ModelObject schema

Field Type and description

id
Required

string

Model identifier (its slug or its full ID).

object
Required

string

Allowed values: ["model"]

name

string

The model's display name.

created
Required

integer

Unix timestamp of model creation.

owned_by
Required

string

Model creator or organization.

type

string

Primary model modality/type (e.g. text-generation, embedding, text-to-image).

context_window

integer | null

The maximum context size (input + output tokens) as DEVUP serves the model. An integer, or null when not set.

context_length

string

A short display label for the context size.

max_output_tokens

integer

The model's own output limit, which differs from model to model: the largest value the model accepts for max_tokens and max_completion_tokens on POST /v1/chat/completions, for max_output_tokens on POST /v1/responses, and for max_tokens on POST /anthropic/v1/messages. A larger value returns HTTP 400 invalid_max_tokens (on POST /anthropic/v1/messages, the same message in an invalid_request_error). A request that sends none of these parameters is limited to the model's default output length, which is at most this value. Listed for models that generate text (type text-generation).

is_replaced

boolean

Whether the model has been superseded by a newer version.

pricing

ModelPricing

capabilities

array of string

Supported modality or capability flags (e.g. multimodal, OCR).

Array items

string

supports

object

Feature support flags, present on every model. supports.reasoning: true with no reasoning object means the model's reasoning mode is not known yet.

Field	Type and description
`tools` Required	boolean The model takes `tools` and can return tool calls.
`vision` Required	boolean The model accepts images in messages.
`reasoning` Required	boolean The model reasons, always or when asked.
`structured_output` Required	boolean A `response_format` of type `json_schema` returns JSON that matches the schema.
`audio_input` Required	boolean The model accepts audio in messages.
`video_input` Required	boolean The model accepts video in messages.
`reasoning_can_be_disabled` Required	boolean The model can answer without reasoning.

tool_calls

object

Tool calling details for the model. Each key is present only when known; the object is omitted when no key is known.

Field	Type and description
`chat_completions`	boolean `false`: tool calls for this model are served on `/v1/responses`, and a `POST /v1/chat/completions` request with `tools` returns HTTP 400 `use_responses_api`. `true`: tool calls are served on `/v1/chat/completions`.
`parallel`	boolean `true`: the model can return several tool calls in one reply. `false`: it returns at most one tool call per reply.

{
  "chat_completions": false
}

tool_choice

object

For each tool_choice value whose handling is known: true when the model enforces it, false when the model selects tools on its own (a request with that value is answered with the notice tool_choice_not_enforced). function is a named function. auto is not listed: the model always decides. A value that is not listed is not known yet. Omitted when no value is known.

Field	Type and description
`none`	boolean
`required`	boolean
`function`	boolean

{
  "required": false,
  "function": false
}

reasoning

object

The model's reasoning mode and, when known, the request parameter that controls it with the reasoning levels you can send to the model. Omitted while the mode is not known: supports.reasoning: true with no reasoning object means the mode is not known yet.

Field Type and description

mode
Required

string

always: the model reasons without being asked. on_request: it reasons when asked. none: no configurable reasoning mode; a request with reasoning_effort or reasoning is answered with the notice reasoning_not_available.

Allowed values: ["always","on_request","none"]

parameter

string

The request parameter that turns reasoning on or sets its level, when known (for example reasoning_effort). It can appear with mode always, where it sets the level, and with mode on_request.

values

array of string | number | boolean

The reasoning levels you can send to this model with parameter, from least to most reasoning. none, when listed, turns reasoning off. How much each level changes the reasoning depends on the model. Some models list a single value, which turns reasoning on. For reasoning_effort, the values come from none, minimal, low, medium, high, xhigh and max, in that order.

Array items

string | number | boolean

{
  "mode": "on_request",
  "parameter": "reasoning_effort",
  "values": [
    "low",
    "medium",
    "high"
  ]
}