm_provider": "perplexity", + "mode": "responses", + "input_cost_per_token": 2e-07, + "output_cost_per_token": 5e-07, + "cache_read_input_token_cost": 4e-08, + "source": "https://docs.perplexity.ai/docs/agent-api/models" + }, "perplexity/perplexity/nemotron-3-ultra-550b-a55b": { "litellm_provider": "perplexity", "mode": "responses", @@ -74795,7 +74811,7 @@ "supports_function_calling": true, "input_cost_per_token": 2e-06, "output_cost_per_token": 1e-05, - "cache_read_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1e-07, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/anthropic/claude-fable-5-1": { @@ -74843,6 +74859,9 @@ "output_cost_per_token": 5e-05, "cache_read_input_token_cost": 1e-06, "cache_creation_input_token_cost": 1.25e-05, + "input_cost_per_token_above_272k_tokens": 2e-05, + "output_cost_per_token_above_272k_tokens": 7.5e-05, + "cache_read_input_token_cost_above_272k_tokens": 2e-06, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "perplexity/openai/gpt-6-luna": { @@ -76308,6 +76327,9 @@ "input_cost_per_token": 1e-07, "output_cost_per_token": 5e-07, "cache_read_input_token_cost": 1e-08, + "input_cost_per_token_above_100k_tokens": 5e-07, + "output_cost_per_token_above_100k_tokens": 2.5e-06, + "cache_read_input_token_cost_above_100k_tokens": 5e-08, "source": "https://docs.perplexity.ai/docs/agent-api/models" }, "us-gov.anthropic.claude-haiku-5-5": {