> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.runtype.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.runtype.com/_mcp/server.

# Get grouped models

GET https://api.runtype.com/v1/model-configs/grouped

Get models grouped by base model with all provider options. Supports filtering to configured-only models. The account custom models (`isCustom: true`) always follow the catalog groups; `category=custom` returns only them. `credentialPolicy` states which providers may serve a call.

Reference: https://docs.runtype.com/api-reference/runtype-api/model-configs/get-grouped-models

## Authentication

- `Authorization` header (bearer token, required) — API key or Clerk session token

## Servers

- `https://api.runtype.com` (Production, default)
- `https://api.runtype-staging.com` (Staging)

## Request

### Query parameters

- `showAll` (string, optional)
- `category` (string, optional)
- `configured` (string, optional)

## Response

### 200

Grouped model catalog

- `data` (list of V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItems, required)
- `stats` (V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaStats, required)
- `total` (integer, required)
- `credentialPolicy` (V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaCredentialPolicy, optional) — Which providers may serve a model call for this account. A model whose `keyStatus` is `needs_setup` is refused at execution.

## Errors

### 401 Unauthorized Error

Unauthorized

- `error` (string, required)
- `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs.
- `details` (list of ErrorDetailsItems, optional)
- `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs.

### 500 Internal Server Error

Internal server error

- `error` (string, required)
- `code` (string, optional) — Stable error code. `insufficient_scope` marks an API key that lacks a scope this request needs.
- `details` (list of ErrorDetailsItems, optional)
- `requiredScopes` (list of string, optional) — On `insufficient_scope`: every API key scope this request needs.

## Types

### V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItems

- `baseModel` (string, required)
- `configuredConfigs` (list of V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsConfiguredConfigsItems, required)
- `configuredProviders` (list of string, required)
- `contextLength` (double, required)
- `creator` (string, required)
- `creatorDisplayName` (string, required)
- `displayName` (string, required)
- `isConfigured` (boolean, required)
- `lowestCost` (double, required)
- `maxOutputTokens` (double, required)
- `providers` (list of V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsProvidersItems, required)
- `tags` (list of string, required)
- `creditPromoLabel` (string, optional, nullable) — Plain-language discount callout for the family, e.g. "90% off". null when undiscounted.
- `creditPromoMultiplier` (double, optional) — Factor platform-key spend on this model family is billed at while a credit promo is active (0.1 = 90% off). Follows the routed primary provider (a same-model failover onto another provider bills at that provider nominal price, undiscounted); 1 when undiscounted.
- `isCustom` (boolean, optional) — True for a model the account declared itself that the platform catalog does not list. `baseModel` is then the exact model id to run.
- `reasoningCapability` (V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsReasoningCapability, optional)
- `supportsReasoning` (boolean, optional) — True when any provider entry supports extended reasoning
- `supportsToolUse` (boolean, optional) — True when any provider entry supports tool/function calling
- `supportsVision` (boolean, optional) — True when any provider entry supports image input
- `uiCategory` (string, optional)
- `uiPriority` (double, optional)

### V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaStats

- `providersWithPlatformKeys` (list of string, required)
- `totalModels` (integer, required)
- `uniqueBaseModels` (integer, required)

### V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaCredentialPolicy

Which providers may serve a model call for this account. A model whose `keyStatus` is `needs_setup` is refused at execution.

- `blockedProviders` (list of string, required) — Providers organization policy refuses until a credential is connected.
- `byokProviders` (list of string, required) — Providers served by the account own credentials. `generic-openai` is its custom inference endpoint.
- `mode` (enum, required) — `byok_only`: the organization requires its own model keys; only `byokProviders` serve calls and Runtype platform keys are never used. `mixed`: some providers run on the account credentials and others on platform keys. `platform`: the account has connected no provider credentials.
  - Allowed values: `byok_only`, `mixed`, `platform`
- `platformProviders` (list of string, required) — Providers served by Runtype platform keys.
- `summary` (string, required) — Plain-language statement of the same facts.

### ErrorDetailsItems

- `message` (string, required)
- `code` (string, optional) — Stable Runtype validation code (e.g. MISSING_REQUIRED_FIELD, INVALID_ENUM).
- `path` (string, optional) — Dotted JSON path to the offending field.
- `suggestion` (string, optional) — Actionable hint (allowed values, accepted range, …).

### V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsConfiguredConfigsItems

- `id` (string, required)
- `modelId` (string, required)
- `provider` (string, required)

### V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsProvidersItems

- `costPer1kTokens` (double, required)
- `hasPlatformKey` (boolean, required)
- `inputCostPer1kTokens` (double, required)
- `modelId` (string, required)
- `outputCostPer1kTokens` (double, required)
- `provider` (string, required)
- `providerDisplayName` (string, required)
- `creditPromoLabel` (string, optional, nullable) — Plain-language discount callout, e.g. "90% off". null when undiscounted.
- `creditPromoMultiplier` (double, optional) — Factor platform-key spend on this listing is billed at (0.1 = 90% off); 1 when undiscounted.
- `keyStatus` (enum, optional)
  - Allowed values: `platform`, `custom`, `needs_setup`

### V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsReasoningCapability

- `supported` (boolean, required)
- `anthropicThinkingMode` (enum, optional) — Anthropic only: the thinking request shape sent. adaptive (Claude 4.6 and later, including the Claude 5 family) accepts effort and rejects budgetTokens; enabled is the legacy budgetTokens form.
  - Allowed values: `adaptive`, `enabled`
- `builtInReasoning` (boolean, optional) — The model always reasons (GPT-5 / o-series); disabling is an effort floor, not off.
- `googleThinkingMode` (enum, optional)
  - Allowed values: `budget`, `level`
- `options` (V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsReasoningCapabilityOptions, optional) — Which reasoning knobs this model's API accepts (catalog-sourced from models.dev reasoning_options). Absent when the catalog has no claim for the model.
- `provider` (string, optional)
- `supportsReasoningSummary` (boolean, optional)

### V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsReasoningCapabilityOptions

Which reasoning knobs this model's API accepts (catalog-sourced from models.dev reasoning_options). Absent when the catalog has no claim for the model.

