---
title: "List available models"
method: GET
path: "/v1/models"
---

# List available models

`GET /v1/models`

Get all available models. If authenticated with a Requesty API key, returns only approved models for your organization. Otherwise, returns all public models.

## Response `200`

List of available models

- ModelsResponse
  - `object` 'list', required — The object type, always 'list'
  - `data` Model[], required — The list of available models
    - `id` string — The model identifier (e.g., 'openai/gpt-5-mini')
    - `object` 'model' — The object type, always 'model'
    - `created` integer — The Unix timestamp (in seconds) when the model was created
    - `owned_by` string — The system or organization that owns the model
    - `input_price` number, float — Price per input token in USD
    - `caching_price` number, float — Price per token for caching in USD
    - `cached_price` number, float — Price per cached token in USD
    - `output_price` number, float — Price per output token in USD
    - `max_output_tokens` integer — Maximum number of output tokens the model can generate
    - `context_window` integer — Maximum context window size in tokens
    - `supports_caching` boolean — Whether the model supports caching
    - `supports_vision` boolean — Whether the model supports vision/image inputs
    - `supports_computer_use` boolean — Whether the model supports computer use capabilities
    - `supports_reasoning` boolean — Whether the model supports reasoning capabilities
    - `supports_web_search` boolean — Whether the model supports web search via the `web_search` tool type
    - `supports_json_schema` boolean — Whether the model supports strict structured outputs via `response_format` with `{ "type": "json_schema" }`
    - `description` string — A description of the model's capabilities and use cases
    - `retires_at` string, date-time — When the model is scheduled to be retired, in ISO 8601 format. After this date, requests to the model fail. Null if no retirement is scheduled.

## Other responses

- `400` — Bad request - malformed payload or invalid parameters.
- `401` — Unauthorized - missing or empty Authorization header.
- `402` — Payment required - organization balance exhausted.
- `403` — Forbidden - invalid token or model not in access list.
- `404` — Not found - provider/model not supported.
- `429` — Rate limit exceeded. Retry after the Retry-After header value.
- `500` — Internal server error.
- `502` — Bad gateway - upstream provider returned an invalid response.

---

[API](https://skmtc.dev/requesty/apis/requesty-api.md) · [All operations](https://skmtc.dev/requesty/apis/requesty-api/llms.txt) · [OpenAPI document](https://skmtc-service-production.skmtc.workers.dev/v1/apis/requesty/requesty-api/revisions/63bc7d99ccde/schema)