Merge pull request #19479 from BerriAI/litellm_sarvam_int

Add support for sarvam models

litellm/llms/openai_like/providers.json

@@ -71,5 +71,16 @@
     "param_mappings": {
       "max_completion_tokens": "max_tokens"
     }
+  },
+  "sarvam": {
+    "base_url": "https://api.sarvam.ai/v1",
+    "api_key_env": "SARVAM_API_KEY",
+    "base_class": "openai_gpt",
+    "param_mappings": {
+      "max_completion_tokens": "max_tokens"
+    },
+    "headers": {
+      "api-subscription-key": "{api_key}"
+    }
   }
 }

litellm/model_prices_and_context_window_backup.json

@@ -34062,5 +34062,18 @@
         "output_cost_per_token": 0,
         "litellm_provider": "llamagate",
         "mode": "embedding"
+    },
+    "sarvam/sarvam-m": {
+        "cache_creation_input_token_cost": 0,
+        "cache_creation_input_token_cost_above_1hr": 0,
+        "cache_read_input_token_cost": 0,
+        "input_cost_per_token": 0,
+        "litellm_provider": "sarvam",
+        "max_input_tokens": 8192,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "supports_reasoning": true
     }
 }

litellm/router.py

@@ -63,6 +63,7 @@ from litellm.litellm_core_utils.credential_accessor import CredentialAccessor
 from litellm.litellm_core_utils.dd_tracing import tracer
 from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLogging
 from litellm.litellm_core_utils.sensitive_data_masker import SensitiveDataMasker
+from litellm.llms.openai_like.json_loader import JSONProviderRegistry
 from litellm.router_strategy.budget_limiter import RouterBudgetLimiting
 from litellm.router_strategy.least_busy import LeastBusyLoggingHandler
 from litellm.router_strategy.lowest_cost import LowestCostLoggingHandler
@@ -5877,7 +5878,8 @@ class Router:
                 ),
             )
             # done reading model["litellm_params"]
-            if custom_llm_provider not in litellm.provider_list:
+            # Check if provider is supported: either in enum or JSON-configured
+            if custom_llm_provider not in litellm.provider_list and not JSONProviderRegistry.exists(custom_llm_provider):
                 raise Exception(f"Unsupported provider - {custom_llm_provider}")
 
         #### DEPLOYMENT NAMES INIT ########

model_prices_and_context_window.json

@@ -34062,5 +34062,18 @@
         "output_cost_per_token": 0,
         "litellm_provider": "llamagate",
         "mode": "embedding"
+    },
+    "sarvam/sarvam-m": {
+        "cache_creation_input_token_cost": 0,
+        "cache_creation_input_token_cost_above_1hr": 0,
+        "cache_read_input_token_cost": 0,
+        "input_cost_per_token": 0,
+        "litellm_provider": "sarvam",
+        "max_input_tokens": 8192,
+        "max_output_tokens": 32000,
+        "max_tokens": 32000,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "supports_reasoning": true
     }
 }

provider_endpoints_support.json

@@ -2358,6 +2358,15 @@
         "a2a": true,
         "interactions": true
       }
+    },
+    "sarvam": {
+      "display_name": "Sarvam (`sarvam`)",
+      "url": "https://docs.litellm.ai/docs/providers/sarvam",
+      "endpoints": {
+        "chat_completions": true,
+        "messages": true,
+        "responses": true
+      }
     }
   },
   "endpoints": {

tests/litellm_utils_tests/test_utils.py

@@ -37,6 +37,7 @@ from litellm.utils import (
     trim_messages,
     validate_environment,
 )
+from litellm.llms.openai_like.json_loader import JSONProviderRegistry
 from unittest.mock import AsyncMock, MagicMock, patch
 
 
@@ -1383,7 +1384,7 @@ def test_models_by_provider():
             providers.add(v["litellm_provider"])
 
     for provider in providers:
-        assert provider in models_by_provider.keys()
+        assert provider in models_by_provider.keys() or JSONProviderRegistry.exists(provider)
 
 
 @pytest.mark.parametrize(