diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index c75a67cfc19..900894f74d6 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.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/local_testing/test_amazing_vertex_completion.py b/tests/local_testing/test_amazing_vertex_completion.py index 4d3b356bac4..58cd2477bf1 100644 --- a/tests/local_testing/test_amazing_vertex_completion.py +++ b/tests/local_testing/test_amazing_vertex_completion.py @@ -891,7 +891,7 @@ async def test_partner_models_httpx(model, region, sync_mode): "model,region", [ # vertex_ai/meta/llama-4-scout-17b-16e-instruct-maas removed - consistently returns 400 BadRequest on Vertex AI - ("vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas", "us-south1"), + # vertex_ai/qwen/qwen3-coder-480b-a35b-instruct-maas removed - us-south1 endpoint unavailable in CI ( "vertex_ai/mistral-small-2503", "us-central1", diff --git a/tests/local_testing/test_custom_callback_input.py b/tests/local_testing/test_custom_callback_input.py index 6bbeb3f5a54..fcdfcfe6e70 100644 --- a/tests/local_testing/test_custom_callback_input.py +++ b/tests/local_testing/test_custom_callback_input.py @@ -1085,7 +1085,10 @@ def test_standard_logging_payload(model, turn_off_message_logging): if turn_off_message_logging: print("checks redacted-by-litellm") assert "redacted-by-litellm" == slobject["messages"][0]["content"] - assert {"text": "redacted-by-litellm"} == slobject["response"] + # response is a full ModelResponse dict (choices format) since d84e5e381acf + response = slobject["response"] + assert response["choices"][0]["message"]["content"] == "redacted-by-litellm" + assert response["choices"][0]["message"].get("audio") is None @pytest.mark.parametrize( @@ -1185,7 +1188,10 @@ def test_standard_logging_payload_audio(turn_off_message_logging, stream): if turn_off_message_logging: print("checks redacted-by-litellm") assert "redacted-by-litellm" == slobject["messages"][0]["content"] - assert {"text": "redacted-by-litellm"} == slobject["response"] + # response is a full ModelResponse dict (choices format) since d84e5e381acf + response = slobject["response"] + assert response["choices"][0]["message"]["content"] == "redacted-by-litellm" + assert response["choices"][0]["message"].get("audio") is None @pytest.mark.skip(reason="Works locally. Flaky on ci/cd")