Custom Providers

Connect Cyberstrike to any OpenAI-compatible API endpoint or custom provider.

📸 SCREENSHOT: custom-provider-config.png

Custom provider configuration

OpenAI-Compatible APIs

Many services provide OpenAI-compatible endpoints:

Service	Base URL
Together AI	https://api.together.xyz/v1
Anyscale	https://api.endpoints.anyscale.com/v1
Fireworks	https://api.fireworks.ai/inference/v1
Groq	https://api.groq.com/openai/v1
DeepInfra	https://api.deepinfra.com/v1/openai
Perplexity	https://api.perplexity.ai

Basic Configuration

Generic OpenAI-Compatible

{
  "provider": {
    "openai-compatible": {
      "name": "Custom Provider",
      "options": {
        "baseURL": "https://api.example.com/v1",
        "apiKey": "{env:CUSTOM_API_KEY}"
      }
    }
  }
}

Command Line

cyberstrike --model openai-compatible/model-name

Provider Examples

Groq

Fast inference with Groq:

{
  "provider": {
    "groq": {
      "name": "Groq",
      "options": {
        "baseURL": "https://api.groq.com/openai/v1",
        "apiKey": "{env:GROQ_API_KEY}"
      }
    }
  },
  "model": "groq/llama-3.3-70b-versatile"
}

Available models:

llama-3.3-70b-versatile
llama-3.1-8b-instant
mixtral-8x7b-32768

Together AI

{
  "provider": {
    "together": {
      "name": "Together AI",
      "options": {
        "baseURL": "https://api.together.xyz/v1",
        "apiKey": "{env:TOGETHER_API_KEY}"
      }
    }
  },
  "model": "together/meta-llama/Llama-3.3-70B-Instruct-Turbo"
}

Fireworks AI

{
  "provider": {
    "fireworks": {
      "name": "Fireworks",
      "options": {
        "baseURL": "https://api.fireworks.ai/inference/v1",
        "apiKey": "{env:FIREWORKS_API_KEY}"
      }
    }
  },
  "model": "fireworks/accounts/fireworks/models/llama-v3p3-70b-instruct"
}

DeepInfra

{
  "provider": {
    "deepinfra": {
      "name": "DeepInfra",
      "options": {
        "baseURL": "https://api.deepinfra.com/v1/openai",
        "apiKey": "{env:DEEPINFRA_API_KEY}"
      }
    }
  },
  "model": "deepinfra/meta-llama/Llama-3.3-70B-Instruct"
}

OpenRouter

Access multiple providers through OpenRouter:

{
  "provider": {
    "openrouter": {
      "options": {
        "apiKey": "{env:OPENROUTER_API_KEY}"
      }
    }
  },
  "model": "openrouter/anthropic/claude-sonnet-4"
}

Available Models

OpenRouter provides access to:

Anthropic (Claude)
OpenAI (GPT-4)
Google (Gemini)
Meta (Llama)
Mistral
And many more

Model Selection

cyberstrike --model openrouter/openai/gpt-4o
cyberstrike --model openrouter/anthropic/claude-sonnet-4
cyberstrike --model openrouter/google/gemini-pro

Self-Hosted Solutions

vLLM

{
  "provider": {
    "vllm": {
      "name": "vLLM Server",
      "options": {
        "baseURL": "http://localhost:8000/v1",
        "apiKey": "dummy"
      }
    }
  }
}

Start vLLM:

python -m vllm.entrypoints.openai.api_server \
  --model meta-llama/Llama-3.3-70B-Instruct \
  --port 8000

Text Generation WebUI

{
  "provider": {
    "textgen": {
      "name": "Text Generation WebUI",
      "options": {
        "baseURL": "http://localhost:5000/v1",
        "apiKey": "dummy"
      }
    }
  }
}

LM Studio

{
  "provider": {
    "lmstudio": {
      "name": "LM Studio",
      "options": {
        "baseURL": "http://localhost:1234/v1",
        "apiKey": "lm-studio"
      }
    }
  }
}

Azure OpenAI

{
  "provider": {
    "azure": {
      "name": "Azure OpenAI",
      "options": {
        "baseURL": "https://your-resource.openai.azure.com/openai/deployments/your-deployment",
        "apiKey": "{env:AZURE_API_KEY}",
        "apiVersion": "2024-02-15-preview"
      }
    }
  }
}

Environment Variables

export AZURE_API_KEY="..."
export AZURE_RESOURCE_NAME="your-resource"
export AZURE_DEPLOYMENT_NAME="your-deployment"

Advanced Configuration

Custom Headers

{
  "provider": {
    "custom": {
      "options": {
        "baseURL": "https://api.example.com/v1",
        "apiKey": "your-key",
        "headers": {
          "X-Custom-Header": "value"
        }
      }
    }
  }
}

Timeout and Retries

{
  "provider": {
    "custom": {
      "options": {
        "baseURL": "https://api.example.com/v1",
        "timeout": 120000,
        "maxRetries": 3
      }
    }
  }
}

Proxy Configuration

{
  "provider": {
    "custom": {
      "options": {
        "baseURL": "https://api.example.com/v1",
        "httpAgent": {
          "proxy": "http://proxy.example.com:8080"
        }
      }
    }
  }
}

Model Mapping

Map custom model names:

{
  "provider": {
    "custom": {
      "options": {
        "baseURL": "https://api.example.com/v1",
        "modelMapping": {
          "gpt-4": "custom-gpt-4-equivalent",
          "claude-sonnet": "custom-claude-equivalent"
        }
      }
    }
  }
}

Testing Custom Providers

Verify Connection

cyberstrike --model custom/model-name

Test Message

> Hello, can you confirm you're working?

Check Model List

Some providers support listing models:

curl https://api.example.com/v1/models \
  -H "Authorization: Bearer $API_KEY"

Troubleshooting

Authentication Failed

Error: 401 Unauthorized

Verify:

API key is correct
Key has required permissions
Authorization header format

Model Not Found

Error: Model not found

Check:

Model ID matches provider’s format
Model is available on the provider
Correct provider is selected

Connection Timeout

Error: Request timeout

Solutions:

Increase timeout value
Check network connectivity
Verify base URL is correct

Invalid Response Format

Error: Unexpected response format

The provider may not be fully OpenAI-compatible. Check:

API documentation
Response structure
Required headers

Caution

Not all OpenAI-compatible APIs support all features. Tool calling and streaming may vary by provider.

Providers Overview - All providers
Ollama - Local models
Configuration - Full options