---
title: "Fetch Detailed Models"
method: GET
path: "/v1/models/detailed"
tags: ["Models"]
---

# Fetch Detailed Models

`GET /v1/models/detailed`

## Request

- Base URL: `https://apipie.ai`
- URL: `https://apipie.ai/v1/models/detailed`
- Auth: API key in header `Authorization`

Fetch detailed information about models

## Query parameters

- `type` string
- `provider` string
- `model` string

## Response `200`

List of detailed models

- ModelDetailedResponse
  - `object` string: Type of the response object, always a list
  - `data` ModelDetailed[]
    - `enabled` boolean, required: Whether the model is enabled
    - `available` boolean, required: Whether the model is currently available
    - `latency` string: Average latency by combined prompt/response size
    - `query_count` integer: Total count of queries for this model
    - `type` string, required: Type of the model
    - `subtype` string: Subtype of the model
    - `provider` string, required: Provider of the model
    - `id` string, required: Unique identifier for the model
    - `model` string, required: The base model name
    - `route` string, required: Provider specific identifier
    - `description` string: Description of the model
    - `input_modalities` string[]: Input modalities supported by the model
    - `output_modalities` string[]: Output modalities supported by the model
    - `pool` string: Pool the model belongs to
    - `instruct_type` string: Instruction type for the model
    - `abortable` boolean: Whether requests to the model can be aborted
    - `moderationRequired` boolean: Whether content moderation is required
    - `supports_multipart` boolean: Whether multipart requests are supported
    - `quantization` string: Quantization level of the model
    - `mmlu` number: MMLU score of the model
    - `max_tokens` integer: Maximum tokens supported by the model
    - `max_response_tokens` integer: Maximum tokens in response
    - `output_vector_size` integer: Size of output vectors from embedding models
    - `max_images_per_prompt` integer: Maximum images per prompt
    - `max_audio_per_prompt` integer: Maximum audio files per prompt
    - `max_audio_length_hours` integer: Maximum audio length in hours
    - `max_pdf_size_mb` integer: Maximum PDF size in MB
    - `max_video_length` integer: Maximum video length
    - `max_videos_per_prompt` integer: Maximum videos per prompt
    - `supported_input_parameters` object: Input parameters supported by the model with detailed specifications
    - `pricing` object
      - `confirmed` object
        - `img_price` number: Image price
        - `avg_cost` number: Average cost
        - `price_type` string: Price type
        - `input_cost` number: Input cost
        - `output_cost` number: Output cost
      - `advertised` object
        - `img_json` object
          - `modelfamily` object: modelfamily will be the model type ie Flux, SD, SDXL, Dalle-3
            - `quality1` object: Image quality ie HD or SD
              - …
            - `quality2` object: Image quality ie HD or SD
              - …
        - `input_cache_read` number: Input cache read cost
        - `input_cache_write` number: Input cache write cost
        - `web_search` number: Web search cost
        - `internal_reasoning` number: Internal reasoning cost
        - `input_cost_per_token` number: Input cost per token
        - `output_cost_per_token` number: Output cost per token
        - `input_cost_per_token_batches` number: Input cost per token batches
        - `output_cost_per_token_batches` number: Output cost per token batches
        - `input_cost_per_audio_token` number: Input cost per audio token
        - `output_cost_per_audio_token` number: Output cost per audio token
        - `input_cost_per_audio_second` number: Input cost per audio second
        - `output_cost_per_audio_second` number: Output cost per audio second
        - `input_cost_per_video_per_second` number: Input cost per video per second
        - `output_cost_per_video_per_second` number: Output cost per video per second
        - `input_cost_per_character` number: Input cost per character
        - `output_cost_per_character` number: Output cost per character

---

[API](https://skmtc.dev/apipie/apis/introduction.md) · [All operations](https://skmtc.dev/apipie/apis/introduction/llms.txt) · [OpenAPI document](https://skmtc.dev/apipie/apis/introduction/revisions/f8386be4eb3f?raw)