Skip to content

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Add OrcaRouter pre-configured provider config

jinhaosong-source2abeecbc639f
diff --git a/README.md b/README.md
index fc5ca587..ac9421d6 100644
--- a/README.md
+++ b/README.md
@@ -2902,12 +2902,15 @@ docker run --rm \
#### Using Pre-configured Providers
-The Docker image comes with built-in support for major providers (OpenAI, Anthropic, Gemini, Ollama) and pre-configured provider files for additional services (OpenRouter, DeepInfra, DeepSeek, Moonshot, Novita):
+The Docker image comes with built-in support for major providers (OpenAI, Anthropic, Gemini, Ollama) and pre-configured provider files for additional services (OpenRouter, OrcaRouter, DeepInfra, DeepSeek, Moonshot, Novita):
```bash
# Test with OpenRouter configuration
docker exec -it pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/openrouter.provider.yml
+# Test with OrcaRouter configuration
+docker exec -it pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/orcarouter.provider.yml
+
# Test with DeepInfra configuration
docker exec -it pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/deepinfra.provider.yml
@@ -2960,11 +2963,11 @@ docker exec -it pentagi /opt/pentagi/bin/ctester -config /opt/pentagi/conf/ollam
To use these configurations, your `.env` file only needs to contain:
```
-LLM_SERVER_URL=https://openrouter.ai/api/v1 # or https://api.deepinfra.com/v1/openai or https://api.openai.com/v1 or https://api.novita.ai/openai
+LLM_SERVER_URL=https://openrouter.ai/api/v1 # or https://api.orcarouter.ai/v1 or https://api.deepinfra.com/v1/openai or https://api.openai.com/v1 or https://api.novita.ai/openai
LLM_SERVER_KEY=your_api_key
LLM_SERVER_MODEL= # Leave empty, as models are specified in the config
-LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/openrouter.provider.yml # or deepinfra.provider.ymll or custom-openai.provider.yml or novita.provider.yml
-LLM_SERVER_PROVIDER= # Provider name for LiteLLM proxy (e.g., openrouter, deepseek, moonshot, novita)
+LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/openrouter.provider.yml # or orcarouter.provider.yml or deepinfra.provider.ymll or custom-openai.provider.yml or novita.provider.yml
+LLM_SERVER_PROVIDER= # Provider name for LiteLLM proxy (e.g., openrouter, orcarouter, deepseek, moonshot, novita)
LLM_SERVER_LEGACY_REASONING=false # Controls reasoning format, for OpenAI must be true (default: false)
LLM_SERVER_PRESERVE_REASONING=false # Preserve reasoning content in multi-turn conversations (required by Moonshot, default: false)
@@ -3083,6 +3086,7 @@ When using LiteLLM proxy, set the corresponding `*_PROVIDER` variable to enable
- `dashscope` - for Qwen models (`QWEN_PROVIDER=dashscope` → `dashscope/qwen-plus`)
- `openai`, `anthropic`, `gemini` - for major cloud providers
- `openrouter` - for OpenRouter aggregator
+- `orcarouter` - for OrcaRouter aggregator
- `deepinfra` - for DeepInfra hosting
- `novita` - for Novita AI
- Any other provider name configured in your LiteLLM instance
diff --git a/examples/configs/orcarouter.provider.yml b/examples/configs/orcarouter.provider.yml
new file mode 100644
index 00000000..493cd813
--- /dev/null
+++ b/examples/configs/orcarouter.provider.yml
@@ -0,0 +1,134 @@
+# OrcaRouter provider configuration (OpenAI-compatible meta-router).
+# Use via the custom LLM endpoint:
+# LLM_SERVER_URL=https://api.orcarouter.ai/v1
+# LLM_SERVER_KEY=sk-orca-...
+# LLM_SERVER_CONFIG_PATH=/opt/pentagi/conf/orcarouter.provider.yml
+# Model IDs are namespaced (e.g. openai/gpt-5.5); "orcarouter/auto" is a virtual
+# adaptive router. Prices are indicative - regenerate from https://www.orcarouter.ai/api/pricing.
+
+simple:
+ model: "google/gemini-3.5-flash"
+ temperature: 0.3
+ top_p: 0.9
+ n: 1
+ max_tokens: 4000
+ price:
+ input: 0.3
+ output: 2.5
+
+simple_json:
+ model: "google/gemini-3.5-flash"
+ temperature: 0.3
+ top_p: 1.0
+ n: 1
+ max_tokens: 4000
+ json: true
+ price:
+ input: 0.3
+ output: 2.5
+
+primary_agent:
+ model: "openai/gpt-5.5"
+ n: 1
+ max_tokens: 6000
+ reasoning:
+ effort: high
+ price:
+ input: 1.25
+ output: 10.0
+
+assistant:
+ model: "openai/gpt-5.5"
+ n: 1
+ max_tokens: 6000
+ reasoning:
+ effort: high
+ price:
+ input: 1.25
+ output: 10.0
+
+generator:
+ model: "anthropic/claude-sonnet-4.6"
+ n: 1
+ max_tokens: 12000
+ reasoning:
+ max_tokens: 4000
+ price:
+ input: 3.0
+ output: 15.0
+
+refiner:
+ model: "openai/gpt-5.5"
+ n: 1
+ max_tokens: 10000
+ reasoning:
+ effort: medium
+ price:
+ input: 1.25
+ output: 10.0
+
+adviser:
+ model: "openai/gpt-5.5"
+ n: 1
+ max_tokens: 6000
+ reasoning:
+ effort: high
+ price:
+ input: 1.25
+ output: 10.0
+
+reflector:
+ model: "google/gemini-3.5-flash"
+ temperature: 0.5
+ top_p: 1.0
+ n: 1
+ max_tokens: 4000
+ price:
+ input: 0.3
+ output: 2.5
+
+searcher:
+ model: "google/gemini-3.5-flash"
+ n: 1
+ max_tokens: 4000
+ price:
+ input: 0.3
+ output: 2.5
+
+enricher:
+ model: "google/gemini-3.5-flash"
+ temperature: 0.5
+ top_p: 1.0
+ n: 1
+ max_tokens: 6000
+ price:
+ input: 0.3
+ output: 2.5
+
+coder:
+ model: "anthropic/claude-sonnet-4.6"
+ n: 1
+ max_tokens: 8000
+ reasoning:
+ max_tokens: 2000
+ price:
+ input: 3.0
+ output: 15.0
+
+installer:
+ model: "google/gemini-3.5-flash"
+ n: 1
+ max_tokens: 4000
+ price:
+ input: 0.3
+ output: 2.5
+
+pentester:
+ model: "openai/gpt-5.5"
+ n: 1
+ max_tokens: 6000
+ reasoning:
+ effort: high
+ price:
+ input: 1.25
+ output: 10.0