Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_add_gemini_3_1_flash_lite_image

litellm/constants.py

@@ -783,6 +783,7 @@ openai_compatible_endpoints: Final[list] = [
     "https://pinstripes.io/v1",
     "https://api.meta.ai/v1",
     "https://api.cognition.ai/v1",
+    "https://api.scx.ai/v1",
 ]
 
 
@@ -851,6 +852,7 @@ openai_compatible_providers: Final[list] = [
     "darkbloom",
     "meta",  # Meta Model API (Muse Spark) - JSON-configured provider
     "cognition",
+    "scx-ai",
 ]
 openai_text_completion_compatible_providers: Final[list] = [  # providers that support `/v1/completions`
     "together_ai",

litellm/llms/openai_like/providers.json

@@ -188,5 +188,17 @@
       "max_completion_tokens": "max_tokens"
     },
     "supported_endpoints": ["/v1/chat/completions", "/v1/responses", "/v1/embeddings"]
+  },
+  "scx-ai": {
+    "base_url": "https://api.scx.ai/v1",
+    "api_key_env": "SCX_API_KEY",
+    "api_base_env": "SCX_API_BASE",
+    "param_mappings": {
+      "max_completion_tokens": "max_tokens"
+    },
+    "constraints": {
+      "temperature_max": 1.99
+    },
+    "supported_endpoints": ["/v1/chat/completions"]
   }
 }

litellm/model_prices_and_context_window_backup.json

@@ -36722,6 +36722,40 @@
         "supports_vision": true,
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
+    "scx-ai/GLM-5.2": {
+        "cache_read_input_token_cost": 2.2e-07,
+        "input_cost_per_token": 6.1e-07,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.98e-06,
+        "source": "https://scx.ai/pricing",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "scx-ai/Qwen3.8-Max": {
+        "cache_read_input_token_cost": 2.1e-07,
+        "input_cost_per_token": 1.65e-06,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 4.99e-06,
+        "source": "https://scx.ai/pricing",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "snowflake/claude-3-5-sonnet": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 200000,

litellm/provider_endpoints_support_backup.json

@@ -2027,6 +2027,23 @@
         "interactions": true
       }
     },
+    "scx-ai": {
+      "display_name": "SCX.ai (`scx-ai`)",
+      "url": "https://docs.litellm.ai/docs/providers/scx_ai",
+      "endpoints": {
+        "chat_completions": true,
+        "messages": false,
+        "responses": false,
+        "embeddings": false,
+        "image_generations": false,
+        "audio_transcriptions": false,
+        "audio_speech": false,
+        "moderations": false,
+        "batches": false,
+        "rerank": false,
+        "a2a": false
+      }
+    },
     "snowflake": {
       "display_name": "Snowflake (`snowflake`)",
       "url": "https://docs.litellm.ai/docs/providers/snowflake",

litellm/proxy/public_endpoints/provider_create_fields.json

@@ -2726,6 +2726,34 @@
     ],
     "default_model_placeholder": "sap/gpt-4"
   },
+  {
+    "provider": "SCX_AI",
+    "provider_display_name": "SCX.ai",
+    "litellm_provider": "scx-ai",
+    "credential_fields": [
+      {
+        "key": "api_base",
+        "label": "API Base",
+        "placeholder": "https://api.scx.ai/v1",
+        "tooltip": null,
+        "required": false,
+        "field_type": "text",
+        "options": null,
+        "default_value": null
+      },
+      {
+        "key": "api_key",
+        "label": "API Key",
+        "placeholder": null,
+        "tooltip": null,
+        "required": true,
+        "field_type": "password",
+        "options": null,
+        "default_value": null
+      }
+    ],
+    "default_model_placeholder": "scx-ai/GLM-5.2"
+  },
   {
     "provider": "Snowflake",
     "provider_display_name": "Snowflake",

litellm/types/utils.py

@@ -3790,6 +3790,7 @@ class LlmProviders(str, Enum):
     LIBERTAI = "libertai"
     PINSTRIPES = "pinstripes"
     COGNITION = "cognition"
+    SCX_AI = "scx-ai"
     DARKBLOOM = "darkbloom"
     META = "meta"
     LITELLM_AGENT = "litellm_agent"

