---
title: "Replace a custom model"
description: "Replace editable fields for a custom model. The `model_name` path value remains the identifier."
---

<a id="playground-button:docs/apis/models/replace-custom-model"></a>

**PUT** `https://api.respan.ai/api/models/{model_name}/`

Replace editable fields for a custom model. The `model_name` path value remains the identifier.

## Servers

`https://api.respan.ai` — Respan API Server

<a id="request.auth"></a>

## Authentication

<a id="request.auth.Authorization"></a>

### RespanApiKey

Use your Respan API key for Respan API authentication. Enter only the Respan API key value; clients send Authorization: Bearer &lt;RESPAN_API_KEY&gt;. For /api/responses, provider credentials such as Perplexity, OpenAI, or Azure OpenAI go in Settings -&gt; Providers or respan_params.credential_override in the request body, not in this authentication field.

HTTP scheme: `bearer`; format: `Respan API key`.


```http
Authorization: Bearer $RESPAN_API_KEY
```


**Or:**

### DashboardJwt

Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.

HTTP scheme: `bearer`; format: `Dashboard JWT`.


```http
Authorization: Bearer $RESPAN_DASHBOARD_JWT
```


<a id="request.path"></a>

## Path parameters


| Parameter | Type | Required | Description and constraints |
| --- | --- | --- | --- |
| <a id="request.path.model_name"></a>`model_name` | `string` | Required | Model name. The route supports names containing slashes, such as `openai/gpt-4o-mini`. |


<a id="request"></a>

## Request body

A request body is required.

### application/json


| Field | Type | Requirement | Description and constraints |
| --- | --- | --- | --- |
| `$` | `object` | Required body | — |
| <a id="request.body.base_model_name"></a>`base_model_name` | `string` | Optional | Base model to inherit properties from.<br />Example: `"gpt-4o"` |
| <a id="request.body.custom_provider_id"></a>`custom_provider_id` | `string` | Optional | Custom provider string ID or provider identifier to associate.<br />Example: `"my-vllm"` |
| <a id="request.body.provider_id"></a>`provider_id` | `string` | Optional | Alternative to `custom_provider_id`.<br />Example: `"my-vllm"` |
| <a id="request.body.input_cost"></a>`input_cost` | `number` | Optional | Cost per 1M input tokens in USD.<br />Example: `2.5` |
| <a id="request.body.output_cost"></a>`output_cost` | `number` | Optional | Cost per 1M output tokens in USD.<br />Example: `10` |
| <a id="request.body.cache_hit_input_cost"></a>`cache_hit_input_cost` | `number` | Optional | Cost per 1M cached input tokens in USD. |
| <a id="request.body.cache_creation_input_cost"></a>`cache_creation_input_cost` | `number` | Optional | Cost per 1M cache creation input tokens in USD. |
| <a id="request.body.max_context_window"></a>`max_context_window` | `integer` | Optional | Maximum context window size.<br />Example: `128000` |
| <a id="request.body.function_call"></a>`function_call` | `integer` | Optional | Allowed: `0`, `1` |
| <a id="request.body.image_support"></a>`image_support` | `integer` | Optional | Allowed: `0`, `1` |
| <a id="request.body.supported_params_override"></a>`supported_params_override` | `object` | Optional | Partial override for the model's parameters: a map of parameter name to a parameter definition with the same shape as `supported_params` entries (`name`, `type`, `default`, `range` with `min` and `max`, `description`, `required`), or `null` to remove the parameter. Replaces any earlier override. The response returns the computed `supported_params`.<br />Additional properties are allowed |


<details class="api-schema-source">
<summary>OpenAPI request schema</summary>


```json
{
  "type": "object",
  "properties": {
    "base_model_name": {
      "type": "string",
      "description": "Base model to inherit properties from.",
      "example": "gpt-4o"
    },
    "custom_provider_id": {
      "type": "string",
      "description": "Custom provider string ID or provider identifier to associate.",
      "example": "my-vllm"
    },
    "provider_id": {
      "type": "string",
      "description": "Alternative to `custom_provider_id`.",
      "example": "my-vllm"
    },
    "input_cost": {
      "type": "number",
      "description": "Cost per 1M input tokens in USD.",
      "example": 2.5
    },
    "output_cost": {
      "type": "number",
      "description": "Cost per 1M output tokens in USD.",
      "example": 10
    },
    "cache_hit_input_cost": {
      "type": "number",
      "description": "Cost per 1M cached input tokens in USD."
    },
    "cache_creation_input_cost": {
      "type": "number",
      "description": "Cost per 1M cache creation input tokens in USD."
    },
    "max_context_window": {
      "type": "integer",
      "description": "Maximum context window size.",
      "example": 128000
    },
    "function_call": {
      "type": "integer",
      "enum": [
        0,
        1
      ]
    },
    "image_support": {
      "type": "integer",
      "enum": [
        0,
        1
      ]
    },
    "supported_params_override": {
      "type": "object",
      "description": "Partial override for the model's parameters: a map of parameter name to a parameter definition with the same shape as `supported_params` entries (`name`, `type`, `default`, `range` with `min` and `max`, `description`, `required`), or `null` to remove the parameter. Replaces any earlier override. The response returns the computed `supported_params`.",
      "additionalProperties": true
    }
  }
}
```

</details>

<a id="response"></a>

## Responses

### 200

Updated model.

