From dfe2f6f99150f968f3e589ced6323215d94594b1 Mon Sep 17 00:00:00 2001 From: Cursor Agent Date: Sat, 7 Mar 2026 02:47:11 +0000 Subject: [PATCH] fix: add /vertex_ai/live to supported endpoints and azure gpt-5.1 reasoning flags - Add /vertex_ai/live to JSON schema validation enum in test_utils.py - Add supports_none_reasoning_effort=true to 10 azure/gpt-5.1 model entries (matching the OpenAI gpt-5.1 behavior) Co-authored-by: Ishaan Jaff --- model_prices_and_context_window.json | 50 +++++++++++++++++----------- tests/test_litellm/test_utils.py | 1 + 2 files changed, 31 insertions(+), 20 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index c75a67cfc19..900894f74d6 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -2110,7 +2110,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/eu/gpt-5.1-chat": { "cache_read_input_token_cost": 1.4e-07, @@ -2143,7 +2144,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/eu/gpt-5.1-codex": { "cache_read_input_token_cost": 1.4e-07, @@ -2410,7 +2412,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/global/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -2443,7 +2446,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/global/gpt-5.1-codex": { "cache_read_input_token_cost": 1.25e-07, @@ -3456,7 +3460,8 @@ "supports_system_messages": true, "supports_tool_choice": true, "supports_service_tier": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/gpt-5.1-chat-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -3491,7 +3496,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": false, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/gpt-5.1-codex-2025-11-13": { "cache_read_input_token_cost": 1.25e-07, @@ -3906,7 +3912,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/gpt-5.1-chat": { "cache_read_input_token_cost": 1.25e-07, @@ -3939,7 +3946,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/gpt-5.1-codex": { "cache_read_input_token_cost": 1.25e-07, @@ -5273,7 +5281,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/us/gpt-5.1-chat": { "cache_read_input_token_cost": 1.4e-07, @@ -5306,7 +5315,8 @@ "supports_response_schema": true, "supports_system_messages": true, "supports_tool_choice": true, - "supports_vision": true + "supports_vision": true, + "supports_none_reasoning_effort": true }, "azure/us/gpt-5.1-codex": { "cache_read_input_token_cost": 1.4e-07, @@ -21068,18 +21078,18 @@ "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_priority": 6e-05, - "input_cost_per_token_above_272k_tokens_priority": 1.2e-04, + "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.8e-04, - "output_cost_per_token_above_272k_tokens": 2.7e-04, + "output_cost_per_token": 0.00018, + "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "output_cost_per_token_priority": 2.7e-04, - "output_cost_per_token_above_272k_tokens_priority": 4.05e-04, + "output_cost_per_token_priority": 0.00027, + "output_cost_per_token_above_272k_tokens_priority": 0.000405, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", @@ -21117,18 +21127,18 @@ "input_cost_per_token_flex": 1.5e-05, "input_cost_per_token_batches": 1.5e-05, "input_cost_per_token_priority": 6e-05, - "input_cost_per_token_above_272k_tokens_priority": 1.2e-04, + "input_cost_per_token_above_272k_tokens_priority": 0.00012, "litellm_provider": "openai", "max_input_tokens": 1050000, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 1.8e-04, - "output_cost_per_token_above_272k_tokens": 2.7e-04, + "output_cost_per_token": 0.00018, + "output_cost_per_token_above_272k_tokens": 0.00027, "output_cost_per_token_flex": 9e-05, "output_cost_per_token_batches": 9e-05, - "output_cost_per_token_priority": 2.7e-04, - "output_cost_per_token_above_272k_tokens_priority": 4.05e-04, + "output_cost_per_token_priority": 0.00027, + "output_cost_per_token_above_272k_tokens_priority": 0.000405, "supported_endpoints": [ "/v1/chat/completions", "/v1/batch", diff --git a/tests/test_litellm/test_utils.py b/tests/test_litellm/test_utils.py index 27e6363e53d..c2df3db0e30 100644 --- a/tests/test_litellm/test_utils.py +++ b/tests/test_litellm/test_utils.py @@ -764,6 +764,7 @@ def test_aaamodel_prices_and_context_window_json_is_valid(): "/v1/audio/transcriptions", "/v1/audio/speech", "/v1/ocr", + "/vertex_ai/live", ], }, },