feat: add OrcaRouter as a named provider

.env.example

@@ -2,18 +2,21 @@
 ANTHROPIC_API_KEY="your-anthropic-api-key" # Needed if proxying *to* Anthropic
 OPENAI_API_KEY="sk-..."
 GEMINI_API_KEY="your-google-ai-studio-key"
+ORCAROUTER_API_KEY="sk-orca-..." # Needed if PREFERRED_PROVIDER=orcarouter
 
 # Optional: Provider Preference and Model Mapping
-# Controls which provider (google, openai, or anthropic) is preferred for mapping haiku/sonnet.
+# Controls which provider (google, openai, orcarouter, or anthropic) is preferred for mapping haiku/sonnet.
 # Defaults to openai if not set.
 # Set to "anthropic" for "just an Anthropic proxy" mode (no remapping)
 PREFERRED_PROVIDER="openai"
 OPENAI_BASE_URL="https://api.openai.com/v1"
+ORCAROUTER_BASE_URL="https://api.orcarouter.ai/v1" # Optional, it's the default
 
 # Optional: Specify the exact models to map haiku/sonnet to.
 # If PREFERRED_PROVIDER=google, these MUST be valid Gemini model names known to the server.
 # Defaults to gemini-2.5-pro and gemini-2.5-flash if PREFERRED_PROVIDER=google.
 # Defaults to gpt-4.1 and gpt-4.1-mini if PREFERRED_PROVIDER=openai.
+# Defaults to anthropic/claude-sonnet-4.6 and anthropic/claude-haiku-4.5 if PREFERRED_PROVIDER=orcarouter.
 # These are IGNORED when PREFERRED_PROVIDER=anthropic (models are not remapped).
 # BIG_MODEL="gpt-4.1"
 # SMALL_MODEL="gpt-4.1-mini"
@@ -29,6 +32,11 @@ OPENAI_BASE_URL="https://api.openai.com/v1"
 # BIG_MODEL="gemini-2.5-pro"
 # SMALL_MODEL="gemini-2.5-flash"
 
+# Example OrcaRouter mapping:
+# PREFERRED_PROVIDER="orcarouter"
+# BIG_MODEL="anthropic/claude-sonnet-4.6" # any model id from OrcaRouter's catalog, e.g. orcarouter/auto
+# SMALL_MODEL="anthropic/claude-haiku-4.5"
+
 # Example "just an Anthropic proxy" mode:
 # PREFERRED_PROVIDER="anthropic"
 # (BIG_MODEL and SMALL_MODEL are ignored in this mode)

README.md

@@ -1,8 +1,8 @@
-# Anthropic API Proxy for Gemini & OpenAI Models 🔄
+# Anthropic API Proxy for Gemini, OpenAI & OrcaRouter Models 🔄
 
-**Use Anthropic clients (like Claude Code) with Gemini, OpenAI, or direct Anthropic backends.** 🤝
+**Use Anthropic clients (like Claude Code) with Gemini, OpenAI, OrcaRouter, or direct Anthropic backends.** 🤝
 
-A proxy server that lets you use Anthropic clients with Gemini, OpenAI, or Anthropic models themselves (a transparent proxy of sorts), all via LiteLLM. 🌉
+A proxy server that lets you use Anthropic clients with Gemini, OpenAI, OrcaRouter, or Anthropic models themselves (a transparent proxy of sorts), all via LiteLLM. 🌉
 
 
 ![Anthropic API Proxy](pic.png)
@@ -13,6 +13,7 @@ A proxy server that lets you use Anthropic clients with Gemini, OpenAI, or Anthr
 
 - OpenAI API key 🔑
 - Google AI Studio (Gemini) API key (if using Google provider) 🔑
+- OrcaRouter API key (if using OrcaRouter provider) 🔑
 - Google Cloud Project with Vertex AI API enabled (if using Application Default Credentials for Gemini) ☁️
 - [uv](https://github.com/astral-sh/uv) installed.
 