#### application/json


| Field | Type | Requirement | Description and constraints |
| --- | --- | --- | --- |
| `$` | `object` | Body | Additional properties are allowed |
| <a id="response.body.id"></a>`id` | `string` | Required in parent | Model string ID. Same value as `model_name`.<br />Example: `"my-custom-gpt-4o"` |
| <a id="response.body.model_name"></a>`model_name` | `string` | Required in parent | Model name used in API calls.<br />Example: `"my-custom-gpt-4o"` |
| <a id="response.body.base_model_name"></a>`base_model_name` | `string` | Optional | Base model inherited from, when configured.<br />Example: `"gpt-4o"` |
| <a id="response.body.affiliation_category"></a>`affiliation_category` | `string` | Optional | `keywordsai` for built-in models, `custom` for your organization's models.<br />Allowed: `"keywordsai"`, `"custom"`<br />Example: `"custom"` |
| <a id="response.body.is_called_by_custom_name"></a>`is_called_by_custom_name` | `boolean` | Optional | Whether requests are sent upstream using this custom model name.<br />Example: `false` |
| <a id="response.body.input_cost"></a>`input_cost` | `number` | Optional | Input list price per 1M tokens in USD. Same as `pricing.current.input.list_price`.<br />Deprecated<br />Example: `2.5` |
| <a id="response.body.output_cost"></a>`output_cost` | `number` | Optional | Output list price per 1M tokens in USD. Same as `pricing.current.output.list_price`.<br />Deprecated<br />Example: `10` |
| <a id="response.body.cache_hit_input_cost"></a>`cache_hit_input_cost` | `number` | Optional | Cached input list price per 1M tokens in USD. Same as `pricing.current.cache_read.list_price`.<br />Deprecated<br />Example: `0.5` |
| <a id="response.body.cache_creation_input_cost"></a>`cache_creation_input_cost` | `number` | Optional | Cache creation input list price per 1M tokens in USD. Same as `pricing.current.cache_creation.list_price`.<br />Deprecated<br />Example: `3` |
| <a id="response.body.max_context_window"></a>`max_context_window` | `integer` | Optional | Maximum context window size.<br />Example: `128000` |
| <a id="response.body.function_call"></a>`function_call` | `integer` | Optional | Function/tool calling support. `0` = no, `1` = yes.<br />Allowed: `0`, `1`<br />Example: `1` |
| <a id="response.body.image_support"></a>`image_support` | `integer` | Optional | Vision input support. `0` = no, `1` = yes.<br />Allowed: `0`, `1`<br />Example: `1` |
| <a id="response.body.model_type"></a>`model_type` | `string` | Optional | Model type.<br />Allowed: `"chat"`, `"embedding"`, `"audio"`<br />Example: `"chat"` |
| <a id="response.body.supported_params"></a>`supported_params` | `object` | Optional | Computed parameter support after applying model-specific overrides.<br />Additional properties are allowed |
| <a id="response.body.provider"></a>`provider` | `object` | Optional | Additional properties are allowed |
| `provider.id` | `string` | Required in parent | Provider string ID. Same value as `provider_id`.<br />Example: `"my-vllm"` |
| `provider.provider_id` | `string` | Required in parent | Unique provider identifier within your organization.<br />Example: `"my-vllm"` |
| `provider.provider_name` | `string` | Required in parent | Human-readable provider name.<br />Example: `"My vLLM Server"` |
| `provider.extra_kwargs` | `object` | Optional | Provider configuration such as `base_url` and timeout values. Secret values are not returned here.<br />Additional properties are allowed<br />Example: `{"base_url":"https://vllm.example.com/v1"}` |
| `provider.created_at` | `string or null` | Optional | Format: `date-time` |
| `provider.updated_at` | `string or null` | Optional | Format: `date-time` |
| `pricing` | `object` | Optional | The model's prices as the gateway bills them. Read prices from here rather than from the cost fields. |
| `pricing (allOf 1)` | `object` | Schema variant | The model's prices, resolved from `unit_prices`.<br />Reference: `#/components/schemas/ModelDetailPricing` |
| `pricing (allOf 1).current` | `object` | Required in parent | What a plain request to the model pays at the time of the request. A dimension the model does not price, or whose price is hidden, is `null`.<br />Reference: `#/components/schemas/CurrentPricing` |
