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

# ModelConfig

> Configuration dataclass for defining models in a cascade — provider, cost, capabilities, and routing metadata.

# ModelConfig

Defines a model in the cascade. Models are sorted by cost — cheaper models are tried first as drafters, more expensive models serve as verifiers.

## Definition

```python theme={null}
from cascadeflow import ModelConfig

model = ModelConfig(
    name="gpt-4o-mini",
    provider="openai",
    cost=0.000375,
    supports_tools=True,
)
```

## Fields

| Field               | Type        | Default  | Description                                     |
| ------------------- | ----------- | -------- | ----------------------------------------------- |
| `name`              | `str`       | required | Model name (e.g., `"gpt-4o-mini"`)              |
| `provider`          | `str`       | required | Provider name (e.g., `"openai"`, `"anthropic"`) |
| `cost`              | `float`     | `0.0`    | Cost per 1K tokens in USD                       |
| `keywords`          | `list[str]` | `[]`     | Keywords for domain routing                     |
| `domains`           | `list[str]` | `[]`     | Domain tags for routing                         |
| `supports_tools`    | `bool`      | `False`  | Whether model supports tool calling             |
| `supports_vision`   | `bool`      | `False`  | Whether model supports vision input             |
| `max_tokens`        | `int`       | `2000`   | Max generation tokens                           |
| `latency_ms`        | `float`     | `100.0`  | Estimated latency in milliseconds               |
| `temperature`       | `float`     | `0.7`    | Default temperature                             |
| `top_p`             | `float`     | `1.0`    | Top-p sampling                                  |
| `frequency_penalty` | `float`     | `0.0`    | Frequency penalty                               |

## Providers

| Provider   | Value          | Models                                             |
| ---------- | -------------- | -------------------------------------------------- |
| OpenAI     | `"openai"`     | gpt-4o, gpt-4o-mini, gpt-5, gpt-5-mini             |
| Anthropic  | `"anthropic"`  | claude-opus-4.5, claude-sonnet-4, claude-haiku-3.5 |
| Groq       | `"groq"`       | llama-3.3-70b, mixtral-8x7b                        |
| Ollama     | `"ollama"`     | Any locally served model                           |
| vLLM       | `"vllm"`       | Any self-hosted model                              |
| OpenRouter | `"openrouter"` | Any OpenRouter model                               |
| Together   | `"together"`   | Any Together AI model                              |

## Examples

### Two-Model Cascade

```python theme={null}
from cascadeflow import CascadeAgent, ModelConfig

agent = CascadeAgent(models=[
    ModelConfig(name="gpt-4o-mini", provider="openai", cost=0.000375),
    ModelConfig(name="gpt-4o", provider="openai", cost=0.00625),
])
```

### Multi-Provider Cascade

```python theme={null}
agent = CascadeAgent(models=[
    ModelConfig(name="llama-3.3-70b", provider="groq", cost=0.00059),
    ModelConfig(name="gpt-4o-mini", provider="openai", cost=0.000375),
    ModelConfig(name="claude-sonnet-4", provider="anthropic", cost=0.009),
])
```

### With Domain Routing

```python theme={null}
legal_model = ModelConfig(
    name="gpt-4o",
    provider="openai",
    cost=0.00625,
    domains=["legal", "compliance"],
    keywords=["contract", "regulation", "statute"],
)
```

### Local Model

```python theme={null}
local = ModelConfig(
    name="llama3:8b",
    provider="ollama",
    cost=0.0,  # Free
    latency_ms=50.0,
)
```