OpenAI's image generation and editing model with built-in O-series reasoning, up to 2K resolution, non-Latin text rendering, and batch generation of up to 8 images per prompt. Available via API as gpt-image-2.
Reasoning★
Reasoning
Multi-step reasoning★
Reasoning
Multilingual★
Language
Planning★
Planning
Token-based pricing. Input image tokens: $8/1M, cached: $2/1M, output: $30/1M. Text tokens: input $5/1M, output $10/1M. Batch API (asynchronous, up to 24h): 50% discount on input and output. Estimated cost per image (1024×1024): low ~$0.006, medium ~$0.053, high ~$0.211. At 1024×1536 (portrait) lower: low ~$0.005, medium ~$0.041, high ~$0.165.
INPUT
$5.0000 / per 1M tokens
OUTPUT
$10.0000 / per 1M tokens
CACHE
$1.2500 / per 1M tokens
TOTAL
for 10K tokens
Image tokens (image input/output). Editing with a reference image is billed at the image input token rate at maximum fidelity (high-fidelity), regardless of the quality parameter setting. Source: openai.com/api/pricing/
Tokens for text prompts. Cached text input: $1.25/1M. Source: openai.com/api/pricing/
Batch API — 50% discount on image tokens (input and output). Asynchronous processing up to 24 hours. Model quality is identical. Source: OpenAI API changelog and Batch API documentation.
Model available exclusively through OpenAI's cloud infrastructure (closed weights). Thinking mode and advanced features are restricted to paid plans (Plus, Pro, Business, Enterprise). API access requires OpenAI developer account verification; organizational verification may be required for full access to GPT Image models via API.
Technical information
The model enforces content policy at generation time — requests that violate the policy return a 400 error (BadRequestError) with a content_policy message. AI-generated content is tagged with AI metadata. Transparent background (PNG with alpha channel) is not supported in the Responses API tool option — use gpt-image-1.5 for that purpose. Free tier access is limited to standard/instant mode with a restricted number of generations (approximately 2 images/day per tester reports). Streaming, function calling, and structured outputs are not supported by the gpt-image-2 API (confirmed on the model's page).