model_prices_and_context_window.json

@@ -36722,6 +36722,40 @@
         "supports_vision": true,
         "source": "https://cloud.sambanova.ai/plans/pricing"
     },
+    "scx-ai/GLM-5.2": {
+        "cache_read_input_token_cost": 2.2e-07,
+        "input_cost_per_token": 6.1e-07,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1048576,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 1.98e-06,
+        "source": "https://scx.ai/pricing",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": false
+    },
+    "scx-ai/Qwen3.8-Max": {
+        "cache_read_input_token_cost": 2.1e-07,
+        "input_cost_per_token": 1.65e-06,
+        "litellm_provider": "scx-ai",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 131072,
+        "max_tokens": 131072,
+        "mode": "chat",
+        "output_cost_per_token": 4.99e-06,
+        "source": "https://scx.ai/pricing",
+        "supports_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true,
+        "supports_vision": true
+    },
     "snowflake/claude-3-5-sonnet": {
         "litellm_provider": "snowflake",
         "max_input_tokens": 200000,

provider_endpoints_support.json

@@ -2261,6 +2261,23 @@
         "interactions": true
       }
     },
+    "scx-ai": {
+      "display_name": "SCX.ai (`scx-ai`)",
+      "url": "https://docs.litellm.ai/docs/providers/scx_ai",
+      "endpoints": {
+        "chat_completions": true,
+        "messages": false,
+        "responses": false,
+        "embeddings": false,
+        "image_generations": false,
+        "audio_transcriptions": false,
+        "audio_speech": false,
+        "moderations": false,
+        "batches": false,
+        "rerank": false,
+        "a2a": false
+      }
+    },
     "snowflake": {
       "display_name": "Snowflake (`snowflake`)",
       "url": "https://docs.litellm.ai/docs/providers/snowflake",

