fix(together_ai): let an explicit api_key beat the Together env key on api_base match

litellm/litellm_core_utils/get_llm_provider_logic.py

@@ -274,7 +274,7 @@ def get_llm_provider(
                         dynamic_api_key = get_secret_str("DEEPSEEK_API_KEY")
                     elif endpoint == "api.together.ai/v1" or endpoint == "api.together.xyz/v1":
                         custom_llm_provider = "together_ai"
-                        dynamic_api_key = (
+                        dynamic_api_key = api_key or (
                             get_secret_str("TOGETHER_API_KEY")
                             or get_secret_str("TOGETHER_AI_API_KEY")
                             or get_secret_str("TOGETHERAI_API_KEY")

litellm/llms/together_ai/rerank/handler.py

@@ -51,7 +51,7 @@ class TogetherAIRerank(BaseLLM):
             raise ValueError("TogetherAI does not support max_chunks_per_doc")
 
         if _is_async:
-            return self.async_rerank(request_data_dict, api_key, api_base)  # Call async method
+            return self.async_rerank(request_data_dict, api_key, api_base)
 
         response: Final = client.post(
             _rerank_url(api_base),

tests/test_litellm/litellm_core_utils/test_get_llm_provider_endpoint_match.py

@@ -165,6 +165,18 @@ class TestTogetherApiBaseResolvesProvider:
         assert returned_api_base == api_base
         assert model == "some-model"
 
+    def test_explicit_api_key_beats_together_env_key(self, monkeypatch):
+        monkeypatch.setenv("TOGETHER_API_KEY", "together-key-from-env")
+
+        _, provider, dynamic_api_key, _ = get_llm_provider(
+            model="some-model",
+            api_base="https://api.together.ai/v1",
+            api_key="explicit-caller-key",
+        )
+
+        assert provider == "together_ai"
+        assert dynamic_api_key == "explicit-caller-key"
+
     def test_together_default_api_base_is_together_ai(self, monkeypatch):
         monkeypatch.delenv("TOGETHER_AI_API_BASE", raising=False)