diff --git a/litellm/__init__.py b/litellm/__init__.py
index 25cae832826..0b2ec8820b6 100644
--- a/litellm/__init__.py
+++ b/litellm/__init__.py
@@ -483,7 +483,12 @@ openai_compatible_providers: List = [
     "azure_ai",
     "github",
 ]
-
+openai_text_completion_compatible_providers: List = (
+    [  # providers that support `/v1/completions`
+        "together_ai",
+        "fireworks_ai",
+    ]
+)
 
 # well supported replicate llms
 replicate_models: List = [
diff --git a/litellm/main.py b/litellm/main.py
index cb355561916..2095322328f 100644
--- a/litellm/main.py
+++ b/litellm/main.py
@@ -1209,6 +1209,9 @@ def completion(
             custom_llm_provider == "text-completion-openai"
             or "ft:babbage-002" in model
             or "ft:davinci-002" in model  # support for finetuned completion models
+            or custom_llm_provider
+            in litellm.openai_text_completion_compatible_providers
+            and kwargs.get("text_completion") is True
         ):
             openai.api_type = "openai"
 
@@ -4099,8 +4102,8 @@ def text_completion(
 
     kwargs.pop("prompt", None)
 
-    if (
-        _model is not None and custom_llm_provider == "openai"
+    if _model is not None and (
+        custom_llm_provider == "openai"
     ):  # for openai compatible endpoints - e.g. vllm, call the native /v1/completions endpoint for text completion calls
         if _model not in litellm.open_ai_chat_completion_models:
             model = "text-completion-openai/" + _model
diff --git a/litellm/tests/test_text_completion.py b/litellm/tests/test_text_completion.py
index 70325c44e22..e6a4a0499cc 100644
--- a/litellm/tests/test_text_completion.py
+++ b/litellm/tests/test_text_completion.py
@@ -4239,3 +4239,14 @@ def test_completion_vllm():
         mock_call.assert_called_once()
 
         assert "hello" in mock_call.call_args.kwargs["extra_body"]
+
+
+def test_completion_fireworks_ai_multiple_choices():
+    litellm.set_verbose = True
+    response = litellm.text_completion(
+        model="fireworks_ai/llama-v3p1-8b-instruct",
+        prompt=["halo", "hi", "halo", "hi"],
+    )
+    print(response.choices)
+
+    assert len(response.choices) == 4