tests/test_litellm/llms/openai_like/test_scx_ai_provider.py

@@ -0,0 +1,211 @@
+"""
+Tests for SCX.ai provider configuration and integration.
+"""
+
+import litellm
+
+
+class TestSCXAIProviderConfig:
+    def test_scx_ai_in_provider_list(self):
+        from litellm import LlmProviders
+
+        assert hasattr(LlmProviders, "SCX_AI")
+        assert LlmProviders.SCX_AI.value == "scx-ai"
+        assert "scx-ai" in litellm.provider_list
+
+    def test_scx_ai_json_config_exists(self):
+        from litellm.llms.openai_like.json_loader import JSONProviderRegistry
+
+        assert JSONProviderRegistry.exists("scx-ai")
+
+        scx = JSONProviderRegistry.get("scx-ai")
+        assert scx is not None
+        assert scx.base_url == "https://api.scx.ai/v1"
+        assert scx.api_key_env == "SCX_API_KEY"
+        assert scx.param_mappings.get("max_completion_tokens") == "max_tokens"
+        assert scx.constraints.get("temperature_max") == 1.99
+
+    def test_scx_ai_in_openai_compatible_providers(self):
+        from litellm.constants import openai_compatible_providers
+
+        assert "scx-ai" in openai_compatible_providers
+
+    def test_scx_ai_provider_resolution(self):
+        from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
+
+        model, provider, api_key, api_base = get_llm_provider(
+            model="scx-ai/GLM-5.2",
+            custom_llm_provider=None,
+            api_base=None,
+            api_key=None,
+        )
+
+        assert model == "GLM-5.2"
+        assert provider == "scx-ai"
+        assert api_base == "https://api.scx.ai/v1"
+
+    def test_scx_ai_api_base_override(self):
+        from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
+
+        model, provider, api_key, api_base = get_llm_provider(
+            model="scx-ai/GLM-5.2",
+            custom_llm_provider=None,
+            api_base="https://custom.scx.ai/v1",
+            api_key="sk-test",
+        )
+
+        assert provider == "scx-ai"
+        assert api_base == "https://custom.scx.ai/v1"
+        assert api_key == "sk-test"
+
+    def test_scx_ai_url_autodetection(self):
+        from litellm.litellm_core_utils.get_llm_provider_logic import get_llm_provider
+
+        model, provider, api_key, api_base = get_llm_provider(
+            model="GLM-5.2",
+            custom_llm_provider=None,
+            api_base="https://api.scx.ai/v1",
+            api_key=None,
+        )
+        assert provider == "scx-ai"
+        assert api_base == "https://api.scx.ai/v1"
+
+    def test_scx_ai_temperature_clamped_to_max(self):
+        from litellm.llms.openai_like.dynamic_config import create_config_class
+        from litellm.llms.openai_like.json_loader import JSONProviderRegistry
+
+        provider = JSONProviderRegistry.get("scx-ai")
+        assert provider is not None
+        config = create_config_class(provider)()
+
+        optional_params = config.map_openai_params(
+            non_default_params={"temperature": 2.5},
+            optional_params={},
+            model="GLM-5.2",
+            drop_params=False,
+        )
+        assert optional_params["temperature"] == 1.99
+
+        optional_params = config.map_openai_params(
+            non_default_params={"temperature": 1.7},
+            optional_params={},
+            model="GLM-5.2",
+            drop_params=False,
+        )
+        assert optional_params["temperature"] == 1.7
+
+        optional_params = config.map_openai_params(
+            non_default_params={"temperature": 0.4},
+            optional_params={},
+            model="GLM-5.2",
+            drop_params=False,
+        )
+        assert optional_params["temperature"] == 0.4
+
+    def test_scx_ai_max_completion_tokens_mapped(self):
+        from litellm.llms.openai_like.dynamic_config import create_config_class
+        from litellm.llms.openai_like.json_loader import JSONProviderRegistry
+
+        provider = JSONProviderRegistry.get("scx-ai")
+        assert provider is not None
+        config = create_config_class(provider)()
+
+        optional_params = config.map_openai_params(
+            non_default_params={"max_completion_tokens": 256},
+            optional_params={},
+            model="GLM-5.2",
+            drop_params=False,
+        )
+        assert optional_params["max_tokens"] == 256
+        assert "max_completion_tokens" not in optional_params
+
+    def test_scx_ai_router_config(self):
+        from litellm import Router
+
+        router = Router(
+            model_list=[
+                {
+                    "model_name": "scx-chat",
+                    "litellm_params": {
+                        "model": "scx-ai/GLM-5.2",
+                        "api_key": "test-key",
+                    },
+                }
+            ]
+        )
+
+        assert len(router.model_list) == 1
+        assert router.model_list[0]["model_name"] == "scx-chat"
+
+
+class TestSCXAIModelMetadata:
+    SCX_MODELS = (
+        "scx-ai/GLM-5.2",
+        "scx-ai/Qwen3.8-Max",
+    )
+    VISION_MODELS = ("scx-ai/Qwen3.8-Max",)
+
+    @staticmethod
+    def _load(path_parts):
+        import json
+        from pathlib import Path
+
+        json_path = Path(__file__).parents[4].joinpath(*path_parts)
+        with open(json_path) as f:
+            return json.load(f)
+
+    def test_scx_ai_models_registered_with_correct_metadata(self):
+        model_cost = self._load(("model_prices_and_context_window.json",))
+        for model in self.SCX_MODELS:
+            info = model_cost.get(model)
+            assert info is not None, f"{model} missing from model_prices_and_context_window.json"
+            assert info["litellm_provider"] == "scx-ai"
+            assert info["mode"] == "chat"
+            assert info["input_cost_per_token"] > 0
+            assert info["output_cost_per_token"] > 0
+            assert info["supports_function_calling"] is True
+            assert info["supports_tool_choice"] is True
+            assert info["supports_reasoning"] is True
+            assert info["supports_response_schema"] is True
+            assert info.get("supports_vision", False) is (model in self.VISION_MODELS)
+
+            assert info["supports_prompt_caching"] is True
+            assert 0 < info["cache_read_input_token_cost"] < info["input_cost_per_token"]
+
+            assert info["max_output_tokens"] == 131072
+            assert info["max_tokens"] == info["max_output_tokens"]
+            assert info["max_input_tokens"] >= 1_000_000
+
+    def test_scx_ai_models_synced_to_backup(self):
+        model_cost = self._load(("model_prices_and_context_window.json",))
+        backup = self._load(("litellm", "model_prices_and_context_window_backup.json"))
+        for model in self.SCX_MODELS:
+            assert model in backup, f"{model} missing from backup json"
+            assert backup[model] == model_cost[model], f"{model} differs between root and backup json"
+
+
+class TestSCXAIDashboardRegistration:
+    @staticmethod
+    def _provider_create_fields():
+        import json
+        from pathlib import Path
+
+        import litellm
+
+        path = Path(litellm.__file__).parent / "proxy" / "public_endpoints" / "provider_create_fields.json"
+        with open(path) as f:
+            return json.load(f)
+
+    def test_scx_ai_is_selectable_in_the_add_model_form(self):
+        entries = [e for e in self._provider_create_fields() if e["litellm_provider"] == "scx-ai"]
+        assert len(entries) == 1, "scx-ai must appear exactly once in provider_create_fields.json"
+
+        entry = entries[0]
+        assert entry["provider"] == "SCX_AI"
+        assert entry["provider_display_name"] == "SCX.ai"
+        assert entry["default_model_placeholder"].startswith("scx-ai/")
+
+        fields = {f["key"]: f for f in entry["credential_fields"]}
+        assert fields["api_key"]["required"] is True
+        assert fields["api_key"]["field_type"] == "password"
+        assert fields["api_base"]["required"] is False

ui/litellm-dashboard/src/components/provider_info_helpers.test.tsx

@@ -62,6 +62,17 @@ describe("provider_info_helpers", () => {
       expect(result.logo).toBe(providerLogoMap[Providers.Groq]);
     });
 