| `pricing (allOf 1).current.input` | `object or null` | Required in parent | Text input, else the first media input priced. |
| `pricing (allOf 1).current.input (allOf 1)` | `object` | Schema variant | One priced dimension of `pricing.current`.<br />Reference: `#/components/schemas/PriceSide` |
| `pricing (allOf 1).current.input (allOf 1).price` | `number` | Required in parent | What a request pays: after the Respan discount, at the time-of-day schedule multiplier in effect at the time of the request.<br />Example: `2.5` |
| `pricing (allOf 1).current.input (allOf 1).list_price` | `number` | Required in parent | The same price before the discount.<br />Example: `2.5` |
| `pricing (allOf 1).current.input (allOf 1).unit` | `string` | Required in parent | What a price is quoted per: `token` is 1M tokens, `character` is 1M characters, the others are one image, second, minute or hour.<br />Reference: `#/components/schemas/PriceUnit`<br />Allowed: `"token"`, `"image"`, `"second"`, `"minute"`, `"hour"`, `"character"`, `"request"`, `"megapixel_second"` |
| `pricing (allOf 1).current.output` | `object or null` | Required in parent | Text output, else the first media output priced. |
| `pricing (allOf 1).current.output (allOf 1)` | `object` | Schema variant | One priced dimension of `pricing.current`.<br />Reference: `#/components/schemas/PriceSide` |
| `pricing (allOf 1).current.output (allOf 1).price` | `number` | Required in parent | What a request pays: after the Respan discount, at the time-of-day schedule multiplier in effect at the time of the request.<br />Example: `2.5` |
| `pricing (allOf 1).current.output (allOf 1).list_price` | `number` | Required in parent | The same price before the discount.<br />Example: `2.5` |
| `pricing (allOf 1).current.output (allOf 1).unit` | `string` | Required in parent | What a price is quoted per: `token` is 1M tokens, `character` is 1M characters, the others are one image, second, minute or hour.<br />Reference: `#/components/schemas/PriceUnit`<br />Allowed: `"token"`, `"image"`, `"second"`, `"minute"`, `"hour"`, `"character"`, `"request"`, `"megapixel_second"` |
| `pricing (allOf 1).current.cache_read` | `object or null` | Required in parent | Cached input read. |
| `pricing (allOf 1).current.cache_read (allOf 1)` | `object` | Schema variant | One priced dimension of `pricing.current`.<br />Reference: `#/components/schemas/PriceSide` |
| `pricing (allOf 1).current.cache_read (allOf 1).price` | `number` | Required in parent | What a request pays: after the Respan discount, at the time-of-day schedule multiplier in effect at the time of the request.<br />Example: `2.5` |
| `pricing (allOf 1).current.cache_read (allOf 1).list_price` | `number` | Required in parent | The same price before the discount.<br />Example: `2.5` |
| `pricing (allOf 1).current.cache_read (allOf 1).unit` | `string` | Required in parent | What a price is quoted per: `token` is 1M tokens, `character` is 1M characters, the others are one image, second, minute or hour.<br />Reference: `#/components/schemas/PriceUnit`<br />Allowed: `"token"`, `"image"`, `"second"`, `"minute"`, `"hour"`, `"character"`, `"request"`, `"megapixel_second"` |
| `pricing (allOf 1).current.cache_creation` | `object or null` | Required in parent | Cache write. |
| `pricing (allOf 1).current.cache_creation (allOf 1)` | `object` | Schema variant | One priced dimension of `pricing.current`.<br />Reference: `#/components/schemas/PriceSide` |
| `pricing (allOf 1).current.cache_creation (allOf 1).price` | `number` | Required in parent | What a request pays: after the Respan discount, at the time-of-day schedule multiplier in effect at the time of the request.<br />Example: `2.5` |
| `pricing (allOf 1).current.cache_creation (allOf 1).list_price` | `number` | Required in parent | The same price before the discount.<br />Example: `2.5` |
| `pricing (allOf 1).current.cache_creation (allOf 1).unit` | `string` | Required in parent | What a price is quoted per: `token` is 1M tokens, `character` is 1M characters, the others are one image, second, minute or hour.<br />Reference: `#/components/schemas/PriceUnit`<br />Allowed: `"token"`, `"image"`, `"second"`, `"minute"`, `"hour"`, `"character"`, `"request"`, `"megapixel_second"` |
