> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/nullclaw/nullclaw/llms.txt
> Use this file to discover all available pages before exploring further.

# Model Configuration

> Configure AI providers and model selection for NullClaw

NullClaw supports 50+ AI providers through a unified configuration interface. Configure provider credentials, default models, and temperature settings.

## Basic Model Configuration

### Provider Setup

Configure providers in the `models.providers` section:

```json theme={null}
{
  "models": {
    "providers": {
      "openrouter": {
        "api_key": "YOUR_OPENROUTER_API_KEY"
      },
      "openai": {
        "api_key": "YOUR_OPENAI_API_KEY"
      }
    }
  }
}
```

<ParamField path="models.providers" type="object">
  Map of provider name to provider configuration. Each key is a provider identifier (e.g., `openrouter`, `openai`, `anthropic`).
</ParamField>

<ParamField path="models.providers.<name>.api_key" type="string" required>
  API key for the provider. Can also be set via environment variables like `OPENROUTER_API_KEY`.
</ParamField>

<ParamField path="models.providers.<name>.base_url" type="string">
  Optional custom base URL for API requests. Useful for proxies or compatible providers.
</ParamField>

<ParamField path="models.providers.<name>.native_tools" type="boolean" default="true">
  Whether the provider supports native OpenAI-style tool calls. Set to `false` to use XML tool format via system prompt.
</ParamField>

## Default Model Selection

Configure the default model used by agents:

```json theme={null}
{
  "agents": {
    "defaults": {
      "model": {
        "primary": "openrouter/anthropic/claude-sonnet-4"
      }
    }
  },
  "default_provider": "openrouter"
}
```

<ParamField path="agents.defaults.model.primary" type="string" default="openrouter/anthropic/claude-sonnet-4">
  Primary model identifier. Format: `provider/model-name` or just `model-name` if using the default provider.
</ParamField>

<ParamField path="default_provider" type="string" default="openrouter">
  Default provider when model identifier doesn't specify one.
</ParamField>

<ParamField path="default_model" type="string">
  Legacy fallback model name (prefer `agents.defaults.model.primary`).
</ParamField>

## Temperature Configuration

Control model creativity and randomness:

```json theme={null}
{
  "default_temperature": 0.7
}
```

<ParamField path="default_temperature" type="number" default="0.7">
  Sampling temperature (0.0 to 1.0). Lower values are more deterministic, higher values more creative.
</ParamField>

<ParamField path="reasoning_effort" type="string">
  Optional reasoning effort level for compatible models (e.g., `low`, `medium`, `high`).
</ParamField>

## Multiple Provider Configuration

You can configure multiple providers for fallback and redundancy:

```json theme={null}
{
  "models": {
    "providers": {
      "openrouter": {
        "api_key": "sk-or-v1-..."
      },
      "openai": {
        "api_key": "sk-..."
      },
      "anthropic": {
        "api_key": "sk-ant-..."
      }
    }
  },
  "reliability": {
    "fallback_providers": ["openai", "anthropic"],
    "provider_retries": 2,
    "provider_backoff_ms": 500
  }
}
```

<ParamField path="reliability.fallback_providers" type="array">
  Ordered list of fallback provider names to try if the primary fails.
</ParamField>

<ParamField path="reliability.provider_retries" type="number" default="2">
  Number of retry attempts per provider before moving to fallback.
</ParamField>

<ParamField path="reliability.provider_backoff_ms" type="number" default="500">
  Milliseconds to wait between retry attempts (exponential backoff).
</ParamField>

## Supported Providers

NullClaw supports these providers out of the box:

* **openrouter** — Multi-provider router (recommended)
* **openai** — GPT-4, GPT-3.5, and embedding models
* **anthropic** — Claude 3/4 family
* **google** — Gemini models
* **mistral** — Mistral AI models
* **groq** — Fast inference for open models
* **ollama** — Local model hosting
* **cohere** — Cohere models
* **together** — Together AI models
* And 40+ more compatible providers

## Environment Variable Overrides

You can set API keys via environment variables instead of config file:

```bash theme={null}
export OPENROUTER_API_KEY="sk-or-v1-..."
export OPENAI_API_KEY="sk-..."
export ANTHROPIC_API_KEY="sk-ant-..."
```

Environment variables take precedence over config file values.

## Example: Local Model with Ollama

Run models locally using Ollama:

```json theme={null}
{
  "models": {
    "providers": {
      "ollama": {
        "base_url": "http://localhost:11434"
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "ollama/llama3"
      }
    }
  },
  "default_provider": "ollama"
}
```

<Info>
  No API key is required for Ollama. Just ensure the Ollama server is running locally.
</Info>