@@ -42,16 +43,19 @@ A proxy server that lets you use Anthropic clients with Gemini, OpenAI, or Anthr
    *   `ANTHROPIC_API_KEY`: (Optional) Needed only if proxying *to* Anthropic models.
    *   `OPENAI_API_KEY`: Your OpenAI API key (Required if using the default OpenAI preference or as fallback).
    *   `GEMINI_API_KEY`: Your Google AI Studio (Gemini) API key (Required if `PREFERRED_PROVIDER=google` and `USE_VERTEX_AUTH=true`).
+   *   `ORCAROUTER_API_KEY`: Your [OrcaRouter](https://www.orcarouter.ai) API key (Required if `PREFERRED_PROVIDER=orcarouter`).
+   *   `ORCAROUTER_BASE_URL` (Optional): OrcaRouter's OpenAI-compatible endpoint. Defaults to `https://api.orcarouter.ai/v1`.
    *   `USE_VERTEX_AUTH` (Optional): Set to `true` to use Application Default Credentials (ADC) will be used (no static API key required). Note: when USE_VERTEX_AUTH=true, you must configure `VERTEX_PROJECT` and `VERTEX_LOCATION`.
    *   `VERTEX_PROJECT` (Optional): Your Google Cloud Project ID (Required if `PREFERRED_PROVIDER=google` and `USE_VERTEX_AUTH=true`).
    *   `VERTEX_LOCATION` (Optional): The Google Cloud region for Vertex AI (e.g., `us-central1`) (Required if `PREFERRED_PROVIDER=google` and `USE_VERTEX_AUTH=true`).
-   *   `PREFERRED_PROVIDER` (Optional): Set to `openai` (default), `google`, or `anthropic`. This determines the primary backend for mapping `haiku`/`sonnet`.
-   *   `BIG_MODEL` (Optional): The model to map `sonnet` requests to. Defaults to `gpt-4.1` (if `PREFERRED_PROVIDER=openai`) or `gemini-2.5-pro-preview-03-25`. Ignored when `PREFERRED_PROVIDER=anthropic`.
-   *   `SMALL_MODEL` (Optional): The model to map `haiku` requests to. Defaults to `gpt-4.1-mini` (if `PREFERRED_PROVIDER=openai`) or `gemini-2.0-flash`. Ignored when `PREFERRED_PROVIDER=anthropic`.
+   *   `PREFERRED_PROVIDER` (Optional): Set to `openai` (default), `google`, `orcarouter`, or `anthropic`. This determines the primary backend for mapping `haiku`/`sonnet`.
+   *   `BIG_MODEL` (Optional): The model to map `sonnet` requests to. Defaults to `gpt-4.1` (if `PREFERRED_PROVIDER=openai`), `gemini-2.5-pro-preview-03-25` (if `PREFERRED_PROVIDER=google`), or `anthropic/claude-sonnet-4.6` (if `PREFERRED_PROVIDER=orcarouter`). Ignored when `PREFERRED_PROVIDER=anthropic`.
+   *   `SMALL_MODEL` (Optional): The model to map `haiku` requests to. Defaults to `gpt-4.1-mini` (if `PREFERRED_PROVIDER=openai`), `gemini-2.0-flash` (if `PREFERRED_PROVIDER=google`), or `anthropic/claude-haiku-4.5` (if `PREFERRED_PROVIDER=orcarouter`). Ignored when `PREFERRED_PROVIDER=anthropic`.
 
    **Mapping Logic:**
    - If `PREFERRED_PROVIDER=openai` (default), `haiku`/`sonnet` map to `SMALL_MODEL`/`BIG_MODEL` prefixed with `openai/`.
    - If `PREFERRED_PROVIDER=google`, `haiku`/`sonnet` map to `SMALL_MODEL`/`BIG_MODEL` prefixed with `gemini/` *if* those models are in the server's known `GEMINI_MODELS` list (otherwise falls back to OpenAI mapping).
+   - If `PREFERRED_PROVIDER=orcarouter`, `haiku`/`sonnet` map to `SMALL_MODEL`/`BIG_MODEL` prefixed with `openai/` (OrcaRouter speaks the OpenAI wire format) and are routed through [OrcaRouter](https://www.orcarouter.ai) using `ORCAROUTER_API_KEY` + `ORCAROUTER_BASE_URL`.
    - If `PREFERRED_PROVIDER=anthropic`, `haiku`/`sonnet` requests are passed directly to Anthropic with the `anthropic/` prefix without remapping to different models.
 