| `pricing (allOf 1).current.schedule_multiplier` | `number or null` | Required in parent | The time-of-day multiplier in the prices; `null` without a schedule. |
| `pricing (allOf 1).current.valid_until` | `string or null` | Required in parent | When the schedule next changes the prices; `null` without one.<br />Format: `date-time` |
| `pricing (allOf 1).sheet` | `object` | Required in parent | Every rate the model states: one block per long-prompt tier and schedule level.<br />Reference: `#/components/schemas/PriceSheet` |
| `pricing (allOf 1).sheet.blocks` | `array<object>` | Required in parent | — |
| `pricing (allOf 1).sheet.blocks[]` | `object` | Array item | Reference: `#/components/schemas/PriceSheetBlock` |
| `pricing (allOf 1).sheet.blocks[].prompt_tokens_above` | `integer or null` | Required in parent | The long-prompt tier the block prices; `null` for the base. |
| `pricing (allOf 1).sheet.blocks[].schedule_multiplier` | `number or null` | Required in parent | The schedule level the block prices; `null` without a schedule. |
| `pricing (allOf 1).sheet.blocks[].windows` | `array<object> or null` | Required in parent | This week's hours the level applies; `null` for all other times. |
| `pricing (allOf 1).sheet.blocks[].windows[]` | `object` | Array item | One occurrence this week of a schedule window.<br />Reference: `#/components/schemas/PriceSheetWindow` |
| `pricing (allOf 1).sheet.blocks[].windows[].start` | `string` | Required in parent | Format: `date-time` |
| `pricing (allOf 1).sheet.blocks[].windows[].end` | `string` | Required in parent | Format: `date-time` |
| `pricing (allOf 1).sheet.blocks[].lines` | `array<object>` | Required in parent | — |
| `pricing (allOf 1).sheet.blocks[].lines[]` | `object` | Array item | Reference: `#/components/schemas/PriceSheetLine` |
| `pricing (allOf 1).sheet.blocks[].lines[].dimension` | `string` | Required in parent | What is priced, such as `input`, `output`, `cache_read` or `cache_creation`.<br />Example: `"input"` |
| `pricing (allOf 1).sheet.blocks[].lines[].price` | `number` | Required in parent | After the Respan discount.<br />Example: `2.5` |
| `pricing (allOf 1).sheet.blocks[].lines[].list_price` | `number` | Required in parent | Before the Respan discount.<br />Example: `2.5` |
| `pricing (allOf 1).sheet.blocks[].lines[].unit` | `string` | Required in parent | What the price is quoted per, such as `token`, `image`, `second` or `request`.<br />Example: `"token"` |
| `pricing (allOf 1).sheet.blocks[].lines[].conditions` | `array<object>` | Required in parent | Conditions under which this price applies. Empty for the base price. |
| `pricing (allOf 1).sheet.blocks[].lines[].conditions[]` | `object` | Array item | A condition a price depends on, such as a long prompt, a service tier or a resolution.<br />Reference: `#/components/schemas/PriceCondition` |
| `pricing (allOf 1).sheet.blocks[].lines[].conditions[].key` | `string` | Required in parent | Example: `"cache_ttl"` |
| `pricing (allOf 1).sheet.blocks[].lines[].conditions[].value` | `any` | Required in parent | The value of the condition.<br />Example: `"1h"` |
| `pricing (allOf 1).sheet.multipliers` | `array<object>` | Required in parent | Multipliers on every price when the conditions hold. |
| `pricing (allOf 1).sheet.multipliers[]` | `object` | Array item | — |
| `pricing (allOf 1).sheet.multipliers[].conditions` | `array<object>` | Required in parent | — |
| `pricing (allOf 1).sheet.multipliers[].conditions[]` | `object` | Array item | A condition a price depends on, such as a long prompt, a service tier or a resolution.<br />Reference: `#/components/schemas/PriceCondition` |
| `pricing (allOf 1).sheet.multipliers[].conditions[].key` | `string` | Required in parent | Example: `"cache_ttl"` |
| `pricing (allOf 1).sheet.multipliers[].conditions[].value` | `any` | Required in parent | The value of the condition.<br />Example: `"1h"` |
| `pricing (allOf 1).sheet.multipliers[].multiplier` | `number` | Required in parent | — |
| `unit_prices` | `object` | Optional | The stored price entries, multipliers and schedule that `pricing` is resolved from. Read-only: set prices with the cost fields on the request.<br />Additional properties are allowed<br />Example: `{"entries":[{"dimension":"input","unit":"token","price":2.5},{"dimension":"output","unit":"token","price":10}]}` |