+    it("should map scx-ai slug and SCX_AI enum key to the SCX.ai display name and logo", () => {
+      const fromSlug = getProviderLogoAndName("scx-ai");
+      expect(fromSlug.displayName).toBe(Providers.SCX_AI);
+      expect(fromSlug.logo).toBe(providerLogoMap[Providers.SCX_AI]);
+      expect(fromSlug.logo).toBeTruthy();
+
+      const fromEnumKey = getProviderLogoAndName("SCX_AI");
+      expect(fromEnumKey.displayName).toBe(Providers.SCX_AI);
+      expect(fromEnumKey.logo).toBe(providerLogoMap[Providers.SCX_AI]);
+    });
+
     it("should map bedrock_mantle slug to Bedrock Mantle display name and logo", () => {
       const result = getProviderLogoAndName("bedrock_mantle");
       expect(result.displayName).toBe(Providers.BedrockMantle);
@@ -180,6 +191,10 @@ describe("provider_info_helpers", () => {
       expect(getPlaceholder(Providers.Vertex_AI)).toBe("gemini-pro");
     });
 
+    it("should return an scx-ai model placeholder for SCX_AI provider", () => {
+      expect(getPlaceholder(Providers.SCX_AI)).toBe("scx-ai/GLM-5.2");
+    });
+
     it("should return claude-3-opus placeholder for Anthropic provider", () => {
       expect(getPlaceholder(Providers.Anthropic)).toBe("claude-3-opus");
     });

ui/litellm-dashboard/src/components/provider_info_helpers.tsx

@@ -50,6 +50,7 @@ import replicateLogo from "../../public/assets/logos/replicate.svg";
 import runwayLogo from "../../public/assets/logos/runway.png";
 import sambanovaLogo from "../../public/assets/logos/sambanova.svg";
 import sapLogo from "../../public/assets/logos/sap.png";
+import scxAiLogo from "../../public/assets/logos/scx_ai.svg";
 import snowflakeLogo from "../../public/assets/logos/snowflake.svg";
 import sonioxLogo from "../../public/assets/logos/soniox.svg";
 import togetheraiLogo from "../../public/assets/logos/togetherai.svg";
@@ -153,6 +154,7 @@ export enum Providers {
   SAGEMAKER_LEGACY = "Sagemaker",
   Sambanova = "Sambanova",
   SAP = "SAP Generative AI Hub",
+  SCX_AI = "SCX.ai",
   Snowflake = "Snowflake",
   Soniox = "Soniox",
   TEXT_COMPLETION_CODESTRAL = "Text-Completion-Codestral",
@@ -264,6 +266,7 @@ export const provider_map: Record<string, string> = {
   SageMaker: "sagemaker_chat",
   Sambanova: "sambanova",
   SAP: "sap",
+  SCX_AI: "scx-ai",
   Snowflake: "snowflake",
   Soniox: "soniox",
   TEXT_COMPLETION_CODESTRAL: "text-completion-codestral",
@@ -356,6 +359,7 @@ export const providerLogoMap: Partial<Record<Providers, string>> = {
   [Providers.SAGEMAKER_LEGACY]: bedrockLogo.src,
   [Providers.Sambanova]: sambanovaLogo.src,
   [Providers.SAP]: sapLogo.src,
+  [Providers.SCX_AI]: scxAiLogo.src,
   [Providers.Snowflake]: snowflakeLogo.src,
   [Providers.Soniox]: sonioxLogo.src,
   [Providers.TEXT_COMPLETION_CODESTRAL]: mistralLogo.src,
@@ -421,6 +425,7 @@ const providerPlaceholderMap: Partial<Record<Providers, string>> = {
   [Providers.Oracle]: "oci/xai.grok-4",
   [Providers.RunwayML]: "runwayml/gen4_turbo",
   [Providers.SageMaker]: "sagemaker/jumpstart-dft-meta-textgeneration-llama-2-7b",
+  [Providers.SCX_AI]: "scx-ai/GLM-5.2",
   [Providers.Snowflake]: "snowflake/mistral-7b",
   [Providers.Vertex_AI]: "gemini-pro",
   [Providers.VolcEngine]: "volcengine/<any-model-on-volcengine>",