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

# List models

> Get all available AI models with pricing, context windows, and capabilities

<Tip>
  **Visual Model Browser:** Prefer a visual interface? [Browse all 195+ models](https://case.dev/models) with filtering, search, and comparison.
</Tip>

```bash title="Endpoint" theme={"theme":{"light":"github-light","dark":"one-dark-pro"}}
GET /llm/v1/models
```

<CodeGroup>
  ```bash title="cURL" theme={"theme":{"light":"github-light","dark":"one-dark-pro"}}
  curl https://api.case.dev/llm/v1/models \
    -H "Authorization: Bearer sk_case_YOUR_API_KEY"
  ```

  ```bash title="CLI" theme={"theme":{"light":"github-light","dark":"one-dark-pro"}}
  casedev llm:v1 list-models
  ```

  ```typescript title="Typescript" theme={"theme":{"light":"github-light","dark":"one-dark-pro"}}
  import Casedev from 'casedev';

  const client = new Casedev({ apiKey: 'sk_case_YOUR_API_KEY' });

  const { data: models } = await client.llm.v1.listModels();

  for (const model of models) {
    console.log(`${model.id}: $${model.pricing.input}/input, $${model.pricing.output}/output`);
  }
  ```

  ```python title="Python" theme={"theme":{"light":"github-light","dark":"one-dark-pro"}}
  import casedev

  client = casedev.Casedev(api_key='sk_case_YOUR_API_KEY')

  result = client.llm.v1.list_models()

  for model in result.data:
      print(f'{model.id}: ${model.pricing.input}/input, ${model.pricing.output}/output')
  ```

  ```go title="Go" theme={"theme":{"light":"github-light","dark":"one-dark-pro"}}
  result, _ := client.Llm.V1.ListModels(ctx)
  for _, model := range result.Data {
  	fmt.Printf("%s: $%s/input, $%s/output\n", model.ID, model.Pricing.Input, model.Pricing.Output)
  }
  ```
</CodeGroup>

```json title="Response" theme={"theme":{"light":"github-light","dark":"one-dark-pro"}}
{
  "object": "list",
  "data": [
    {
      "id": "casemark/core-large",
      "name": "CaseMark Core Large",
      "description": "CaseMark's flagship legal reasoning model powered by Kimi K2.6",
      "owned_by": "casemark",
      "context_window": 200000,
      "max_tokens": 128000,
      "tags": ["reasoning", "legal", "tool-use"],
      "pricing": {
        "input": "0.0000015",
        "output": "0.0000035"
      }
    },
    {
      "id": "anthropic/claude-sonnet-4.5",
      "name": "Claude Sonnet 4.5",
      "description": "Anthropic's latest model with vision and reasoning",
      "owned_by": "anthropic",
      "context_window": 200000,
      "max_tokens": 64000,
      "tags": ["vision", "reasoning", "tool-use"],
      "pricing": {
        "input": "0.0000015",
        "output": "0.000015"
      }
    }
  ]
}
```

## Popular models

| Model                         | Context | Best for                   | Input \$/MTok |
| ----------------------------- | ------- | -------------------------- | ------------- |
| `casemark/core-large`         | 200K    | Legal reasoning, workflows | \$1.50        |
| `anthropic/claude-sonnet-4.5` | 200K    | Complex analysis, vision   | \$6.00        |
| `anthropic/claude-opus-4`     | 200K    | Hardest tasks              | \$20.00       |
| `openai/gpt-4o`               | 128K    | General purpose, vision    | \$5.00        |
| `openai/gpt-4o-mini`          | 128K    | Fast, cheap                | \$0.30        |
| `google/gemini-2.5-flash`     | 1M      | Very long documents        | \$0.15        |
| `deepseek/deepseek-chat`      | 64K     | Cost-effective             | \$0.28        |

## Model capabilities

| Tag         | Meaning                    |
| ----------- | -------------------------- |
| `vision`    | Can process images         |
| `tool-use`  | Supports function calling  |
| `reasoning` | Enhanced reasoning         |
| `fast`      | Optimized for low latency  |
| `legal`     | Fine-tuned for legal tasks |

<Info>
  **Prices are per token.** Multiply by 1,000,000 for price per million tokens (MTok).
</Info>