<details class="api-schema-source">
<summary>OpenAPI response schema</summary>


```json
{
  "type": "object",
  "required": [
    "id",
    "model_name"
  ],
  "properties": {
    "id": {
      "type": "string",
      "description": "Model string ID. Same value as `model_name`.",
      "example": "my-custom-gpt-4o"
    },
    "model_name": {
      "type": "string",
      "description": "Model name used in API calls.",
      "example": "my-custom-gpt-4o"
    },
    "base_model_name": {
      "type": "string",
      "description": "Base model inherited from, when configured.",
      "example": "gpt-4o"
    },
    "affiliation_category": {
      "type": "string",
      "description": "`keywordsai` for built-in models, `custom` for your organization's models.",
      "enum": [
        "keywordsai",
        "custom"
      ],
      "example": "custom"
    },
    "is_called_by_custom_name": {
      "type": "boolean",
      "description": "Whether requests are sent upstream using this custom model name.",
      "example": false
    },
    "input_cost": {
      "type": "number",
      "description": "Input list price per 1M tokens in USD. Same as `pricing.current.input.list_price`.",
      "example": 2.5,
      "deprecated": true
    },
    "output_cost": {
      "type": "number",
      "description": "Output list price per 1M tokens in USD. Same as `pricing.current.output.list_price`.",
      "example": 10,
      "deprecated": true
    },
    "cache_hit_input_cost": {
      "type": "number",
      "description": "Cached input list price per 1M tokens in USD. Same as `pricing.current.cache_read.list_price`.",
      "example": 0.5,
      "deprecated": true
    },
    "cache_creation_input_cost": {
      "type": "number",
      "description": "Cache creation input list price per 1M tokens in USD. Same as `pricing.current.cache_creation.list_price`.",
      "example": 3,
      "deprecated": true
    },
    "max_context_window": {
      "type": "integer",
      "description": "Maximum context window size.",
      "example": 128000
    },
    "function_call": {
      "type": "integer",
      "enum": [
        0,
        1
      ],
      "description": "Function/tool calling support. `0` = no, `1` = yes.",
      "example": 1
    },
    "image_support": {
      "type": "integer",
      "enum": [
        0,
        1
      ],
      "description": "Vision input support. `0` = no, `1` = yes.",
      "example": 1
    },
    "model_type": {
      "type": "string",
      "description": "Model type.",
      "enum": [
        "chat",
        "embedding",
        "audio"
      ],
      "example": "chat"
    },
    "supported_params": {
      "type": "object",
      "description": "Computed parameter support after applying model-specific overrides.",
      "additionalProperties": true
    },
    "provider": {
      "type": "object",
      "required": [
        "id",
        "provider_id",
        "provider_name"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "Provider string ID. Same value as `provider_id`.",
          "example": "my-vllm"
        },
        "provider_id": {
          "type": "string",
          "description": "Unique provider identifier within your organization.",
          "example": "my-vllm"
        },
        "provider_name": {
          "type": "string",
          "description": "Human-readable provider name.",
          "example": "My vLLM Server"
        },
        "extra_kwargs": {
          "type": "object",
          "description": "Provider configuration such as `base_url` and timeout values. Secret values are not returned here.",
          "additionalProperties": true,
          "example": {
            "base_url": "https://vllm.example.com/v1"
          }
        },
        "created_at": {
          "type": "string",
          "format": "date-time",
          "nullable": true
        },
        "updated_at": {
          "type": "string",
          "format": "date-time",
          "nullable": true
        }
      },
      "additionalProperties": true
    },
    "pricing": {
      "allOf": [
        {
          "$ref": "#/components/schemas/ModelDetailPricing"
        }
      ],
      "description": "The model's prices as the gateway bills them. Read prices from here rather than from the cost fields."
    },
    "unit_prices": {
      "type": "object",
      "additionalProperties": true,
      "description": "The stored price entries, multipliers and schedule that `pricing` is resolved from. Read-only: set prices with the cost fields on the request.",
      "example": {
        "entries": [
          {
            "dimension": "input",
            "unit": "token",
            "price": 2.5
          },
          {
            "dimension": "output",
            "unit": "token",
            "price": 10
          }
        ]
      }
    }
  },
  "additionalProperties": true
}
```

