On this page

Custom Providers

Cyberstrike bundles many providers beyond the big four — and you can connect any OpenAI-compatible endpoint yourself.

📸 SCREENSHOT: custom-provider-config.png

Custom provider configuration

Built-in Extra Providers

These are already bundled — you don’t need any provider config. Just set the API-key environment variable and select a model as provider-id/model:

Provider id	Env var	Example model
`groq`	`GROQ_API_KEY`	`groq/llama-3.3-70b-versatile`
`togetherai`	`TOGETHER_API_KEY`	`togetherai/meta-llama/Llama-3.3-70B-Instruct-Turbo`
`deepinfra`	`DEEPINFRA_API_KEY`	`deepinfra/meta-llama/Llama-3.3-70B-Instruct`
`perplexity`	`PERPLEXITY_API_KEY`	`perplexity/sonar`
`openrouter`	`OPENROUTER_API_KEY`	`openrouter/anthropic/claude-sonnet-4`

export GROQ_API_KEY="gsk_..."
cyberstrike --model groq/llama-3.3-70b-versatile

Others (mistral, xai, deepseek, cohere, cerebras, and more) work the same way — set their key and use provider-id/model. See AI Providers.

Custom OpenAI-Compatible Provider

For an endpoint that isn’t bundled (Fireworks, vLLM, LM Studio, a private gateway), define it under provider. Loading is triggered by the top-level api field (the base URL); npm defaults to @ai-sdk/openai-compatible, and you list the models you want:

{
  "provider": {
    "my-endpoint": {
      "name": "My Endpoint",
      "api": "https://api.example.com/v1",
      "options": { "apiKey": "{env:MY_API_KEY}" },
      "models": {
        "my-model": { "name": "My Model" }
      }
    }
  },
  "model": "my-endpoint/my-model"
}

vLLM

{
  "provider": {
    "vllm": {
      "name": "vLLM",
      "api": "http://localhost:8000/v1",
      "models": { "llama-3.3-70b": { "name": "Llama 3.3 70B" } }
    }
  }
}

LM Studio

{
  "provider": {
    "lmstudio": {
      "name": "LM Studio",
      "api": "http://localhost:1234/v1",
      "models": { "local-model": { "name": "Local Model" } }
    }
  }
}

Caution

A config-only provider is loaded because it has an api URL — options.baseURL alone won’t register it. Use the top-level api field.

Azure OpenAI

{
  "provider": {
    "azure": {
      "name": "Azure OpenAI",
      "options": {
        "apiKey": "{env:AZURE_API_KEY}"
      }
    }
  }
}

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

Troubleshooting

401 Unauthorized — check the API key env var and that it’s referenced with {env:VAR}.
Model not found — the model id must match the provider’s format and be listed under models for a custom provider.
Unexpected response — the endpoint may not be fully OpenAI-compatible; tool calling and streaming vary by provider.

AI Providers - All providers and keys
Ollama - Local models (a custom provider)
Configuration - Provider config options