 4. **Run the server**:
@@ -194,13 +198,24 @@ BIG_MODEL="gpt-4o" # Example specific model
 SMALL_MODEL="gpt-4o-mini" # Example specific model
 ```
 
+**Example 5: Prefer [OrcaRouter](https://www.orcarouter.ai)**
+```dotenv
+ORCAROUTER_API_KEY="sk-orca-..."
+PREFERRED_PROVIDER="orcarouter"
+# ORCAROUTER_BASE_URL="https://api.orcarouter.ai/v1" # Optional, it's the default
+# BIG_MODEL="anthropic/claude-sonnet-4.6" # Optional, it's the default for OrcaRouter pref
+# SMALL_MODEL="anthropic/claude-haiku-4.5" # Optional, it's the default for OrcaRouter pref
+```
+
+*Use case: [OrcaRouter](https://www.orcarouter.ai) is an OpenAI-compatible LLM router with one API key for 150+ models (Anthropic, OpenAI, Google, DeepSeek, and more). Set `BIG_MODEL`/`SMALL_MODEL` to any model id from its catalog — e.g. `anthropic/claude-sonnet-4.6`, `openai/gpt-4o`, `google/gemini-2.5-flash`, or the smart `orcarouter/auto` router. It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.*
+
 ## How It Works 🧩
 
 This proxy works by:
 
 1. **Receiving requests** in Anthropic's API format 📥
 2. **Translating** the requests to OpenAI format via LiteLLM 🔄
-3. **Sending** the translated request to OpenAI 📤
+3. **Sending** the translated request to the configured backend (OpenAI, Gemini, OrcaRouter, or Anthropic) 📤
 4. **Converting** the response back to Anthropic format 🔄
 5. **Returning** the formatted response to the client ✅
 

server.py

@@ -100,13 +100,23 @@ def format(self, record):
 # Get OpenAI base URL from environment (if set)
 OPENAI_BASE_URL = os.environ.get("OPENAI_BASE_URL")
 
+# Get OrcaRouter API key and base URL from environment (if set)
+ORCAROUTER_API_KEY = os.environ.get("ORCAROUTER_API_KEY")
+ORCAROUTER_BASE_URL = os.environ.get(
+    "ORCAROUTER_BASE_URL", "https://api.orcarouter.ai/v1"
+)
+
 # Get preferred provider (default to openai)
 PREFERRED_PROVIDER = os.environ.get("PREFERRED_PROVIDER", "openai").lower()
 
 # Get model mapping configuration from environment
 # Default to latest OpenAI models if not set
-BIG_MODEL = os.environ.get("BIG_MODEL", "gpt-4.1")
-SMALL_MODEL = os.environ.get("SMALL_MODEL", "gpt-4.1-mini")
+if PREFERRED_PROVIDER == "orcarouter":
+    BIG_MODEL = os.environ.get("BIG_MODEL", "anthropic/claude-sonnet-4.6")
+    SMALL_MODEL = os.environ.get("SMALL_MODEL", "anthropic/claude-haiku-4.5")
+else:
+    BIG_MODEL = os.environ.get("BIG_MODEL", "gpt-4.1")
+    SMALL_MODEL = os.environ.get("SMALL_MODEL", "gpt-4.1-mini")
 
 # List of OpenAI models
 OPENAI_MODELS = [
@@ -631,11 +641,13 @@ def convert_anthropic_to_litellm(anthropic_request: MessagesRequest) -> Dict[str
 
                 messages.append({"role": msg.role, "content": processed_content})
 
-    # Cap max_tokens for OpenAI models to their limit of 16384
+    # Cap max_tokens for OpenAI models to their limit of 16384.
+    # Skip for OrcaRouter: it routes to Claude models with larger output limits.
     max_tokens = anthropic_request.max_tokens
-    if anthropic_request.model.startswith(
-        "openai/"
-    ) or anthropic_request.model.startswith("gemini/"):
+    if (
+        anthropic_request.model.startswith("openai/")
+        or anthropic_request.model.startswith("gemini/")
+    ) and PREFERRED_PROVIDER != "orcarouter":
         max_tokens = min(max_tokens, 16384)
         logger.debug(
             f"Capping max_tokens to 16384 for OpenAI/Gemini model (original value: {anthropic_request.max_tokens})"
@@ -1242,15 +1254,22 @@ async def create_message(request: MessagesRequest, raw_request: Request):
 
         # Determine which API key to use based on the model
         if request.model.startswith("openai/"):
-            litellm_request["api_key"] = OPENAI_API_KEY
-            # Use custom OpenAI base URL if configured
-            if OPENAI_BASE_URL:
-                litellm_request["api_base"] = OPENAI_BASE_URL
+            if PREFERRED_PROVIDER == "orcarouter":
+                litellm_request["api_key"] = ORCAROUTER_API_KEY
+                litellm_request["api_base"] = ORCAROUTER_BASE_URL
                 logger.debug(
-                    f"Using OpenAI API key and custom base URL {OPENAI_BASE_URL} for model: {request.model}"
+                    f"Using OrcaRouter API key and base URL {ORCAROUTER_BASE_URL} for model: {request.model}"
                 )
             else:
-                logger.debug(f"Using OpenAI API key for model: {request.model}")
+                litellm_request["api_key"] = OPENAI_API_KEY
+                # Use custom OpenAI base URL if configured
+                if OPENAI_BASE_URL:
+                    litellm_request["api_base"] = OPENAI_BASE_URL
+                    logger.debug(
+                        f"Using OpenAI API key and custom base URL {OPENAI_BASE_URL} for model: {request.model}"
+                    )
+                else:
+                    logger.debug(f"Using OpenAI API key for model: {request.model}")
         elif request.model.startswith("gemini/"):
             if USE_VERTEX_AUTH:
                 litellm_request["vertex_project"] = VERTEX_PROJECT
@@ -1620,8 +1639,11 @@ async def count_tokens(request: TokenCountRequest, raw_request: Request):
             }
 
             # Add custom base URL for OpenAI models if configured
-            if request.model.startswith("openai/") and OPENAI_BASE_URL:
-                token_counter_args["api_base"] = OPENAI_BASE_URL
+            if request.model.startswith("openai/"):
+                if PREFERRED_PROVIDER == "orcarouter":
+                    token_counter_args["api_base"] = ORCAROUTER_BASE_URL
+                elif OPENAI_BASE_URL:
+                    token_counter_args["api_base"] = OPENAI_BASE_URL
 
             # Count tokens
             token_count = token_counter(**token_counter_args)