</details>

<a id="response.error"></a>

### 400

Bad Request

#### application/json


| Field | Type | Requirement | Description and constraints |
| --- | --- | --- | --- |
| `$` | `object` | Body | — |
| `detail` | `string` | Optional | — |
| `error` | `string` | Optional | — |


<details class="api-schema-source">
<summary>OpenAPI response schema</summary>


```json
{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string"
    },
    "error": {
      "type": "string"
    }
  }
}
```

</details>

##### Example


```json
{
  "error": "Invalid request"
}
```


### 403

The API key is missing, invalid or expired, or it doesn't have permission for this action.

#### application/json


| Field | Type | Requirement | Description and constraints |
| --- | --- | --- | --- |
| `$` | `object` | Body | — |
| `detail` | `string` | Required in parent | — |


<details class="api-schema-source">
<summary>OpenAPI response schema</summary>


```json
{
  "type": "object",
  "required": [
    "detail"
  ],
  "properties": {
    "detail": {
      "type": "string"
    }
  }
}
```

</details>

##### Example


```json
{
  "detail": "Your API key is invalid or expired, please check your API key in the platform settings."
}
```


### 404

Not Found

#### application/json


| Field | Type | Requirement | Description and constraints |
| --- | --- | --- | --- |
| `$` | `object` | Body | — |
| `detail` | `string` | Optional | — |
| `error` | `string` | Optional | — |


<details class="api-schema-source">
<summary>OpenAPI response schema</summary>


```json
{
  "type": "object",
  "properties": {
    "detail": {
      "type": "string"
    },
    "error": {
      "type": "string"
    }
  }
}
```

</details>

##### Example


```json
{
  "error": "Not found"
}
```


## OpenAPI source

The operation and referenced components below retain the complete OpenAPI definitions, including constraints and examples.

