diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 8897e330f42..fb80de3e77d 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -38967,6 +38967,49 @@ ], "supports_audio_input": true }, + "meta/muse-wonder-1.0": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "meta_llama/Llama-3.3-70B-Instruct": { "litellm_provider": "meta_llama", "max_input_tokens": 128000, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 8897e330f42..fb80de3e77d 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -38967,6 +38967,49 @@ ], "supports_audio_input": true }, + "meta/muse-wonder-1.0": { + "cache_read_input_token_cost": 2e-07, + "input_cost_per_token": 4e-06, + "litellm_provider": "meta", + "max_input_tokens": 1048576, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 2e-05, + "search_context_cost_per_query": { + "search_context_size_high": 0.0025, + "search_context_size_low": 0.0025, + "search_context_size_medium": 0.0025 + }, + "source": "https://dev.meta.ai/docs/pricing-rate-limits", + "supported_endpoints": [ + "/v1/chat/completions", + "/v1/responses", + "/v1/messages" + ], + "supported_modalities": [ + "text", + "image", + "video" + ], + "supported_output_modalities": [ + "text" + ], + "supports_function_calling": true, + "supports_max_reasoning_effort": true, + "supports_minimal_reasoning_effort": true, + "supports_none_reasoning_effort": false, + "supports_parallel_function_calling": true, + "supports_pdf_input": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_system_messages": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_web_search": true, + "supports_xhigh_reasoning_effort": true + }, "meta_llama/Llama-3.3-70B-Instruct": { "litellm_provider": "meta_llama", "max_input_tokens": 128000, diff --git a/tests/unit/test_muse_spark_1_3_model_metadata.py b/tests/unit/test_muse_spark_1_3_model_metadata.py index 4392553fcc3..049fb988fd5 100644 --- a/tests/unit/test_muse_spark_1_3_model_metadata.py +++ b/tests/unit/test_muse_spark_1_3_model_metadata.py @@ -6,9 +6,11 @@ import pytest import litellm from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider from litellm.litellm_core_utils.llm_cost_calc.tool_call_cost_tracking import StandardBuiltInToolCostTracking +from litellm.router_utils.reasoning_effort_capability import resolve_supported_reasoning_efforts MUSE_SPARK_STANDARD = "meta/muse-spark-1.3" MUSE_SPARK_CONTRIBUTOR = "meta/muse-spark-1.3-contributor" +MUSE_WONDER = "meta/muse-wonder-1.0" WEB_SEARCH_COST_PER_QUERY = 0.0025 PRICING = ( @@ -22,7 +24,7 @@ def _load_cost_map(filename: str = "model_prices_and_context_window.json") -> di return json.load(f) -@pytest.mark.parametrize("model", (MUSE_SPARK_STANDARD, MUSE_SPARK_CONTRIBUTOR)) +@pytest.mark.parametrize("model", (MUSE_SPARK_STANDARD, MUSE_SPARK_CONTRIBUTOR, MUSE_WONDER)) def test_muse_spark_1_3_routes_to_meta_model_api(model: str): routed_model, provider, _, api_base = get_llm_provider(model=model, api_key="sk-test") @@ -31,7 +33,7 @@ def test_muse_spark_1_3_routes_to_meta_model_api(model: str): assert api_base == "https://api.meta.ai/v1" -@pytest.mark.parametrize("model", (MUSE_SPARK_STANDARD, MUSE_SPARK_CONTRIBUTOR)) +@pytest.mark.parametrize("model", (MUSE_SPARK_STANDARD, MUSE_SPARK_CONTRIBUTOR, MUSE_WONDER)) def test_muse_spark_1_3_backup_matches_main(model: str): """Ensure the bundled model cost map stays in sync with the canonical file.""" main_cost = _load_cost_map() @@ -40,6 +42,18 @@ def test_muse_spark_1_3_backup_matches_main(model: str): assert backup_cost.get(model) == main_cost.get(model), f"{model} differs between main and backup model cost maps" +def test_muse_wonder_reasoning_efforts_include_max_and_exclude_none(): + entry = dict(_load_cost_map()[MUSE_WONDER]) + entry["key"] = MUSE_WONDER + + resolved = resolve_supported_reasoning_efforts(entry, deployment_is_mapped=True) + + assert resolved is not None + assert "max" in resolved + assert "xhigh" in resolved + assert "none" not in resolved + + def test_muse_spark_contributor_tier_is_cheaper_than_standard(): cost_map = _load_cost_map() standard = cost_map[MUSE_SPARK_STANDARD]