Back to all models

GPT Image 1

OpenAI Platform · GPT Image

Available
Flagship
Latest in family

Key Metrics

Input Limit

N/A tokens

Output Limit

N/A tokens

Input Cost

$5.00/1M

Output Cost

$40.00/1M

Sample API Code

Required Libraries

Notes

GPT Image 1 is a new state-of-the-art image generation model, often the default choice for such tasks, characterized by high performance and slower speed. It is a natively multimodal language model that accepts both text and image inputs, and produces image outputs. Snapshots like 'gpt-image-1' allow locking in a specific model version for consistent performance.

Capabilities

multimodal language model
image generation
text input processing
image input processing
inpainting

Supported Data Types

Input Types

text
image

Output Types

image

Strengths & Weaknesses

Exceptional at

State-of-the-art image generation
High performance

Good at

Multimodal processing (text and image inputs to image outputs)
Inpainting

Poor at

Audio processing (not supported)
Relatively slower speed

Additional Information

Latest Update

Jan 1, 1970

Knowledge Cutoff

Similar Models