---
title: "Get Model"
method: GET
path: "/models/{model}"
tags: ["Models"]
---

# Get Model

`GET /models/{model}`

## Request

- Base URL: `https://api.hedra.com/v3`
- URL: `https://api.hedra.com/v3/models/{model}`
- Auth: none required

## Path parameters

- `model` string, required: The model's public id (`GET /v3/models`).

## Response `200`

Successful Response

- ModelDetail
  - `id` string, required: The model's public id — the value POST /v3/models/{model} takes.
  - `modality` 'image' | 'video' | 'audio' | 'text', required: The kind of output a model produces — the axis `?modality=` filters on.
  - `name` string, nullable: Human-readable name.
  - `description` string, nullable: One-line summary of what the model does.
  - `price_description` string: Short USD pricing summary for this model. Exact cost depends on input.
  - `logo_url` string, nullable: URL of the provider's logo.
  - `context_length` integer, nullable: A chat model's context window in tokens; null for other models.
  - `max_output_tokens` integer, nullable: The largest `max_tokens` a chat model accepts; null for other models.
  - `input_schema` object: JSON Schema for this model's `input` object on submit — the same schema `GET /v3/models/{model}/openapi.json` embeds. For a chat model, the JSON Schema of the `POST /v3/chat/completions` request body as this model accepts it; a chat model has no per-model OpenAPI document.
  - `output_schema` object: JSON Schema of one item of a completed job's `outputs[]`. Empty for a chat model.
  - `chat` ChatCapabilities
    - `default_max_tokens` integer, required: The output bound of a request that sets neither `max_tokens` nor `max_completion_tokens`.
    - `pricing` ChatTokenPricing, required
      - `usd_per_1m_input_tokens` number, required: USD per million prompt tokens not served from cache. `price_description` states the cached rate where it differs.
      - `usd_per_1m_output_tokens` number, required: USD per million completion tokens, reasoning tokens included.
    - `input_modalities` string[], required: `text`, and `image` when the model accepts image parts.
    - `max_images_per_request` integer, nullable, required: The most image parts one request may contain; null when the model accepts no images.

## Other responses

- `400`: Invalid or failed-validation request.
- `403`: Insufficient scope or plan.
- `404`: Resource not found.
- `429`: Rate limit exceeded.
- `500`: Internal error.

## Changes

- **2026-10-16** `06692d16e78a`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/hedra-labs/apis/hedra-api/changes/models/:model/get.md)

---

[API](https://skmtc.dev/hedra-labs/apis/hedra-api.md) - [All operations](https://skmtc.dev/hedra-labs/apis/hedra-api/llms.txt) - [OpenAPI document](https://skmtc.dev/hedra-labs/apis/hedra-api/revisions/6ef35a11cefe?raw)