diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 3b35f160528..f8a537fb922 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -16690,6 +16690,46 @@ "supports_tool_choice": true, "supports_vision": true }, + "dashscope/qwen3.8-flash": { + "cache_creation_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "dashscope/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "dashscope/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "dashscope", @@ -18594,6 +18634,46 @@ "supports_tool_choice": true, "supports_vision": true }, + "qwen_ai_platform/qwen3.8-flash": { + "cache_creation_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "qwen_ai_platform/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "qwen_ai_platform/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "qwen_ai_platform", @@ -22090,8 +22170,8 @@ "embed-english-light-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -22108,8 +22188,8 @@ "input_cost_per_image": 0.0001, "input_cost_per_token": 1e-07, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -22130,8 +22210,8 @@ "embed-multilingual-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -22139,8 +22219,8 @@ "embed-multilingual-light-v3.0": { "input_cost_per_token": 0.0001, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -57910,14 +57990,14 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-5.6-sol": { - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, @@ -65816,9 +65896,9 @@ "supports_web_search": false }, "openrouter/z-ai/glm-5.3": { - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 9.1e-07, + "output_cost_per_token": 2.86e-06, + "cache_read_input_token_cost": 1.69e-07, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943717, @@ -70539,14 +70619,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-flash-latest": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 4.2e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -70831,14 +70911,14 @@ "supports_web_search": false }, "openrouter/~z-ai/glm-latest": { - "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost": 1.46625e-07, "input_cost_per_token": 9e-07, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 235929, "max_tokens": 235929, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 2.805e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73982,14 +74062,14 @@ "supports_web_search": false }, "openrouter/tencent/hy3": { - "cache_read_input_token_cost": 3.3e-08, - "input_cost_per_token": 1.32e-07, + "cache_read_input_token_cost": 2.0625e-08, + "input_cost_per_token": 8.25e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.28e-07, + "output_cost_per_token": 3.3e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 3b35f160528..f8a537fb922 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -16690,6 +16690,46 @@ "supports_tool_choice": true, "supports_vision": true }, + "dashscope/qwen3.8-flash": { + "cache_creation_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "dashscope/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "dashscope", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "dashscope/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "dashscope", @@ -18594,6 +18634,46 @@ "supports_tool_choice": true, "supports_vision": true }, + "qwen_ai_platform/qwen3.8-flash": { + "cache_creation_input_token_cost": 2e-07, + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, + "qwen_ai_platform/qwen3.8-omni-flash": { + "cache_read_input_token_cost": 1.6e-08, + "input_cost_per_token": 1.5e-07, + "litellm_provider": "qwen_ai_platform", + "max_input_tokens": 991808, + "max_output_tokens": 131072, + "max_tokens": 131072, + "mode": "chat", + "output_cost_per_token": 4.7e-07, + "source": "https://docs.modelstudio.console.alibabacloud.com/en/model-studio/model-pricing", + "supports_audio_input": true, + "supports_function_calling": true, + "supports_prompt_caching": true, + "supports_reasoning": true, + "supports_response_schema": true, + "supports_tool_choice": true, + "supports_video_input": true, + "supports_vision": true, + "supports_web_search": true + }, "qwen_ai_platform/qwq-plus": { "input_cost_per_token": 8e-07, "litellm_provider": "qwen_ai_platform", @@ -22090,8 +22170,8 @@ "embed-english-light-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0 }, @@ -22108,8 +22188,8 @@ "input_cost_per_image": 0.0001, "input_cost_per_token": 1e-07, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "metadata": { "notes": "'supports_image_input' is a deprecated field. Use 'supports_embedding_image_input' instead." }, @@ -22130,8 +22210,8 @@ "embed-multilingual-v3.0": { "input_cost_per_token": 1e-07, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -22139,8 +22219,8 @@ "embed-multilingual-light-v3.0": { "input_cost_per_token": 0.0001, "litellm_provider": "cohere", - "max_input_tokens": 1024, - "max_tokens": 