GPT Image 2.5 Is Here
Generate and edit images with OpenAI's GPT Image 2.5 Sunburst and Flare. Both add xhigh and max quality settings through the images API, chat completions, and Playground.
Precise image edits and everyday image generation need different tradeoffs. GPT Image 2.5 adds two OpenAI models to LLM Gateway: Sunburst for editing precision, and Flare for fast everyday generation. Both accept text and image inputs and work with your existing gateway API key.
Choose Your Model and Quality
| Model | Use it for |
|---|---|
openai/gpt-image-2.5-sunburst | Image generation and precise edits |
openai/gpt-image-2.5-flare | Fast everyday image generation and editing |
Both support low, medium, high, xhigh, max, and auto quality, with
square, landscape, portrait, and custom image sizes. The new xhigh and max
options are also available in the Playground.
1curl https://api.llmgateway.io/v1/images/generations \2 -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "openai/gpt-image-2.5-sunburst",6 "prompt": "A ceramic teapot on a sunlit kitchen table, editorial photography",7 "size": "1536x1024",8 "quality": "xhigh"9 }'1curl https://api.llmgateway.io/v1/images/generations \2 -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "openai/gpt-image-2.5-sunburst",6 "prompt": "A ceramic teapot on a sunlit kitchen table, editorial photography",7 "size": "1536x1024",8 "quality": "xhigh"9 }'Use /v1/images/edits to modify an existing image, or send
image_config.image_quality through /v1/chat/completions.
Both models use the same token rates as GPT Image 2. Image token consumption can differ, so requests are billed from the provider's reported usage. Check the models page for current pricing.