# GPT Image 2 is live on Kyma

Markdown version of https://kymaapi.com/blog/gpt-image-2-on-kyma, for agents and crawlers. Same content as the HTML page.

- Generated: 2026-10-09T21:45:05.556Z
- HTML page: https://kymaapi.com/blog/gpt-image-2-on-kyma
- Model catalog: https://kymaapi.com/models.md
- Pricing: https://kymaapi.com/pricing.md

2026-05-01 · 3 min read

OpenAI shipped **GPT Image 2** on April 22, 2026. We rolled it onto Kyma yesterday. If you've been hitting the wall on text inside generated images — logos that come out garbled, posters that mangle non-English script, screenshots that misspell their own headlines — this is the model you've been waiting for.

## See it before you read about it

```bash
# What you send
curl -X POST https://kymaapi.com/v1/images/generations \
  -H "Authorization: Bearer $KYMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A vintage tea brand poster reading \"KYMA TEA — since 2026\" in elegant serif typography, soft cream background, watercolor botanical illustration",
    "size": "1024x1024",
    "quality": "high"
  }'
```

Every letter readable. Em dash where it should be. Year correct. No retry loop, no manual touch-up in Photoshop. That's the upgrade.

## What changed

The previous-generation flagship (`gpt-image-1`) and the open-weight competition (FLUX, Recraft, Ideogram) all rendered text well *enough* — readable English, sometimes a typo, occasionally a missing letter. GPT Image 2 closes the gap to "photo of the real thing":

- **Multilingual text** — Japanese, Korean, Chinese, Hindi, Bengali, Arabic, Thai, and 25+ other scripts now render at the same fidelity as English. Useful if you ship product to anyone outside the US/UK.
- **Reasoning-augmented composition** — describe a chart, diagram, recipe card, or data visualization and the model figures out the layout before drawing it.
- **Higher resolution ceiling** — 2048×2048 supported on Kyma (4K available upstream; we'll add it when there's user demand).
- **Edit + mask support** — inpainting via the same endpoint with `image_url` (multipart upload coming next).

## Quality dropdown — the real innovation

OpenAI exposes three quality tiers in a single model: `low`, `medium`, and `high`. You pick per request, you pay only for what you use.

| Quality | 1024² price | What it's for |
|---|:-:|---|
| `low` | **$0.014** | Layout drafts, ideation, rapid A/B variations. ~19s. Costs less than the cheapest GIF stock site. |
| `medium` (default) | **$0.081** | Production output for most cases. ~30s. The picker default — same fidelity ceiling as flux-2-pro at a comparable price. |
| `high` | **$0.297** | Hero shots, marketing, anything user-facing. ~60s. Near-perfect text-in-image. |

A request with `quality: "high"` and `n: 3` (three variations) bills $0.891 — the hold books that exact amount up front, so there's no refund-and-rebill drift. Holds always match settles.

## Pick by your strongest constraint

| If you need… | Use |
|---|---|
| **Text in image** (logos, posters, packaging, ads, mockups) | `gpt-image-2` |
| **Multilingual text** at the same quality as English | `gpt-image-2` |
| **Photoreal humans** with multi-reference blending (up to 10 sources) | `flux-2-pro` |
| **Native SVG output** with editable paths and layers | `recraft-v4-vector` |
| **Print-ready 4MP** without paying gpt-image-2 high tier | `recraft-v4-pro` |
| **Sub-cent budget tier** for bulk generation | `minimax-image-01` |

[Picker positioning details on the model page →](/models/gpt-image-2)

## Provider isolation

OpenAI is the creator and the inference provider for `gpt-image-2`. Per our isolation policy, creator names are public — the model page shows OpenAI as the source. There is no relay layer and no hidden gateway. Pricing is a flat per-image rate per quality tier, published on the [pricing page](https://kymaapi.com/pricing).

## How to use it

Default works for most cases — pass `model: "gpt-image-2"` and you get `quality: "medium"` at $0.081/image. Opt into `low` for drafts, `high` for hero shots:

```python
from openai import OpenAI

client = OpenAI(
    api_key="kyma-your-kyma-key",
    base_url="https://kymaapi.com/v1",
)

# Hero asset
result = client.images.generate(
    model="gpt-image-2",
    prompt="...",
    size="1024x1024",
    quality="high",
    n=1,
)
print(result.data[0].url)  # Vercel blob URL, hosted on Kyma's CDN
```

The endpoint is async — POST returns `202` with a `job_id`; poll `GET /v1/jobs/{id}` until status is `succeeded`. Output is a Vercel blob URL hosted on Kyma's CDN, not an expiring OpenAI URL — no expiry to manage in your storage layer.

## What's next

Tomorrow we'll roll out the in-app composer's quality dropdown so picker users can switch tiers without dropping to the API. After that: image edit + mask support via multipart upload (`/v1/images/edits`), and the 4K resolution tier.

If you've been waiting for a model that takes typography seriously, [grab a key](https://kymaapi.com/signup) and try `quality: "high"` on something that's been failing on your other tools. `gpt-image-2` is outside the [free tier](https://kymaapi.com/pricing#free-tier), so the $0.50 signup credit does not reach it — add credits first.

— The Kyma team