> This page is for version v2 (default).
> For other versions, use one of these documentation indexes:
> - v2 (default): https://developer.ideogram.ai/v2/llms.txt
> - v1: https://developer.ideogram.ai/v1/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developer.ideogram.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developer.ideogram.ai/_mcp/server.

> Get the price of an Ideogram API request before it runs with dry_run. Read the PriceQuote response, compare a quote with the final charge, and estimate a batch.

Add `dry_run=true` to a request and the Ideogram API returns its price instead of running it. The request is validated and priced, but nothing is generated, stored or billed, and no safety review is performed. Send exactly the request you would send to generate, so the quote reflects the same options.

## Request a quote

`dry_run` is a query parameter. Everything else stays the same as the real request:

```bash
curl -X POST "https://api.ideogram.ai/v2/image/generate/ideogram-4-5?dry_run=true" \
  -H "Api-Key: $IDEOGRAM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "A ceramic mug on a wooden table, soft window light", "quality": "medium"}'
```

The response is a `PriceQuote` object in place of the endpoint's usual response. This one was returned on November 11, 2026:

```json
{
  "object": "price_quote",
  "billing_identifier": "ideogram_4_5_generate",
  "quantity": 1,
  "usd_micros": 60000,
  "credit_millis": 6000,
  "qualifier": "exact"
}
```

Prices change. See [API pricing](https://ideogram.ai/api-pricing) for current rates.

## The PriceQuote fields

| Field                    | Meaning                                                                                         |
| ------------------------ | ----------------------------------------------------------------------------------------------- |
| `object`                 | Always `price_quote`.                                                                           |
| `billing_identifier`     | The product the request would bill, such as `ideogram_4_5_generate`.                            |
| `quantity`               | The billable units the request would use, usually the number of images.                         |
| `usd_micros`             | The price in millionths of a US dollar. `60000` is \$0.06.                                      |
| `credit_millis`          | The charge for callers funded from credits, in thousandths of a credit at your own credit rate. |
| `qualifier`              | `exact` or `estimate`.                                                                          |
| `upper_bound_usd_micros` | The most the request can cost, in millionths of a US dollar. Not every quote includes it.       |

Money is in millionths of a dollar so you can compare a quote with `usage_cost_usd_micros` and your balance without rounding.

## How a quote relates to the final charge

* **An `exact` quote** is the price of that request at current prices. The price is fixed when Ideogram accepts the real request, so a price change between the quote and the request changes the charge.
* **An `estimate`** is for products whose final quantity is known only after the work runs. The final charge uses the actual quantity, up to `upper_bound_usd_micros`.
* **A quote doesn't check your account.** It doesn't look at your balance or your in-flight requests, so the real request can still return `402` or `429`. See [Errors and billing](/v2/ideogram-api/errors) and [Rate limits](/v2/ideogram-api/rate-limits).

After a request completes, compare the quote with what you were charged: `usage_cost_usd_micros` on [`GET /v2/generations/{generation_id}`](/v2/api-reference/generations/get-generation) (present when the request uses variable usage-based pricing) and [`GET /v2/account/usage`](/v2/api-reference/account/usage).

## Estimate a batch

Quote one representative request, then multiply. For 10,000 requests like the one above, each quoted at `usd_micros: 60000`:

10,000 × 60,000 = 600,000,000 millionths of a dollar, or \$600.

This is arithmetic, not a commitment. Requests with different options have different prices, so quote each kind of request you plan to send.

## Endpoints without dry_run

These operations don't take `dry_run`:

* `GET` endpoints, such as [`GET /v2/generations/{generation_id}`](/v2/api-reference/generations/get-generation) and the account endpoints
* `POST /v2/image/describe/ideogram-3` and `POST /v2/image/describe/ideogram-4`
* `POST /v2/tool/ad-variations`, `POST /v2/tool/model-pose-variants` and `POST /v2/tool/sketch-to-render`

An endpoint that takes `dry_run` can still answer `400` with "Price quotes are not available" for some requests. Each endpoint's reference lists its parameters.