GPT Image 2 is OpenAI’s flagship image generation model, optimized for photorealistic outputs, multilingual text rendering, and logo-grade typography. Reach for it when you need high-fidelity image composition from text or image prompts with reliable lettering accuracy.
Modalities
Text+Image → Image
Price
$0.072 / image
Context
0K
Pricing
Per image. Async generation; you only pay for successful renders.
$0.072 / imageWhen to use GPT Image 2
Where this model earns its cost — and where it doesn't.
Released in April 2026, this model accepts text and image inputs to generate images at 1024×1024, 1024×1536, 1536×1024, or 2048×2048 resolutions. It features reasoning-augmented composition and supports low, medium, and high quality tiers, with medium as the default.
Kyma routes requests through an OpenAI-compatible endpoint using a single API key. The platform provides automatic failover if a serving path degrades, and every response returns the exact cost in the usage.cost field alongside an X-Kyma-Model header confirming the executed model. Prompt caching is supported, billing repeated prefixes at this model's cached input rate.
The model does not support structured outputs or reasoning capabilities. Generation speed is rated medium, and it operates strictly as an image-to-image or text-to-image generator without native text output capabilities.
Multilingual Typography Rendering
Generates accurate text overlays in multiple languages directly within generated images.
Photorealistic Scene Composition
Produces high-fidelity photographs and realistic environments from descriptive prompts.
Logo and Brand Asset Creation
Renders precise, logo-grade lettering and graphic elements suitable for branding workflows.
Reference Image Editing
Modifies existing images using text instructions while preserving core visual structure.
Not ideal for: Do not use this model if you require fast, low-latency generation, structured JSON outputs, or reasoning capabilities.
Quick start
Up and running in under two minutes.
- 1
Create an API key
Sign up and grab a key from the dashboard. GPT Image 2 needs a top-up — the signup credit covers the free tier.
Get API key → - 2
Make your first request
Submit a generation job and poll until it succeeds.
curl https://kymaapi.com/v1/images/generations \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-image-2", "prompt": "A serene mountain lake at sunrise, photorealistic", "n": 1 }' # Response: { "id": "img_...", "status": "queued" } # Poll: GET /v1/jobs/{id} until status="succeeded"
FAQ
Common questions about this model.
How much does GPT Image 2 cost?
How do I use GPT Image 2?
Does Kyma support prompt caching for this model?
What happens if the primary serving path fails?
Can I get structured outputs like JSON from this model?
More models by OpenAI
See all 12 →| Model | Context | Input | Output |
|---|---|---|---|
 GPT-6 Astra | 1M | $13.50 | $67.50 |
| GPT Transcribe | — | $0.006075 / min | |
| GPT-5.6 Terra | 1M | $2.70 | $16.20 |
| GPT-5.6 Luna | 1M | $0.27 | $1.62 |
| GPT-5.6 Luna Pro | 1M | $0.27 | $1.62 |
| GPT-5.6 Terra Pro | 1M | $2.70 | $16.20 |
| GPT-5.6 Sol | 1M | $2.70 | $13.50 |
| GPT-5.6 Sol Pro | 1M | $2.70 | $13.50 |