<!-- openapi-operation:start -->
<details class="api-schema-source">
<summary>OpenAPI operation</summary>


```json
{
  "summary": "Replace a custom model",
  "operationId": "replaceCustomModel",
  "tags": [
    "Models"
  ],
  "description": "Replace editable fields for a custom model. The `model_name` path value remains the identifier.",
  "parameters": [
    {
      "name": "model_name",
      "in": "path",
      "required": true,
      "schema": {
        "type": "string"
      },
      "description": "Model name. The route supports names containing slashes, such as `openai/gpt-4o-mini`."
    }
  ],
  "requestBody": {
    "required": true,
    "content": {
      "application/json": {
        "schema": {
          "type": "object",
          "properties": {
            "base_model_name": {
              "type": "string",
              "description": "Base model to inherit properties from.",
              "example": "gpt-4o"
            },
            "custom_provider_id": {
              "type": "string",
              "description": "Custom provider string ID or provider identifier to associate.",
              "example": "my-vllm"
            },
            "provider_id": {
              "type": "string",
              "description": "Alternative to `custom_provider_id`.",
              "example": "my-vllm"
            },
            "input_cost": {
              "type": "number",
              "description": "Cost per 1M input tokens in USD.",
              "example": 2.5
            },
            "output_cost": {
              "type": "number",
              "description": "Cost per 1M output tokens in USD.",
              "example": 10
            },
            "cache_hit_input_cost": {
              "type": "number",
              "description": "Cost per 1M cached input tokens in USD."
            },
            "cache_creation_input_cost": {
              "type": "number",
              "description": "Cost per 1M cache creation input tokens in USD."
            },
            "max_context_window": {
              "type": "integer",
              "description": "Maximum context window size.",
              "example": 128000
            },
            "function_call": {
              "type": "integer",
              "enum": [
                0,
                1
              ]
            },
            "image_support": {
              "type": "integer",
              "enum": [
                0,
                1
              ]
            },
            "supported_params_override": {
              "type": "object",
              "description": "Partial override for the model's parameters: a map of parameter name to a parameter definition with the same shape as `supported_params` entries (`name`, `type`, `default`, `range` with `min` and `max`, `description`, `required`), or `null` to remove the parameter. Replaces any earlier override. The response returns the computed `supported_params`.",
              "additionalProperties": true
            }
          }
        }
      }
    }
  },
  "responses": {
    "200": {
      "description": "Updated model.",
      "content": {
        "application/json": {
          "schema": {
            "type": "object",
            "required": [
              "id",
              "model_name"
            ],
            "properties": {
              "id": {
                "type": "string",
                "description": "Model string ID. Same value as `model_name`.",
                "example": "my-custom-gpt-4o"
              },
              "model_name": {
                "type": "string",
                "description": "Model name used in API calls.",
                "example": "my-custom-gpt-4o"
              },
              "base_model_name": {
                "type": "string",
                "description": "Base model inherited from, when configured.",
                "example": "gpt-4o"
              },
              "affiliation_category": {
                "type": "string",
                "description": "`keywordsai` for built-in models, `custom` for your organization's models.",
                "enum": [
                  "keywordsai",
                  "custom"
                ],
                "example": "custom"
              },
              "is_called_by_custom_name": {
                "type": "boolean",
                "description": "Whether requests are sent upstream using this custom model name.",
                "example": false
              },
              "input_cost": {
                "type": "number",
                "description": "Input list price per 1M tokens in USD. Same as `pricing.current.input.list_price`.",
                "example": 2.5,
                "deprecated": true
              },
              "output_cost": {
                "type": "number",
                "description": "Output list price per 1M tokens in USD. Same as `pricing.current.output.list_price`.",
                "example": 10,
                "deprecated": true
              },
              "cache_hit_input_cost": {
                "type": "number",
                "description": "Cached input list price per 1M tokens in USD. Same as `pricing.current.cache_read.list_price`.",
                "example": 0.5,
                "deprecated": true
              },
              "cache_creation_input_cost": {
                "type": "number",
                "description": "Cache creation input list price per 1M tokens in USD. Same as `pricing.current.cache_creation.list_price`.",
                "example": 3,
                "deprecated": true
              },
              "max_context_window": {
                "type": "integer",
                "description": "Maximum context window size.",
                "example": 128000
              },
              "function_call": {
                "type": "integer",
                "enum": [
                  0,
                  1
                ],
                "description": "Function/tool calling support. `0` = no, `1` = yes.",
                "example": 1
              },
              "image_support": {
                "type": "integer",
                "enum": [
                  0,
                  1
                ],
                "description": "Vision input support. `0` = no, `1` = yes.",
                "example": 1
              },
              "model_type": {
                "type": "string",
                "description": "Model type.",
                "enum": [
                  "chat",
                  "embedding",
                  "audio"
                ],
                "example": "chat"
              },
              "supported_params": {
                "type": "object",
                "description": "Computed parameter support after applying model-specific overrides.",
                "additionalProperties": true
              },
              "provider": {
                "type": "object",
                "required": [
                  "id",
                  "provider_id",
                  "provider_name"
                ],
                "properties": {
                  "id": {
                    "type": "string",
                    "description": "Provider string ID. Same value as `provider_id`.",
                    "example": "my-vllm"
                  },
                  "provider_id": {
                    "type": "string",
                    "description": "Unique provider identifier within your organization.",
                    "example": "my-vllm"
                  },
                  "provider_name": {
                    "type": "string",
                    "description": "Human-readable provider name.",
                    "example": "My vLLM Server"
                  },
                  "extra_kwargs": {
                    "type": "object",
                    "description": "Provider configuration such as `base_url` and timeout values. Secret values are not returned here.",
                    "additionalProperties": true,
                    "example": {
                      "base_url": "https://vllm.example.com/v1"
                    }
                  },
                  "created_at": {
                    "type": "string",
                    "format": "date-time",
                    "nullable": true
                  },
                  "updated_at": {
                    "type": "string",
                    "format": "date-time",
                    "nullable": true
                  }
                },
                "additionalProperties": true
              },
              "pricing": {
                "allOf": [
                  {
                    "$ref": "#/components/schemas/ModelDetailPricing"
                  }
                ],
                "description": "The model's prices as the gateway bills them. Read prices from here rather than from the cost fields."
              },
              "unit_prices": {
                "type": "object",
                "additionalProperties": true,
                "description": "The stored price entries, multipliers and schedule that `pricing` is resolved from. Read-only: set prices with the cost fields on the request.",
                "example": {
                  "entries": [
                    {
                      "dimension": "input",
                      "unit": "token",
                      "price": 2.5
                    },
                    {
                      "dimension": "output",
                      "unit": "token",
                      "price": 10
                    }
                  ]
                }
              }
            },
            "additionalProperties": true
          }
        }
      }
    },
    "400": {
      "description": "Bad Request",
      "content": {
        "application/json": {
          "schema": {
            "type": "object",
            "properties": {
              "detail": {
                "type": "string"
              },
              "error": {
                "type": "string"
              }
            }
          },
          "example": {
            "error": "Invalid request"
          }
        }
      }
    },
    "403": {
      "description": "The API key is missing, invalid or expired, or it doesn't have permission for this action.",
      "content": {
        "application/json": {
          "schema": {
            "type": "object",
            "required": [
              "detail"
            ],
            "properties": {
              "detail": {
                "type": "string"
              }
            }
          },
          "example": {
            "detail": "Your API key is invalid or expired, please check your API key in the platform settings."
          }
        }
      }
    },
    "404": {
      "description": "Not Found",
      "content": {
        "application/json": {
          "schema": {
            "type": "object",
            "properties": {
              "detail": {
                "type": "string"
              },
              "error": {
                "type": "string"
              }
            }
          },
          "example": {
            "error": "Not found"
          }
        }
      }
    }
  },
  "security": [
    {
      "RespanApiKey": []
    },
    {
      "DashboardJwt": []
    }
  ]
}
```

