Bonus

Chinese models Kimi-k3, Qwen3.8-max, and GLM-5.3 are now available at 50% off their official prices; GLM-5.3-flash and DeepSeek-V4.1-flash-1017 are available at 40% off their official prices.

Login
Models/Image/GPT Image 2

OpenAI: GPT Image 2

Visual generation route optimized for prompt fidelity and creative iteration.

Capability support
TText🖼Vision⚙Tools{}JSON⚡Streaming

Generation capabilities

Output specs and parameters this model supports

Supported sizes1024x1024, 1536x1024, 1024x1536, 2048x1152, 2048x2048, 3840x2160, 2160x3840, auto
Quality tierslow, medium, high, auto
Images per request2
Reference image (image-to-image)
Supported
Negative prompt
Not supported

Official pricing

The model's published list prices, used only as the comparison baseline for route pricing and discounts

Text input$5.001M
Image input$8.001M
Image output$30.001M
Text cache read$1.251M
Text cache write$0.00001M
Image cache read$2.001M
Image cache write$0.00001M

Available routes

Provider, public group, live pricing, latency, and uptime per active route

Provider / groupBilling pricesLatencyThroughputUptime
OpenAIGroup: OpenAI Image
Text input / 1M tokens$5.00
Image input / 1M tokens$8.00
Image output / 1M tokens$30.00
Image cache read / 1M tokens$2.00
Text cache read / 1M tokens$1.25
Latency1.8sThroughput—
Uptime