1024, + "max_input_tokens": 512, + "max_tokens": 512, "mode": "embedding", "output_cost_per_token": 0.0, "supports_embedding_image_input": true @@ -57910,14 +57990,14 @@ "supports_tool_choice": true }, "bedrock_mantle/openai.gpt-5.6-sol": { - "input_cost_per_token": 5.5e-06, - "input_cost_per_token_above_272k_tokens": 1.1e-05, - "cache_creation_input_token_cost": 6.875e-06, - "cache_creation_input_token_cost_above_272k_tokens": 1.375e-05, - "cache_read_input_token_cost": 5.5e-07, - "cache_read_input_token_cost_above_272k_tokens": 1.1e-06, - "output_cost_per_token": 3.3e-05, - "output_cost_per_token_above_272k_tokens": 4.95e-05, + "input_cost_per_token": 4.4e-06, + "input_cost_per_token_above_272k_tokens": 8.8e-06, + "cache_creation_input_token_cost": 5.5e-06, + "cache_creation_input_token_cost_above_272k_tokens": 1.1e-05, + "cache_read_input_token_cost": 4.4e-07, + "cache_read_input_token_cost_above_272k_tokens": 8.8e-07, + "output_cost_per_token": 2.2e-05, + "output_cost_per_token_above_272k_tokens": 3.3e-05, "search_context_cost_per_query": { "search_context_size_high": 0.012, "search_context_size_low": 0.012, @@ -65816,9 +65896,9 @@ "supports_web_search": false }, "openrouter/z-ai/glm-5.3": { - "input_cost_per_token": 1.4e-06, - "output_cost_per_token": 4.4e-06, - "cache_read_input_token_cost": 2.6e-07, + "input_cost_per_token": 9.1e-07, + "output_cost_per_token": 2.86e-06, + "cache_read_input_token_cost": 1.69e-07, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 943717, @@ -70539,14 +70619,14 @@ "supports_web_search": false }, "openrouter/~deepseek/deepseek-flash-latest": { - "cache_read_input_token_cost": 1.5e-08, - "input_cost_per_token": 1.5e-07, + "cache_read_input_token_cost": 4.2e-09, + "input_cost_per_token": 1.4e-07, "litellm_provider": "openrouter", "max_input_tokens": 1048576, "max_output_tokens": 393216, "max_tokens": 393216, "mode": "chat", - "output_cost_per_token": 6e-07, + "output_cost_per_token": 4.2e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -70831,14 +70911,14 @@ "supports_web_search": false }, "openrouter/~z-ai/glm-latest": { - "cache_read_input_token_cost": 1.5e-07, + "cache_read_input_token_cost": 1.46625e-07, "input_cost_per_token": 9e-07, "litellm_provider": "openrouter", "max_input_tokens": 1310720, "max_output_tokens": 235929, "max_tokens": 235929, "mode": "chat", - "output_cost_per_token": 3e-06, + "output_cost_per_token": 2.805e-06, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, @@ -73982,14 +74062,14 @@ "supports_web_search": false }, "openrouter/tencent/hy3": { - "cache_read_input_token_cost": 3.3e-08, - "input_cost_per_token": 1.32e-07, + "cache_read_input_token_cost": 2.0625e-08, + "input_cost_per_token": 8.25e-08, "litellm_provider": "openrouter", "max_input_tokens": 262144, "max_output_tokens": 128000, "max_tokens": 128000, "mode": "chat", - "output_cost_per_token": 5.28e-07, + "output_cost_per_token": 3.3e-07, "source": "https://openrouter.ai/api/v1/models", "supports_audio_input": false, "supports_function_calling": true, diff --git a/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py b/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py index 901c005f5a3..951911ac066 100644 --- a/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py +++ b/tests/test_litellm/llms/bedrock_mantle/test_bedrock_mantle_responses_transformation.py @@ -1839,6 +1839,27 @@ class TestBedrockMantleResponsesSigV4: class TestBedrockMantleResponsesPricing: + @pytest.mark.parametrize( + "model", + ["openai.gpt-5.6-sol", "openai.gpt-5.6-terra", "openai.gpt-5.6-luna"], + ) + def test_mantle_matches_in_region_converse_pricing(self, local_cost_map, model): + """bedrock-mantle serves these models In-Region only, and the AWS model + cards price In-Region and Geo CRIS identically -- so every cost field on + the mantle key must equal the `us.` converse key. A price change applied + to one namespace but not the other shows up here. + """ + mantle = litellm.model_cost[f"bedrock_mantle/{model}"] + converse = litellm.model_cost[f"us.{model}"] + + cost_fields = [k for k in converse if "cost" in k and k != "search_context_cost_per_query"] + assert cost_fields, "expected cost fields on the converse entry" + for field in cost_fields: + assert mantle.get(field) == pytest.approx(converse[field]), ( + f"{model}: {field} is {mantle.get(field)} on bedrock_mantle " + f"but {converse[field]} on us. (bedrock_converse)" + ) + def test_models_registered(self, local_cost_map): assert "bedrock_mantle/openai.gpt-5.5" in litellm.bedrock_mantle_models assert "bedrock_mantle/openai.gpt-5.4" in litellm.bedrock_mantle_models diff --git a/tests/test_litellm/proxy/test_proxy_server.py b/tests/test_litellm/proxy/test_proxy_server.py index 3615946e67a..139fe2cce15 100644 --- a/tests/test_litellm/proxy/test_proxy_server.py +++ b/tests/test_litellm/proxy/test_proxy_server.py @@ -7591,25 +7591,35 @@ async def test_deleting_the_stored_pass_through_row_takes_the_route_out_of_servi deleted. The proxy's own registry of live pass-through routes is what decides whether a request is routed upstream or falls through to the auth error, so it has to lose the entry on the reload rather than at the next process restart.""" - from litellm.proxy.pass_through_endpoints.pass_through_endpoints import InitPassThroughEndpointHelpers - from litellm.proxy.proxy_server import ProxyConfig + from litellm.proxy.pass_through_endpoints.pass_through_endpoints import ( + InitPassThroughEndpointHelpers, + _registered_pass_through_routes, + ) + from litellm.proxy.proxy_server import ProxyConfig, app path: Final = f"/v1/deleted-{uuid.uuid4().hex[:8]}" db_endpoint: Final = {"id": "db-1", "path": path, "target": "https://example.com/post"} + prior_routes: Final = list(app.routes) + prior_registry: Final = dict(_registered_pass_through_routes) def live_routes() -> set[str]: return {route for route in InitPassThroughEndpointHelpers.get_all_registered_pass_through_routes() if path in route} settings: Final = patch("litellm.proxy.proxy_server.general_settings", {}) # test-quality-ok: the method reads this module global; no injection seam yaml_endpoints: Final = patch("litellm.proxy.proxy_server.config_passthrough_endpoints", None) # test-quality-ok: module global holding the YAML endpoints; this case has none - with settings, yaml_endpoints: - pc = ProxyConfig() - await pc._update_general_settings(db_general_settings={"pass_through_endpoints": [db_endpoint]}) - assert live_routes(), "the stored endpoint should be serving before the row is deleted" + try: + with settings, yaml_endpoints: + pc = ProxyConfig() + await pc._update_general_settings(db_general_settings={"pass_through_endpoints": [db_endpoint]}) + assert live_routes(), "the stored endpoint should be serving before the row is deleted" - await pc._update_general_settings(db_general_settings={}) + await pc._update_general_settings(db_general_settings={}) - assert live_routes() == set() + assert live_routes() == set() + finally: + app.routes[:] = prior_routes + _registered_pass_through_routes.clear() + _registered_pass_through_routes.update(prior_registry) @pytest.mark.asyncio @@ -7619,15 +7629,18 @@ async def test_a_stored_pass_through_row_never_disturbs_the_config_declared_rout serving untouched. The stored entry never gets a route of its own.""" from litellm.proxy.pass_through_endpoints.pass_through_endpoints import ( InitPassThroughEndpointHelpers, + _registered_pass_through_routes, initialize_pass_through_endpoints, ) - from litellm.proxy.proxy_server import ProxyConfig + from litellm.proxy.proxy_server import ProxyConfig, app marker: Final = uuid.uuid4().hex[:8] config_path: Final = f"/v1/kept-{marker}" db_path: Final = f"/v1/ignored-{marker}" config_endpoint: Final = {"id": f"cfg-{marker}", "path": config_path, "target": "https://example.com/post"} db_endpoint: Final = {"id": f"db-{marker}", "path": db_path, "target": "https://example.com/post"} + prior_routes: Final = list(app.routes) + prior_registry: Final = dict(_registered_pass_through_routes) def live_paths() -> set[str]: registered: Final = InitPassThroughEndpointHelpers.get_all_registered_pass_through_routes() @@ -7635,17 +7648,22 @@ async def test_a_stored_pass_through_row_never_disturbs_the_config_declared_rout settings: Final = patch("litellm.proxy.proxy_server.general_settings", {"pass_through_endpoints": [config_endpoint]}) # test-quality-ok: the method reads this module global; no injection seam yaml_endpoints: Final = patch("litellm.proxy.proxy_server.config_passthrough_endpoints", [config_endpoint]) # test-quality-ok: module global holding the YAML endpoints the reload merges in - with settings, yaml_endpoints: - await initialize_pass_through_endpoints(pass_through_endpoints=[config_endpoint]) - assert live_paths() == {config_path} + try: + with settings, yaml_endpoints: + await initialize_pass_through_endpoints(pass_through_endpoints=[config_endpoint]) + assert live_paths() == {config_path} - pc = ProxyConfig() - await pc._update_general_settings(db_general_settings={"pass_through_endpoints": [db_endpoint]}) - assert live_paths() == {config_path} + pc = ProxyConfig() + await pc._update_general_settings(db_general_settings={"pass_through_endpoints": [db_endpoint]}) + assert live_paths() == {config_path} - await pc._update_general_settings(db_general_settings={}) + await pc._update_general_settings(db_general_settings={}) - assert live_paths() == {config_path} + assert live_paths() == {config_path} + finally: + app.routes[:] = prior_routes + _registered_pass_through_routes.clear() + _registered_pass_through_routes.update(prior_registry) def _fill_user_api_key_cache(cache: DualCache, count: int) -> None: