Bye Bye LiteLLM

README.md

@@ -115,7 +115,7 @@ export PRIME_API_KEY=...
 
 
 ### Model Providers
-We currently support most major clients (OpenAI, Anthropic), as well as the router platforms (OpenRouter, Portkey, LiteLLM). For local models, we recommend using vLLM (which interfaces with the [OpenAI client](https://github.com/alexzhang13/rlm/blob/main/rlm/clients/openai.py)). To view or add support for more clients, start by looking at [`rlm/clients/`](https://github.com/alexzhang13/rlm/tree/main/rlm/clients).
+We currently support most major clients (OpenAI, Anthropic), as well as the router platforms (OpenRouter, Portkey). For local models, we recommend using vLLM (which interfaces with the [OpenAI client](https://github.com/alexzhang13/rlm/blob/main/rlm/clients/openai.py)). To view or add support for more clients, start by looking at [`rlm/clients/`](https://github.com/alexzhang13/rlm/tree/main/rlm/clients).
 
 ## Relevant Reading
 * **[Dec '25]** [Recursive Language Models arXiv](https://arxiv.org/abs/2512.24601)

docs/api/rlm.md

@@ -71,7 +71,7 @@ RLM(
 #### `backend`
 {: .no_toc }
 
-**Type:** `Literal["openai", "portkey", "openrouter", "vllm", "litellm", "anthropic"]`
+**Type:** `Literal["openai", "portkey", "openrouter", "vllm", "anthropic"]`
 **Default:** `"openai"`
 
 The LM provider backend to use for the root model.
@@ -104,7 +104,7 @@ Configuration passed to the LM client. Required fields vary by backend:
 | `portkey` | `model_name`, `api_key` | `base_url` |
 | `openrouter` | `model_name` | `api_key` |
 | `vllm` | `model_name`, `base_url` | — |
-| `litellm` | `model_name` | varies by provider |
+
 
 ```python
 backend_kwargs = {

docs/src/app/api/page.tsx

@@ -61,7 +61,7 @@ print(result.response)`} />
                 [<code key="2" className="text-sm">"anthropic"</code>, "Anthropic API"],
                 [<code key="3" className="text-sm">"portkey"</code>, "Portkey AI gateway"],
                 [<code key="4" className="text-sm">"openrouter"</code>, "OpenRouter"],
-                [<code key="5" className="text-sm">"litellm"</code>, "LiteLLM (multi-provider)"],
+
                 [<code key="6" className="text-sm">"vllm"</code>, "Local vLLM server"],
               ]}
             />

docs/src/app/backends/page.tsx

@@ -7,7 +7,7 @@ export default function BackendsPage() {
 
       <p className="text-muted-foreground mb-6">
         <p>
-          RLMs natively support a wide range of language model providers, including <code>OpenAI</code>, <code>Anthropic</code>, <code>Portkey</code>, <code>OpenRouter</code>, and <code>LiteLLM</code>. Additional providers can be supported with minimal effort. The <code>backend_kwargs</code> are named arguments passed directly to the backend client.
+          RLMs natively support a wide range of language model providers, including <code>OpenAI</code>, <code>Anthropic</code>, <code>Portkey</code>, and <code>OpenRouter</code>. Additional providers can be supported with minimal effort. The <code>backend_kwargs</code> are named arguments passed directly to the backend client.
         </p>
       </p>
 
@@ -64,20 +64,6 @@ export default function BackendsPage() {
 
       <hr className="my-8 border-border" />
 
-      <h2 className="text-2xl font-semibold mb-4">LiteLLM</h2>
-      <p className="text-muted-foreground mb-4">
-        <a href="https://docs.litellm.ai/docs/" className="text-primary underline font-medium" target="_blank" rel="noopener noreferrer">LiteLLM</a> is a universal interface for 100+ model providers, with support for local models and custom endpoints.
-      </p>
-      <CodeBlock code={`rlm = RLM(
-    backend="litellm",
-    backend_kwargs={
-        "model_name": "gpt-5-mini",
-    },
-)
-# Set provider API keys in environment`} />
-
-      <hr className="my-8 border-border" />
-
       <h2 className="text-2xl font-semibold mb-4">vLLM (Local)</h2>
       <p className="text-muted-foreground mb-4">Local model serving.</p>
       <CodeBlock language="bash" code={`# Start vLLM server

rlm/clients/__init__.py

@@ -41,10 +41,6 @@ def get_client(
 
         backend_kwargs.setdefault("base_url", "https://ai-gateway.vercel.sh/v1")
         return OpenAIClient(**backend_kwargs)
-    elif backend == "litellm":
-        from rlm.clients.litellm import LiteLLMClient
-
-        return LiteLLMClient(**backend_kwargs)
     elif backend == "anthropic":
         from rlm.clients.anthropic import AnthropicClient
 
@@ -59,5 +55,5 @@ def get_client(
         return AzureOpenAIClient(**backend_kwargs)
     else:
         raise ValueError(
-            f"Unknown backend: {backend}. Supported backends: ['openai', 'vllm', 'portkey', 'openrouter', 'litellm', 'anthropic', 'azure_openai', 'gemini', 'vercel']"
+            f"Unknown backend: {backend}. Supported backends: ['openai', 'vllm', 'portkey', 'openrouter', 'anthropic', 'azure_openai', 'gemini', 'vercel']"
         )

rlm/core/types.py

@@ -8,7 +8,6 @@
     "openrouter",
     "vercel",
     "vllm",
-    "litellm",
     "anthropic",
     "azure_openai",
     "gemini",

tests/clients/test_timeout.py

@@ -140,32 +140,6 @@ def test_timeout_passed_to_client(self):
                 assert async_call_kwargs["timeout"] == 120.0
 
 
-class TestLiteLLMClientTimeout:
-    """Tests for LiteLLM client timeout."""
-
-    def test_timeout_passed_to_completion(self):
-        """Timeout should be passed to litellm.completion call."""
-        pytest.importorskip("litellm")
-        from rlm.clients.litellm import LiteLLMClient
-
-        mock_response = MagicMock()
-        mock_response.choices = [MagicMock()]
-        mock_response.choices[0].message.content = "Hello"
-        mock_response.usage.prompt_tokens = 10
-        mock_response.usage.completion_tokens = 5
-        mock_response.usage.total_tokens = 15
-
-        with patch(
-            "rlm.clients.litellm.litellm.completion", return_value=mock_response
-        ) as mock_completion:
-            client = LiteLLMClient(model_name="gpt-4o", timeout=120.0)
-            client.completion("Hello")
-
-            mock_completion.assert_called_once()
-            call_kwargs = mock_completion.call_args[1]
-            assert call_kwargs["timeout"] == 120.0
-
-
 class TestGeminiClientTimeout:
     """Tests for Gemini client timeout."""
 

tests/test_imports.py

@@ -67,13 +67,6 @@ def test_portkey_client_import(self):
 
         assert PortkeyClient is not None
 
-    def test_litellm_client_import(self):
-        """Test LiteLLMClient import."""
-        pytest.importorskip("litellm")
-        from rlm.clients.litellm import LiteLLMClient
-
-        assert LiteLLMClient is not None
-
     def test_get_client_function(self):
         """Test get_client function import."""
         from rlm.clients import get_client
@@ -322,7 +315,6 @@ def test_no_circular_imports(self):
             ("rlm.clients.openai", "openai"),
             ("rlm.clients.anthropic", "anthropic"),
             ("rlm.clients.portkey", "portkey_ai"),
-            ("rlm.clients.litellm", "litellm"),
             ("rlm.environments.modal_repl", "modal"),
             ("rlm.environments.prime_repl", "prime_sandboxes"),
         ]
@@ -463,14 +455,6 @@ def test_all_client_classes_importable(self):
         except Exception:
             pass
 
-        try:
-            pytest.importorskip("litellm")
-            from rlm.clients.litellm import LiteLLMClient
-
-            assert isinstance(LiteLLMClient, type)
-        except Exception:
-            pass
-
     def test_all_environment_classes_importable(self):
         """Test that all environment classes can be imported."""
         from rlm.environments.base_env import BaseEnv, IsolatedEnv, NonIsolatedEnv