Models List API

Retrieves a list of all available AI models.

Get model by id

Retrieves a single model by its id. Returns a single model object.

GET /v3/models/:modelId

https://api.imagerouter.io/v3/models/openai%2Fgpt-image-2

Path parameters

Parameter	Type	Description
`modelId`	string	The ID of the model.

Example response

{
  "id": "openai/gpt-image-2",
  "architecture": {
    "input_modalities": ["image"],
    "output_modalities": ["image"]
  },
  "created": 1776729600,
  "pricing": {
    "min": 0.0062,
    "average": 0.0414, // usual cost for a 1024x1024 medium quality image
    "max": 0.2,
  },
  "supported_parameters": ["quality", "size"],
  "parameters": {
    "size": ["auto", "1024x1024", "1536x1024", "1024x1536", "2560x1440", "3840x2160"]
  }
}

Get All Models

GET /v3/models

https://api.imagerouter.io/v3/models

Returns an array of model objects. Each object includes an id field identifying the model.

This endpoint supports filtering, sorting, limits, and field selection to help you find exactly the models and metadata you need.

Query Parameters

Parameter	Type	Description
`output_modalities`	string	Filter by output modality: `image`, `video`, or `text`
`input_modalities`	string	Filter by supported input modality: `image`, `mask`, `text`, `audio`, or `video`
`provider`	string	Filter by provider name (partial, case-insensitive), e.g. `google`, `openai`
`free`	string	`true` to show only free models, `false` to show only paid models
`name`	string	Filter by model name or alias (partial, case-insensitive)
`sort`	string	Sort by: `name`, `provider`, `price`, or `date`
`limit`	number	Maximum number of models to return
`fields`	string	Comma-separated list of fields to include in the response (see below)

Available Fields

When fields is omitted, all fields are returned. When specified, only the listed fields appear in each model object. The id field is always included.

Field	Type	Description
`id`	string	The model identifier, e.g. `"openai/gpt-image-2"`
`architecture`	object	Input and output modalities (see below)
`created`	number	Release date as a Unix timestamp in seconds (may be absent)
`pricing`	object	Pricing info (see below)
`supported_parameters`	string[]	Names of the generation parameters the model accepts, e.g. `["quality", "size"]`
`parameters`	object	Allowed values for value-based parameters such as `size` and `seconds` (only present when applicable)
`context_length`	number	Maximum context window in tokens (text models only)
`aliases`	string[]	Alternative names for this model (only present if aliases exist)

architecture object fields:

Field	Type	Description
`input_modalities`	string[]	Accepted input modalities, e.g. `["image"]`, `["text"]`, or `[]`
`output_modalities`	string[]	Produced output modalities, e.g. `["image"]`, `["video"]`, or `["text"]`

supported_parameters values:

Value	Description
`quality`	Model supports quality settings
`size`	Model supports output size selection (allowed values in `parameters.size`)
`seconds`	Model supports output duration selection (allowed values in `parameters.seconds`)
`mask`	Model supports a mask for inpainting

Text (LLM) models additionally report OpenAI-style parameters such as temperature, max_tokens, top_p, tools, and tool_choice.

parameters object fields:

Field	Type	Description
`size`	string[]	Supported sizes, e.g. `["1024x1024", "auto"]` or `["custom"]`
`seconds`	(number\|string)[]	Supported durations for video models, e.g. `[4, 6, 8]` or `["auto"]`

pricing object:

For image and video models, pricing contains aggregate per-generation pricing in USD:

Field	Type	Description
`min`	number	Lowest price across configured providers (USD)
`average`	number	Representative/average price (USD)
`max`	number	Highest price across configured providers (USD)

For text (LLM) models, pricing is the upstream per-token pricing object (values are USD per token / per request), for example:

{
  "prompt": "0.15e-6",
  "completion": "0.6e-6",
  "image": "0",
  "request": "0",
  "input_cache_read": "0.075e-6",
  "input_cache_write": "0",
  "web_search": "0",
  "internal_reasoning": "0"
}

Example responses

Image model:

{
  "id": "openai/gpt-image-2",
  "architecture": {
    "input_modalities": ["image"],
    "output_modalities": ["image"]
  },
  "created": 1776729600,
  "pricing": { "min": 0.0062, "average": 0.0414, "max": 0.2 },
  "supported_parameters": ["quality", "size"],
  "parameters": {
    "size": ["auto", "1024x1024", "1536x1024", "1024x1536", "2560x1440", "3840x2160"]
  }
}

Video model:

{
  "id": "google/veo-2",
  "architecture": {
    "input_modalities": ["image"],
    "output_modalities": ["video"]
  },
  "created": 1734307200,
  "pricing": { "min": 1.875, "average": 1.875, "max": 1.875 },
  "supported_parameters": ["size", "seconds"],
  "parameters": {
    "size": ["1280x720", "720x1280", "1920x1080", "1080x1920"],
    "seconds": [5]
  }
}

Text (LLM) model:

{
  "id": "openai/gpt-4o-mini",
  "architecture": {
    "input_modalities": ["text"],
    "output_modalities": ["text"]
  },
  "created": 1721260800,
  "pricing": {
    "prompt": "0.15e-6",
    "completion": "0.6e-6",
    "image": "0",
    "request": "0",
    "input_cache_read": "0.075e-6",
    "input_cache_write": "0",
    "web_search": "0",
    "internal_reasoning": "0"
  },
  "supported_parameters": [
    "temperature", "max_tokens", "top_p",
    "frequency_penalty", "presence_penalty",
    "response_format", "tools", "tool_choice"
  ],
  "context_length": 128000
}

Sorting Order

name: Alphabetical (A-Z).
provider: Alphabetical (A-Z).
price: Ascending (lowest price first).
date: Descending (newest first).

Models List API

Get model by id

Path parameters

Example response

Get All Models

Get all model ids:

Get all model ids and aliases:

Search, Filter, and Sort Models

Examples:

Query Parameters

Available Fields

Example responses

Sorting Order