GPT Image 2Pricing & API costs
State-of-the-art image generation model
$0.006–$0.211
Low through high quality. Input tokens are billed separately.
Context window
400,000 tokens
Maximum output
Not published
Release date
Not published
API model ID
gpt-image-2Model overview
Understand the model before estimating your workload.
GPT Image 2 is OpenAI's image generation and editing model.
Text tokens: $5.00 input · $1.25 cached input · not published output per 1M tokens.
Image tokens: $8.00 input · $2.00 cached input · $30.00 output per 1M tokens. 1024x1024 images cost $0.006–$0.211 depending on quality.
Pricing
Rates are grouped by usage type and available tier.
Token rates
Text
Per 1M tokens
Input
$5.00
Cached input
$1.25
Output
Not published
Image
Per 1M tokens
Input
$8.00
Cached input
$2.00
Output
$30.00
Example image costs
Image size
1024x1024
Low
$0.006
Medium
$0.053
High
$0.211
Image size
1024x1536
Low
$0.005
Medium
$0.041
High
$0.165
Image size
1536x1024
Low
$0.005
Medium
$0.041
High
$0.165
How billing works
The details that turn a token rate into an actual bill.
Use the published billing unit
This model uses / 1M tokens, / 1M tokens. Do not substitute a text-token estimate for image, audio, video, or document charges.
Cache hits have their own rate
The listed cached-input price is $1.25 per million tokens. Reusing a prompt does not automatically qualify: use the provider's reported cached-token count, and account for any cache-write or storage charges.
Check discounts and rate tiers
No batch multiplier is applied to the examples on this page. Check the pricing source before assuming an asynchronous job receives a discount. Review the provider's pricing terms for workload-specific conditions.
Account for the complete workflow
Retries, follow-up calls, and agent tool loops increase request counts. Search, storage, and other tool charges can be billed separately from model inference. Use actual API usage logs to calibrate a budget before scaling traffic.
Capabilities and limits
What the API supports and where limits apply.
- Provider
- OpenAI
- Model type
- Image generation
- Access
- Direct API
- Modalities
- Text · Image
- Context window
- 400,000 tokens
- Max output
- Not published
- Released
- Not published
- Quality
- Low, Medium, High, Auto
- Supported sizes
- 1024x1024, 1536x1024, 1024x1536, 2048x2048, 2048x1152, 3840x2160, 2160x3840, Auto
- Version
- gpt-image-2-2026-04-21
- Max edge
- 3840px
- Aspect ratio
- 3:1
- Pixel range
- 655,360–8,294,400
- Transparent background
- Supported
- Partial image output
- 100 tokens
- Generation endpoint
- /v1/images/generations
- Edit endpoint
- /v1/images/edits
- Deprecation date
- Not announced
Compare API channels
Check the model ID, rate, and limit for each access route.
The same model can have a different ID, price, or output limit depending on how you access it. These are the channels currently tracked in this catalog; they are not a complete list of every hosting provider.
Image: $8.00 input · $2.00 cached input · $30.00 output / 1M tokens; Text: $5.00 input · $1.25 cached input / 1M tokens
Text: $5.00 input · $2.00 cached input / 1M tokens; Image: $8.00 input · $30.00 output / 1M tokens
Sources
Official pages and the date this information was checked.
- Last checked
- 2026-10-12
- Source links
- 3
Next step
Browse related models from this provider.
Frequently asked questions
According to OpenAI's pricing information dated 2026-10-12, a 1024x1024 image costs $0.006 on low quality, $0.053 on medium, and $0.211 on high.
GPT Image 2 supports low, medium, high, auto quality modes and popular sizes such as 1024x1024, 1536x1024, 1024x1536. The maximum edge length is 3840px and the aspect ratio limit is 3:1.
Yes. OpenAI documents GPT Image 2 on both /v1/images/generations for image generation and /v1/images/edits for image edits.
Yes. Transparent backgrounds are supported.
Recent updates
Output limit record updated.
View sourceAdded to the model directory.
View sourceModel details changed in the provider's documentation.
View source