# GPT Image 2 API — pricing & specs

GPT Image 2 is an OpenAI model that generates images from text prompts. On KeepRouter, GPT Image 2 costs $8.00 per 1M input tokens and $30.00 per 1M output tokens, billed pay-as-you-go with no monthly fee; actual request cost depends on measured token usage. Call it through a compatible KeepRouter endpoint supported by its active route, with the model id `gpt-image-2`.

| Spec | Value |
|---|---|
| Maker | OpenAI |
| Modality | Text-to-image |
| Input price | $8.00 per 1M tokens |
| Output price | $30.00 per 1M tokens |
| Capabilities | Image generation (text-to-image) |
| Endpoint | POST /v1/images/generations |
| Model id | `gpt-image-2` |

## Call it via images endpoint

Send image-generation requests to POST /v1/images/generations.

### cURL

```bash
curl https://keeprouter.com/v1/images/generations \
  -H "Authorization: Bearer $KEEPROUTER_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gpt-image-2","prompt":"a red bicycle on a beach"}'
```

### Python

```python
import os
from openai import OpenAI
client = OpenAI(base_url="https://keeprouter.com/v1", api_key=os.environ["KEEPROUTER_KEY"])
img = client.images.generate(model="gpt-image-2", prompt="a red bicycle on a beach")
```

### JavaScript

```js
const res = await fetch("https://keeprouter.com/v1/images/generations", {
  method: "POST",
  headers: { Authorization: "Bearer " + process.env.KEEPROUTER_KEY, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "gpt-image-2", prompt: "a red bicycle on a beach" }),
});
```

## Estimate API costs

At the current KeepRouter customer price, an example workload of 1,000 total input tokens, no cached input, and 500 output tokens per request costs approximately $0.0230 per request. At 100 requests per day, that is $69.00 over 30 days. This is a usage estimate, excluding processing fees, taxes, retries and application infrastructure. Actual usage, cache hits and supported generation durations need their own checks.

[Adjust quantities in the API cost calculator](/tools/api-cost-calculator?model=gpt-image-2).

## How to evaluate GPT Image 2

GPT Image 2 is listed on KeepRouter as text-to-image under the exact id `gpt-image-2`. Use /v1/images/generations for the listed route; a maker's upstream features do not automatically apply to this gateway endpoint. No context limit is asserted here because the exact upstream limit has not been verified for this catalog entry.

**First workload:** Generate a small batch from your real prompt and asset dimensions; review text rendering, composition, retry rate and cost per accepted image.

**Before production:** This is an image-generation route. Do not send it to chat completions or assume another router's image parameters are interchangeable.

## Public model usage evidence

No public, exact-variant usage figure has been verified for this KeepRouter model id. Missing data is not zero usage; family-level or maker-wide traffic is not presented as this model's traffic.

## Published examples and cases

### Image generation and editing examples

OpenAI's developer cookbook shows prompt and image-size examples for GPT Image 2. These are official examples, not a named customer's deployment. [OpenAI developer cookbook](https://developers.openai.com/cookbook/examples/multimodal/image-gen-models-prompting-guide).

## Source and verification boundary

[Official OpenAI website](https://openai.com/). KeepRouter's live catalog is authoritative for the customer price and enabled endpoint shown here; the maker remains authoritative for upstream model capabilities and limits.

## Pricing and implementation guides

- [Calculate your API workload cost](https://keeprouter.com/tools/api-cost-calculator)
- [KeepRouter API keys: move from free to paid models](https://keeprouter.com/blog/keeprouter-api-key-free-to-paid)

## Related models

- [GPT-OSS 120B](https://keeprouter.com/models/gpt-oss-120b.md) by OpenAI — $0.1500 per 1M input tokens and $0.6000 per 1M output tokens
- [GPT Image 1.5](https://keeprouter.com/models/gpt-image-1.5.md) by OpenAI — $8.00 per 1M input tokens and $32.00 per 1M output tokens
- [GPT-4o](https://keeprouter.com/models/gpt-4o.md) by OpenAI — $2.50 per 1M input tokens and $10.00 per 1M output tokens
- [GPT-6.1 Sol](https://keeprouter.com/models/gpt-6.1-sol.md) by OpenAI — $5.00 per 1M input tokens and $15.00 per 1M output tokens
- [GPT-5.5](https://keeprouter.com/models/gpt-5.5.md) by OpenAI — $5.00 per 1M input tokens and $30.00 per 1M output tokens
- [GPT-6 Sol](https://keeprouter.com/models/gpt-6-sol.md) by OpenAI — $5.00 per 1M input tokens and $15.00 per 1M output tokens

## More

- [All models & pricing](https://keeprouter.com/models.md)
- [Quickstart](https://keeprouter.com/docs/quickstart.md)
- [Get an API key](https://keeprouter.com/login?returnTo=%2Fconsole%2Fkeys%3Fmodel%3Dgpt-image-2)

_Catalog facts and prices last changed 2026-10-03._
_Page content reviewed 2026-09-28._