- `budgetTokens` (V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsReasoningCapabilityOptionsBudgetTokens, optional)
- `effort` (list of string, optional)
- `toggle` (boolean, optional)

### V1ModelConfigsGroupedGetResponsesContentApplicationJsonSchemaDataItemsReasoningCapabilityOptionsBudgetTokens

- `max` (double, optional)
- `min` (double, optional)

## Examples

**Response**

```json
{
  "data": [
    {
      "baseModel": "string",
      "configuredConfigs": [
        {
          "id": "string",
          "modelId": "string",
          "provider": "string"
        }
      ],
      "configuredProviders": [
        "string"
      ],
      "contextLength": 1.1,
      "creator": "string",
      "creatorDisplayName": "string",
      "displayName": "string",
      "isConfigured": true,
      "lowestCost": 1.1,
      "maxOutputTokens": 1.1,
      "providers": [
        {
          "costPer1kTokens": 1.1,
          "hasPlatformKey": true,
          "inputCostPer1kTokens": 1.1,
          "modelId": "string",
          "outputCostPer1kTokens": 1.1,
          "provider": "string",
          "providerDisplayName": "string",
          "creditPromoLabel": "string",
          "creditPromoMultiplier": 1.1,
          "keyStatus": "platform"
        }
      ],
      "tags": [
        "string"
      ],
      "creditPromoLabel": "string",
      "creditPromoMultiplier": 1.1,
      "isCustom": true,
      "reasoningCapability": {
        "supported": true,
        "anthropicThinkingMode": "adaptive",
        "builtInReasoning": true,
        "googleThinkingMode": "budget",
        "options": {
          "budgetTokens": {
            "max": 1.1,
            "min": 1.1
          },
          "effort": [
            "string"
          ],
          "toggle": true
        },
        "provider": "string",
        "supportsReasoningSummary": true
      },
      "supportsReasoning": true,
      "supportsToolUse": true,
      "supportsVision": true,
      "uiCategory": "string",
      "uiPriority": 1.1
    }
  ],
  "stats": {
    "providersWithPlatformKeys": [
      "string"
    ],
    "totalModels": 1,
    "uniqueBaseModels": 1
  },
  "total": 1,
  "credentialPolicy": {
    "blockedProviders": [
      "string"
    ],
    "byokProviders": [
      "string"
    ],
    "mode": "byok_only",
    "platformProviders": [
      "string"
    ],
    "summary": "string"
  }
}
```

**SDK Code**

```python
import requests

url = "https://api.runtype.com/v1/model-configs/grouped"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.json())
```

```javascript
const url = 'https://api.runtype.com/v1/model-configs/grouped';
const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
```

```go
package main

import (
	"fmt"
	"net/http"
	"io"
)

func main() {

	url := "https://api.runtype.com/v1/model-configs/grouped"

	req, _ := http.NewRequest("GET", url, nil)

	req.Header.Add("Authorization", "Bearer <token>")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(res)
	fmt.Println(string(body))

}
```

```ruby
require 'uri'
require 'net/http'

url = URI("https://api.runtype.com/v1/model-configs/grouped")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Get.new(url)
request["Authorization"] = 'Bearer <token>'

response = http.request(request)
puts response.read_body
```

```java
import com.mashape.unirest.http.HttpResponse;
import com.mashape.unirest.http.Unirest;

HttpResponse<String> response = Unirest.get("https://api.runtype.com/v1/model-configs/grouped")
  .header("Authorization", "Bearer <token>")
  .asString();
```

```php
<?php
require_once('vendor/autoload.php');

$client = new \GuzzleHttp\Client();

$response = $client->request('GET', 'https://api.runtype.com/v1/model-configs/grouped', [
  'headers' => [
    'Authorization' => 'Bearer <token>',
  ],
]);

echo $response->getBody();
```

```csharp
using RestSharp;

var client = new RestClient("https://api.runtype.com/v1/model-configs/grouped");
var request = new RestRequest(Method.GET);
request.AddHeader("Authorization", "Bearer <token>");
IRestResponse response = client.Execute(request);
```

```swift
import Foundation

let headers = ["Authorization": "Bearer <token>"]

let request = NSMutableURLRequest(url: NSURL(string: "https://api.runtype.com/v1/model-configs/grouped")! as URL,
                                        cachePolicy: .useProtocolCachePolicy,
                                    timeoutInterval: 10.0)
request.httpMethod = "GET"
request.allHTTPHeaderFields = headers

let session = URLSession.shared
let dataTask = session.dataTask(with: request as URLRequest, completionHandler: { (data, response, error) -> Void in
  if (error != nil) {
    print(error as Any)
  } else {
    let httpResponse = response as? HTTPURLResponse
    print(httpResponse)
  }
})

dataTask.resume()
```