List Models

Returns a list of all available models with metadata.

Returns a list of all available models with their metadata including pricing, context window, and capabilities.

GET /v1/models

Authentication

AuthorizationBearerrequired

API key as bearer token in the Authorization header. Create keys at Manage API Keys.

Response

object'list'optional

Always list.

dataModel[]optional

Array of model objects.

Model object

Each model in the data array has this shape:

Field	Type	Description
`id`	string	Unique model identifier. Use this in API requests.
`name`	string	Human-readable model name.
`object`	`'model'`	Always `model`.
`created`	integer	Unix timestamp when the model was added.
`owned_by`	string	Provider or organization that owns the model.
`architecture`	object	Model capabilities and limits.
`pricing`	object	Cost per million tokens.
`deprecated_at`	string	ISO 8601 date the model stops working. Present only during the 10-day deprecation notice. See Model lifecycle.
`deprecated`	boolean	`true` once the deprecation date has passed. Requests to the model are rejected.
`replaced_by`	string	ID of the recommended replacement model. Present during the notice and after deprecation when one is set.

Architecture object

Field	Type	Description
`input_modalities`	string[]	Supported input types: `text`, `image`, `audio`, `video`.
`output_modalities`	string[]	Supported output types: `text`, `image`, `audio`, `video`.
`context_window`	integer	Maximum context window in tokens.
`max_completion_tokens`	integer	Maximum output tokens.
`image_aspect_ratios`	string[]	Supported aspect ratios for image generation models.
`image_resolutions`	string[]	Supported resolution steps for image generation models.
`image_qualities`	string[]	Supported quality levels for image generation models.
`video_sizes`	string[]	Supported video sizes for video generation models.
`supported_parameters`	string[]	Request parameters the model accepts.

Pricing object

Prices are in USD per 1 million tokens unless noted otherwise. Only the fields that apply to a model are present. Token prices are either a flat number or an array of tiers ({ "up_to": 200000, "price": 3 }, { "above": 200000, "price": 6 }) keyed on the request's token count.

Field	Type	Description
`prompt`	number \| tier[]	Cost per 1M input tokens.
`completion`	number \| tier[]	Cost per 1M output tokens.
`cache_read`	number \| tier[]	Cost per 1M cached read tokens.
`cache_write`	number \| tier[]	Cost per 1M cache write tokens.
`cache_write_1h`	number \| tier[]	Cost per 1M tokens written to a 1-hour cache entry.
`image_input_tokens`	number \| tier[]	Cost per 1M image input tokens.
`image_output_tokens`	number \| tier[]	Cost per 1M image output tokens.
`audio_input_tokens`	number \| tier[]	Cost per 1M audio input tokens.
`audio_input`	number	Cost per second of input audio.
`audio_output`	number	Cost per second of output audio.
`text_input`	number	Cost per 1M input characters.
`video_output`	number \| object	Cost per second of generated video. An object maps a resolution (for example `"720p"`) to its price.
`per_image_input`	number	Cost per input reference image.
`per_image_output`	number \| object	Cost per generated image. An object maps a resolution or quality variant (for example `"1K"`) to its price.
`discount`	number	Fraction taken off the listed prices, from `0` to `1`.
`discount_kind`	`'promo'` \| `'baseline'`	Whether `discount` is a limited-time promotion or a permanent price.
`peak_hours`	object[]	UTC windows (`start_hour` inclusive, `end_hour` exclusive, `0` to `23`) during which `peak_pricing` applies.
`peak_pricing`	object	Rates (`prompt`, `completion`, `cache_read`, `cache_write`) charged inside `peak_hours`.
`peak_exclude_days`	integer[]	Weekdays (`0` = Sunday) on which peak pricing never applies.
`peak_exclude_utc_offset_minutes`	integer	UTC offset of the zone that `peak_exclude_days` refers to.
`peak_active_today`	boolean	Whether the peak schedule applies today (false on an excluded day).
`peak_active_now`	boolean	Whether peak pricing applies at the time of the request.