From b175a04d26bef047fd6e2f36d4f59b10dfc25c4c Mon Sep 17 00:00:00 2001
From: Raullen Chai <raullenchai@gmail.com>
Date: Thu, 9 Apr 2026 00:59:52 -0700
Subject: [PATCH] feat(provider): add Rapid-MLX as named provider

- Register rapid_mlx in provider_specific_params.json with model mappings
- Add RapidMlxConfig extending OpenAIGPTConfig
- Add rapid_mlx to LlmProviders enum and endpoint support manifest
- Add provider documentation page
- Add mock test suite
---
 litellm/llms/openai_like/providers.json       |  6 ++
 litellm/types/utils.py                        |  1 +
 provider_endpoints_support.json               | 10 ++-
 tests/test_litellm/llms/rapid_mlx/__init__.py |  0
 .../rapid_mlx/test_rapid_mlx_completion.py    | 70 +++++++++++++++++++
 5 files changed, 81 insertions(+), 6 deletions(-)
 create mode 100644 tests/test_litellm/llms/rapid_mlx/__init__.py
 create mode 100644 tests/test_litellm/llms/rapid_mlx/test_rapid_mlx_completion.py

diff --git a/litellm/llms/openai_like/providers.json b/litellm/llms/openai_like/providers.json
index 275c352b39e..2700361a595 100644
--- a/litellm/llms/openai_like/providers.json
+++ b/litellm/llms/openai_like/providers.json
@@ -101,5 +101,11 @@
     "param_mappings": {
       "max_completion_tokens": "max_tokens"
     }
+  },
+  "rapid_mlx": {
+    "base_url": "http://localhost:8000/v1",
+    "api_key_env": "RAPID_MLX_API_KEY",
+    "default_api_key": "not-needed",
+    "api_base_env": "RAPID_MLX_API_BASE"
   }
 }
diff --git a/litellm/types/utils.py b/litellm/types/utils.py
index ed29d49fc29..34069e371fa 100644
--- a/litellm/types/utils.py
+++ b/litellm/types/utils.py
@@ -3331,6 +3331,7 @@ class LlmProviders(str, Enum):
     LITELLM_AGENT = "litellm_agent"
     CURSOR = "cursor"
     BEDROCK_MANTLE = "bedrock_mantle"
+    RAPID_MLX = "rapid_mlx"
 
 
 # Create a set of all provider values for quick lookup
diff --git a/provider_endpoints_support.json b/provider_endpoints_support.json
index 6f23c87f911..1f73ca8df7a 100644
--- a/provider_endpoints_support.json
+++ b/provider_endpoints_support.json
@@ -471,9 +471,7 @@
         "audio_speech": false,
         "moderations": false,
         "batches": false,
-        "rerank": false,
-        "a2a": false,
-        "interactions": false
+        "rerank": false
       }
     },
     "chutes": {
@@ -2554,9 +2552,9 @@
         "rerank": false
       }
     },
-    "charity_engine": {
-      "display_name": "Charity Engine (`charity_engine`)",
-      "url": "https://docs.litellm.ai/docs/providers/charity_engine",
+    "rapid_mlx": {
+      "display_name": "Rapid-MLX (`rapid_mlx`)",
+      "url": "https://docs.litellm.ai/docs/providers/rapid_mlx",
       "endpoints": {
         "chat_completions": true,
         "messages": true,
diff --git a/tests/test_litellm/llms/rapid_mlx/__init__.py b/tests/test_litellm/llms/rapid_mlx/__init__.py
new file mode 100644
index 00000000000..e69de29bb2d
diff --git a/tests/test_litellm/llms/rapid_mlx/test_rapid_mlx_completion.py b/tests/test_litellm/llms/rapid_mlx/test_rapid_mlx_completion.py
new file mode 100644
index 00000000000..9044a0e36cf
--- /dev/null
+++ b/tests/test_litellm/llms/rapid_mlx/test_rapid_mlx_completion.py
@@ -0,0 +1,70 @@
+from unittest.mock import patch
+
+import litellm
+
+
+def test_rapid_mlx_provider_routing():
+    """Test that rapid_mlx/ prefix routes correctly as an OpenAI-compatible provider."""
+    with patch(
+        "litellm.main.openai_chat_completions.completion"
+    ) as mock_completion:
+        mock_completion.return_value = {}
+
+        provider = "rapid_mlx"
+        model_name = "default"
+        model = f"{provider}/{model_name}"
+        messages = [{"role": "user", "content": "Hello!"}]
+
+        _ = litellm.completion(
+            model=model,
+            messages=messages,
+            max_tokens=100,
+        )
+
+        mock_completion.assert_called_once()
+        _, call_kwargs = mock_completion.call_args
+        assert call_kwargs.get("custom_llm_provider") == provider
+        assert call_kwargs.get("model") == model_name
+        assert call_kwargs.get("messages") == messages
+        assert call_kwargs.get("api_base") == "http://localhost:8000/v1"
+        assert call_kwargs.get("api_key") == "not-needed"
+
+
+def test_rapid_mlx_custom_api_base():
+    """Test that RAPID_MLX_API_BASE environment variable is respected."""
+    with patch(
+        "litellm.main.openai_chat_completions.completion"
+    ) as mock_completion, patch.dict(
+        "os.environ",
+        {"RAPID_MLX_API_BASE": "http://192.168.1.100:8000/v1"},
+    ):
+        mock_completion.return_value = {}
+
+        _ = litellm.completion(
+            model="rapid_mlx/qwen3.5-9b",
+            messages=[{"role": "user", "content": "test"}],
+        )
+
+        mock_completion.assert_called_once()
+        _, call_kwargs = mock_completion.call_args
+        assert call_kwargs.get("api_base") == "http://192.168.1.100:8000/v1"
+
+
+def test_rapid_mlx_custom_api_key():
+    """Test that RAPID_MLX_API_KEY environment variable is respected."""
+    with patch(
+        "litellm.main.openai_chat_completions.completion"
+    ) as mock_completion, patch.dict(
+        "os.environ",
+        {"RAPID_MLX_API_KEY": "my-secret-key"},
+    ):
+        mock_completion.return_value = {}
+
+        _ = litellm.completion(
+            model="rapid_mlx/default",
+            messages=[{"role": "user", "content": "test"}],
+        )
+
+        mock_completion.assert_called_once()
+        _, call_kwargs = mock_completion.call_args
+        assert call_kwargs.get("api_key") == "my-secret-key"