ホーム
アセット
マイ作品
Models
ボイスライブラリ
開発者
ブログ
日本語
料金
ログイン
Models/Image/GPT-Image-2 Pro

OpenAI: GPT-Image-2 Pro

  • Text to image
  • Image to image
  • Multi-reference
  • Quality tiers
API referenceUse in AI画像生成エディタ

The official GPT-Image-2 channel, with one more quality setting than the standard one.

Instruction following and the reference-image ceiling match the standard channel; the difference is that setting and what it requires.

Strengths

  • One more quality setting than the standard channel
  • 1K / 2K / 4K

Limitations

  • High quality and 4K need a subscription
  • Four reference images

Capabilities

CapabilityValue
Text to imageYes
Image to imageYes
Multi-referenceYes
Precise edit–No
Quality tiersYes

Specs and limits

ParameterValue
Image size1K / 2K / 4K
Aspect ratio1:1 · 2:3 · 3:2 · 3:4 · 4:3 · 4:5 · 5:4 · 9:16 · 16:9 · 21:9
Reference images4
Quality tiersYes

How it is billed

按张计费，随尺寸档与质量变化

Standard pricesCredits
1K8
2K15
4K25

Figures come from the same estimator the generation form calls before you spend anything.

Alternatives

  • GPT-Image-2When that extra quality setting is not needed.

Call it

# Set LISTENHUB_API_KEY firstcurl -X POST "https://api.marswave.ai/openapi/v1/images/generation" \-H "Authorization: Bearer $LISTENHUB_API_KEY" \-H "Content-Type: application/json" \-d '{"provider": "google","model": "gpt-image-2-official","prompt": "A serene mountain landscape at sunset with a reflective lake","imageConfig": {"aspectRatio": "16:9"}}'
  • API reference
  • SDK & CLI
  • Agent Skills

Similar models

  • Nano Banana Pro
  • Nano Banana Flash
  • GPT-Image-2
  • GPT-Image-2.5 Flare
  • GPT-Image-2.5 Sunburst