From ba03f60f7143f5d5b78228b63c1a0fe8043642f8 Mon Sep 17 00:00:00 2001 From: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> Date: Wed, 16 Sep 2026 19:50:28 +0000 Subject: [PATCH] fix(models): add batch and flex tier prices on Azure dated and Gemini latest alias rows Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --- .../model_prices_and_context_window_backup.json | 16 ++++++++++++++-- model_prices_and_context_window.json | 16 ++++++++++++++-- 2 files changed, 28 insertions(+), 4 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 2575b227bfc..0f3535d9b18 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -8806,6 +8806,7 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_priority": 1.25e-05, @@ -8817,6 +8818,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, + "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, @@ -8907,9 +8909,11 @@ "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", @@ -9004,9 +9008,11 @@ "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", @@ -56989,7 +56995,10 @@ "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, @@ -57048,7 +57057,10 @@ "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 2575b227bfc..0f3535d9b18 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -8806,6 +8806,7 @@ "cache_read_input_token_cost_above_272k_tokens_priority": 2e-06, "cache_read_input_token_cost_flex": 2.5e-07, "input_cost_per_token": 5e-06, + "input_cost_per_token_batches": 2.5e-06, "input_cost_per_token_above_272k_tokens": 1e-05, "input_cost_per_token_above_272k_tokens_flex": 5e-06, "input_cost_per_token_priority": 1.25e-05, @@ -8817,6 +8818,7 @@ "max_tokens": 128000, "mode": "chat", "output_cost_per_token": 3e-05, + "output_cost_per_token_batches": 1.5e-05, "output_cost_per_token_above_272k_tokens": 4.5e-05, "output_cost_per_token_priority": 7.5e-05, "output_cost_per_token_above_272k_tokens_priority": 9e-05, @@ -8907,9 +8909,11 @@ "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", @@ -9004,9 +9008,11 @@ "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, "cache_read_input_token_cost_priority": 1.375e-06, "input_cost_per_token": 5.5e-06, + "input_cost_per_token_batches": 2.75e-06, "input_cost_per_token_above_272k_tokens": 1.1e-05, "input_cost_per_token_priority": 1.375e-05, "output_cost_per_token": 3.3e-05, + "output_cost_per_token_batches": 1.65e-05, "output_cost_per_token_above_272k_tokens": 4.95e-05, "output_cost_per_token_priority": 8.25e-05, "litellm_provider": "azure", @@ -56989,7 +56995,10 @@ "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini/gemini-pro-latest": { "cache_read_input_token_cost": 2e-07, @@ -57048,7 +57057,10 @@ "prompt_cache_min_tokens": 4096, "supports_native_streaming": true, "supports_url_context": true, - "web_search_billing_unit": "per_query" + "web_search_billing_unit": "per_query", + "cache_read_input_token_cost_flex": 2e-07, + "input_cost_per_token_flex": 1e-06, + "output_cost_per_token_flex": 6e-06 }, "gemini-exp-1206": { "cache_read_input_token_cost": 3e-08,