---
title: "Cost estimate for many models at once"
method: POST
path: "/v1/models/cost"
tags: ["models"]
---

# Cost estimate for many models at once

`POST /v1/models/cost`

## Request

- Base URL: `https://aicontentdrop.com`
- URL: `https://aicontentdrop.com/v1/models/cost`
- Auth: one of:
  - none
  - HTTP bearer

Quote up to 50 model/quantity pairs in one request. Read-only — it never starts a generation. An agent planning a batch would otherwise loop the single-model endpoint and spend its rate-limit budget on arithmetic. A bad line returns a per-item error instead of failing the whole batch.

## Request body

- object
  - `items` object[], required
    - `model_id` string, required
    - `quantity` integer

## Response `200`

Per-item quotes plus the batch total

- object
  - `count` integer, required
  - `credits_total` number, required: Sum across every item that resolved
  - `items` object[], required
    - `index` integer
    - `model_id` string
    - `name` string
    - `credits_each` number
    - `quantity` integer
    - `credits_total` number, nullable
    - `type` string
    - `error` object, nullable
      - `code` string
      - `message` string

## Other responses

- `400`: Missing or oversized items array
- `429`: Rate limited. Read Retry-After (header) or error.retry_after_seconds (body) — they carry the same number — and wait that long. Retrying sooner extends the window rather than shortening it.
- `500`: Unexpected failure on our side. Retry once; nothing was charged.

---

[API](https://skmtc.dev/aicontentdrop/apis/ai-content-drop-api.md) · [All operations](https://skmtc.dev/aicontentdrop/apis/ai-content-drop-api/llms.txt) · [OpenAPI document](https://skmtc.dev/aicontentdrop/apis/ai-content-drop-api/revisions/75a13a8043ae?raw)