</details>
<!-- openapi-operation:end -->

<!-- openapi-path-item:start -->
<details class="api-schema-source">
<summary>OpenAPI path metadata</summary>


```json
{}
```

</details>
<!-- openapi-path-item:end -->

<!-- openapi-components:start -->
<details class="api-schema-source">
<summary>Referenced OpenAPI components</summary>


```json
{
  "schemas": {
    "CurrentPricing": {
      "type": "object",
      "description": "What a plain request to the model pays at the time of the request. A dimension the model does not price, or whose price is hidden, is `null`.",
      "required": [
        "input",
        "output",
        "cache_read",
        "cache_creation",
        "schedule_multiplier",
        "valid_until"
      ],
      "properties": {
        "input": {
          "allOf": [
            {
              "$ref": "#/components/schemas/PriceSide"
            }
          ],
          "nullable": true,
          "description": "Text input, else the first media input priced."
        },
        "output": {
          "allOf": [
            {
              "$ref": "#/components/schemas/PriceSide"
            }
          ],
          "nullable": true,
          "description": "Text output, else the first media output priced."
        },
        "cache_read": {
          "allOf": [
            {
              "$ref": "#/components/schemas/PriceSide"
            }
          ],
          "nullable": true,
          "description": "Cached input read."
        },
        "cache_creation": {
          "allOf": [
            {
              "$ref": "#/components/schemas/PriceSide"
            }
          ],
          "nullable": true,
          "description": "Cache write."
        },
        "schedule_multiplier": {
          "type": "number",
          "nullable": true,
          "description": "The time-of-day multiplier in the prices; `null` without a schedule."
        },
        "valid_until": {
          "type": "string",
          "format": "date-time",
          "nullable": true,
          "description": "When the schedule next changes the prices; `null` without one."
        }
      }
    },
    "ModelDetailPricing": {
      "type": "object",
      "description": "The model's prices, resolved from `unit_prices`.",
      "required": [
        "current",
        "sheet"
      ],
      "properties": {
        "current": {
          "$ref": "#/components/schemas/CurrentPricing"
        },
        "sheet": {
          "$ref": "#/components/schemas/PriceSheet"
        }
      }
    },
    "PriceCondition": {
      "type": "object",
      "description": "A condition a price depends on, such as a long prompt, a service tier or a resolution.",
      "required": [
        "key",
        "value"
      ],
      "properties": {
        "key": {
          "type": "string",
          "example": "cache_ttl"
        },
        "value": {
          "description": "The value of the condition.",
          "example": "1h"
        }
      }
    },
    "PriceSheet": {
      "type": "object",
      "description": "Every rate the model states: one block per long-prompt tier and schedule level.",
      "required": [
        "blocks",
        "multipliers"
      ],
      "properties": {
        "blocks": {
          "type": "array",
          "items": {
            "$ref": "#/components/schemas/PriceSheetBlock"
          }
        },
        "multipliers": {
          "type": "array",
          "description": "Multipliers on every price when the conditions hold.",
          "items": {
            "type": "object",
            "required": [
              "conditions",
              "multiplier"
            ],
            "properties": {
              "conditions": {
                "type": "array",
                "items": {
                  "$ref": "#/components/schemas/PriceCondition"
                }
              },
              "multiplier": {
                "type": "number"
              }
            }
          }
        }
      }
    },
    "PriceSheetBlock": {
      "type": "object",
      "required": [
        "prompt_tokens_above",
        "schedule_multiplier",
        "windows",
        "lines"
      ],
      "properties": {
        "prompt_tokens_above": {
          "type": "integer",
          "nullable": true,
          "description": "The long-prompt tier the block prices; `null` for the base."
        },
        "schedule_multiplier": {
          "type": "number",
          "nullable": true,
          "description": "The schedule level the block prices; `null` without a schedule."
        },
        "windows": {
          "type": "array",
          "nullable": true,
          "items": {
            "$ref": "#/components/schemas/PriceSheetWindow"
          },
          "description": "This week's hours the level applies; `null` for all other times."
        },
        "lines": {
          "type": "array",
          "items": {
            "$ref": "#/components/schemas/PriceSheetLine"
          }
        }
      }
    },
    "PriceSheetLine": {
      "type": "object",
      "required": [
        "dimension",
        "price",
        "list_price",
        "unit",
        "conditions"
      ],
      "properties": {
        "dimension": {
          "type": "string",
          "description": "What is priced, such as `input`, `output`, `cache_read` or `cache_creation`.",
          "example": "input"
        },
        "price": {
          "type": "number",
          "description": "After the Respan discount.",
          "example": 2.5
        },
        "list_price": {
          "type": "number",
          "description": "Before the Respan discount.",
          "example": 2.5
        },
        "unit": {
          "type": "string",
          "description": "What the price is quoted per, such as `token`, `image`, `second` or `request`.",
          "example": "token"
        },
        "conditions": {
          "type": "array",
          "items": {
            "$ref": "#/components/schemas/PriceCondition"
          },
          "description": "Conditions under which this price applies. Empty for the base price."
        }
      }
    },
    "PriceSheetWindow": {
      "type": "object",
      "description": "One occurrence this week of a schedule window.",
      "required": [
        "start",
        "end"
      ],
      "properties": {
        "start": {
          "type": "string",
          "format": "date-time"
        },
        "end": {
          "type": "string",
          "format": "date-time"
        }
      }
    },
    "PriceSide": {
      "type": "object",
      "description": "One priced dimension of `pricing.current`.",
      "required": [
        "price",
        "list_price",
        "unit"
      ],
      "properties": {
        "price": {
          "type": "number",
          "description": "What a request pays: after the Respan discount, at the time-of-day schedule multiplier in effect at the time of the request.",
          "example": 2.5
        },
        "list_price": {
          "type": "number",
          "description": "The same price before the discount.",
          "example": 2.5
        },
        "unit": {
          "$ref": "#/components/schemas/PriceUnit"
        }
      }
    },
    "PriceUnit": {
      "type": "string",
      "enum": [
        "token",
        "image",
        "second",
        "minute",
        "hour",
        "character",
        "request",
        "megapixel_second"
      ],
      "description": "What a price is quoted per: `token` is 1M tokens, `character` is 1M characters, the others are one image, second, minute or hour."
    }
  },
  "securitySchemes": {
    "DashboardJwt": {
      "type": "http",
      "scheme": "bearer",
      "bearerFormat": "Dashboard JWT",
      "description": "Use a dashboard JWT only for dashboard-authenticated endpoints. Respan API-key endpoints use the respanApiKey auth field instead.",
      "x-fern-bearer": {
        "name": "dashboardJwt",
        "env": "RESPAN_DASHBOARD_JWT"
      }
    },
    "RespanApiKey": {
      "type": "http",
      "scheme": "bearer",
      "bearerFormat": "Respan API key",
      "description": "Use your Respan API key for Respan API authentication. Enter only the Respan API key value; clients send Authorization: Bearer <RESPAN_API_KEY>. For /api/responses, provider credentials such as Perplexity, OpenAI, or Azure OpenAI go in Settings -> Providers or respan_params.credential_override in the request body, not in this authentication field.",
      "x-fern-bearer": {
        "name": "respanApiKey",
        "env": "RESPAN_API_KEY"
      }
    }
  }
}
```

</details>
<!-- openapi-components:end -->