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

# Get one model from the catalogue by id

> Check a single model before setting it on an assistant. Every way this fails returns the same 404: unknown provider, no credential for it, or no such model.

Use this to check a single model before you set it on an assistant. The path is the model's `id` from [List models](/api-reference/models/list-models), split at the slash.

Every way this can fail returns the same `404`: an unknown provider, a provider this deployment has no credential for, a model that is not in the catalogue, or a name that is not a model at all. It requires a role that can read assistants, which every role except `dataset_operator` has.

<ParamField path="provider" type="string" required>
  The provider identifier, for example `anthropic`.
</ParamField>

<ParamField path="name" type="string" required>
  The model name within the provider, for example `claude-sonnet-5`.
</ParamField>

## Response

<ResponseField name="id" type="string" required>
  The qualified selector, `provider/name`. Use this as an assistant's `model`.
</ResponseField>

<ResponseField name="provider" type="string" required>
  The provider: `anthropic`, `openai` or `google`.
</ResponseField>

<ResponseField name="name" type="string" required>
  The model name within its provider.
</ResponseField>

<ResponseField name="capabilities" type="string[]" required>
  What the model supports, sorted alphabetically. Values: `chat`, `embedding`, `rerank`,
  `streaming`.
</ResponseField>

<ResponseField name="context_window" type="integer | null" required>
  Input tokens the model accepts, when known.
</ResponseField>

<ResponseField name="max_output_tokens" type="integer | null" required>
  Output tokens the model can produce, when known.
</ResponseField>

<RequestExample>
  ```bash cURL theme={"theme":{"light":"github-light","dark":"github-dark"}}
  curl --request GET "$MITHUNAI_URL/arukz/api/v1/models/anthropic/claude-sonnet-5" \
    --header "Authorization: Bearer $MITHUNAI_API_KEY"
  ```

  ```python Python theme={"theme":{"light":"github-light","dark":"github-dark"}}
  import os, requests

  response = requests.get(
      f"{os.environ['MITHUNAI_URL']}/arukz/api/v1/models/anthropic/claude-sonnet-5",
      headers={"Authorization": f"Bearer {os.environ['MITHUNAI_API_KEY']}"},
      timeout=60,
  )
  response.raise_for_status()
  print(response.json())
  ```

  ```javascript JavaScript theme={"theme":{"light":"github-light","dark":"github-dark"}}
  const response = await fetch(
    `${process.env.MITHUNAI_URL}/arukz/api/v1/models/anthropic/claude-sonnet-5`,
    { headers: { Authorization: `Bearer ${process.env.MITHUNAI_API_KEY}` } },
  )
  console.log(await response.json())
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={"theme":{"light":"github-light","dark":"github-dark"}}
  {
    "id": "anthropic/claude-sonnet-5",
    "provider": "anthropic",
    "name": "claude-sonnet-5",
    "capabilities": ["chat", "streaming"],
    "context_window": 1000000,
    "max_output_tokens": 128000
  }
  ```

  ```json 404 theme={"theme":{"light":"github-light","dark":"github-dark"}}
  { "code": "not_found", "message": "The requested resource was not found." }
  ```
</ResponseExample>